Paper Citation Record · LEDGER

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

As of 5 August 2026, this Paper Citation Record lists 100 of 145 outbound references and 56 inbound Pith citation observations for arXiv:2306.14048.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2306.14048 v3

Coverage vector

measured 100 of 145 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-17T18:00:50.053377Z

measured 156 of 156 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 56 of 56 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T20:53:30.705096Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

100 of 145 outbound references displayed

verified exact59
verified fuzzy33
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch6

External citation measurements

28
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation fced8819-25a8-4397-bd21-65975ce0bbf6 · outbound

This paper cites LaMDA: Language Models for Dialog Applications.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models LaMDA: Language Models for Dialog Applications

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.150984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3723f9fa-8459-42e7-ba17-cd504a4ab633 · outbound

This paper cites Wordcraft: story writing with large language models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Wordcraft: story writing with large language models

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.585642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4f5a1443-9b46-4896-ab1a-eb93dc799768 · outbound

This paper cites Emergent Abilities of Large Language Models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Emergent Abilities of Large Language Models

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.130973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d3ac7804-4d5d-4b0a-88cc-9f74bfbf764d · outbound

This paper cites Benchmarking Large Language Models for News Summarization.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Benchmarking Large Language Models for News Summarization

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.137445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 56958681-84c9-4f80-a94e-4e5c691163df · outbound

This paper cites Efficiently Scaling Transformer Inference.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Efficiently Scaling Transformer Inference

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.145712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e43b65a3-9de0-43bb-8a64-3d1a37572feb · outbound

This paper cites An anomaly in space-time char- acteristics of certain programs running in a paging machine.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models An anomaly in space-time char- acteristics of certain programs running in a paging machine

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.556288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3f23259c-2217-4900-a171-ea4efa633e41 · outbound

This paper cites Reformer: The Efficient Transformer.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Reformer: The Efficient Transformer

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.403497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d04301a6-53f6-4b00-b006-2f96f081ba71 · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Flashattention: Fast and memory-efficient exact attention with io-awareness

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.562913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c0d05d41-8d81-40ff-ba0f-92bab4c0557d · outbound

This paper cites Generating Long Sequences with Sparse Transformers.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Generating Long Sequences with Sparse Transformers

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.407792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e3ff51cd-f292-404f-a82e-ff5464fed06d · outbound

This paper cites Rethinking Attention with Performers.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Rethinking Attention with Performers

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.411525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e29fab6c-c4d5-4e9f-9162-7fb3e13daf97 · outbound

This paper cites Transformers are rnns: Fast autoregressive transformers with linear attention.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Transformers are rnns: Fast autoregressive transformers with linear attention

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.574127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a0b8175c-e1ef-4d7f-bc10-19c7097ebbc8 · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Fast Transformer Decoding: One Write-Head is All You Need

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.415420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b6bc521f-0fb4-4bbc-9491-7624598cf83a · outbound

This paper cites PaLM: Scaling Language Modeling with Pathways.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models PaLM: Scaling Language Modeling with Pathways

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.419451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d777afda-dd71-4d88-8f07-8d34078906b2 · outbound

This paper cites Learning to Compress Prompts with Gist Tokens.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Learning to Compress Prompts with Gist Tokens

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.423410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bfe2969c-938c-4912-ad93-fad37f09316b · outbound

This paper cites A framework for few-shot language model evaluation, September 2021.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models A framework for few-shot language model evaluation, September 2021

Reference 15

Resolution: verified exact; doi, observed 2026-05-17T18:00:50.125201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e7f06c6e-425d-4089-b4da-5e359e40c414 · outbound

This paper cites Holistic Evaluation of Language Models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Holistic Evaluation of Language Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.427058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 39900118-976a-4971-8a9c-d9c4cbe878d9 · outbound

This paper cites DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.431176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 808935d7-d2ef-4e8b-bcc6-8b3a25a05233 · outbound

This paper cites Hugging face accelerate.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Hugging face accelerate

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.594043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ad34b387-962f-4c5c-8a3c-889b798ae04d · outbound

This paper cites FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.435347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c4f47523-3b41-446e-9406-cf3e323a1f4a · outbound

This paper cites SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.439584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f6d64c80-83b1-49e1-982d-3bf2c2709cd0 · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models A Simple and Effective Pruning Approach for Large Language Models

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.443610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 11843369-3084-452a-be33-b5b9ae8df156 · outbound

This paper cites Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.448044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation afcd2480-bf7c-4261-ae6a-cc7b2f109de8 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.452114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a2561729-235e-490c-aa35-b56b9a8c7dc2 · outbound

This paper cites SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.456232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 29d83d7a-d3a3-4d48-b1df-85a29bb200fd · outbound

This paper cites ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.460651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e2894113-913a-4245-bfea-768e0d9661f8 · outbound

This paper cites an unresolved cited work.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-05-17T18:00:50.615585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c79384c4-a832-403c-9ff4-e9d9df506b64 · outbound

This paper cites LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.465229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1d96aeed-1f0c-4b9f-89db-bfff5098ca6f · outbound

This paper cites AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.469602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e171e07a-bf43-456d-94fc-05f4222d9d15 · outbound

This paper cites CoLT5: Faster Long-Range Transformers with Conditional Computation.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models CoLT5: Faster Long-Range Transformers with Conditional Computation

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.473738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4da32423-fa58-431f-b363-29295125d054 · outbound

This paper cites Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.478057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4b4a1bac-4f88-491d-9e00-a224064295ab · outbound

This paper cites Efficient Transformers: A Survey.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Efficient Transformers: A Survey

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.482223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4fef8ba4-b828-43a2-bc4e-ce3ab5674094 · outbound

This paper cites Spatten: Efficient sparse attention architecture with cascade token and head pruning.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Spatten: Efficient sparse attention architecture with cascade token and head pruning

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.632000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 124d4f2d-c709-4ef8-9a2b-68823a89fb29 · outbound

This paper cites The lru-k page replacement algorithm for database disk buffering.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models The lru-k page replacement algorithm for database disk buffering

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.634555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a06881bd-7c08-4ab2-87c1-18cf95ca6c51 · outbound

This paper cites Lrfu: A spectrum of policies that subsumes the least recently used and least frequently used policies.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Lrfu: A spectrum of policies that subsumes the least recently used and least frequently used policies

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.637086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e16670d8-40d1-4f20-8134-227a63d0a8e5 · outbound

This paper cites On the Expressive Power of Self-Attention Matrices.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models On the Expressive Power of Self-Attention Matrices

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.487379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3cec6851-35f7-4026-8f75-32e1079bb50d · outbound

This paper cites Inductive biases and variable creation in self-attention mechanisms.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Inductive biases and variable creation in self-attention mechanisms

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.642232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation adf41e20-c616-497d-973a-5514eef02777 · outbound

This paper cites an unresolved cited work.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-05-17T18:00:50.644639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e4a8c8c6-f9b3-4021-aeb8-9c1db567286a · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models OPT: Open Pre-trained Transformer Language Models

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.491623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6060d875-e1e8-443b-a5fe-02b7e5d77e48 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.496470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b26b22c3-052a-48b3-b637-7204475c6d8b · outbound

This paper cites GPT- NeoX-20B: An open-source autoregressive language model.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models GPT- NeoX-20B: An open-source autoregressive language model

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.652714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 757ed7cf-6910-41e4-b61c-aed7646caff4 · outbound

This paper cites Choice of plausible alternatives: An evaluation of commonsense causal reasoning.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Choice of plausible alternatives: An evaluation of commonsense causal reasoning

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.655275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 04133704-8e88-4ac0-9c7c-4d32fde26b81 · outbound

This paper cites MathQA: Towards interpretable math word problem solving with operation- based formalisms.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models MathQA: Towards interpretable math word problem solving with operation- based formalisms

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.657985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bf96a834-9bf8-40e8-9d2d-fc2496f3bf18 · outbound

This paper cites Can a suit of armor conduct electricity? a new dataset for open book question answering.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Can a suit of armor conduct electricity? a new dataset for open book question answering

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.661003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cee97b64-2cea-4a2a-93ff-fc69196cea8a · outbound

This paper cites Piqa: Reasoning about physical commonsense in natural language.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Piqa: Reasoning about physical commonsense in natural language

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.663867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0dc83c89-93fa-4e34-895d-4a0f1158bf7a · outbound

This paper cites GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.501846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8ae21149-5e5c-4a9c-9c35-e3540ed94964 · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Winogrande: An adversarial winograd schema challenge at scale

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.669424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4f46ea0d-79d6-4bd0-878f-fc561fe7c2e3 · outbound

This paper cites Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.506635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 14aa63f3-2faa-467e-902c-0a4a6c849b10 · outbound

This paper cites Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.511095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c7a107ec-3c6d-415d-b91e-5df8870c6d2d · outbound

This paper cites Hashimoto.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Hashimoto

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.677381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4e444dd0-ec7e-4aef-8704-9dd9576650f9 · outbound

This paper cites P Xing, Hao Zhang, Joseph E.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models P Xing, Hao Zhang, Joseph E

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.679904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6b837594-07d8-4e69-a558-167ac31b889b · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Efficient Streaming Language Models with Attention Sinks

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.515409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1798dffb-aa43-4817-bb5e-e033a0ad4754 · outbound

This paper cites LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.520156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d338e598-f15b-4608-9ea8-b1a674e6ac14 · outbound

This paper cites Compressive transformers for long-range sequence modelling.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Compressive transformers for long-range sequence modelling

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.687807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 96dc0444-d38f-42ba-ad82-431d6e8032ca · outbound

This paper cites Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.525397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2bda1484-707f-48c3-a2a8-72b7f260e5a6 · outbound

This paper cites Quantization and training of neural networks for efficient integer-arithmetic-only inference.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Quantization and training of neural networks for efficient integer-arithmetic-only inference

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.693427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c604098a-7ab9-4bf8-9b79-670b776bd44a · outbound

This paper cites Data-free quantization through weight equalization and bias correction.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Data-free quantization through weight equalization and bias correction

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.696167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1b7d9ff6-7108-46ea-a452-4c2a6d13f6bb · outbound

This paper cites Improving neural network quantization without retraining using outlier channel splitting.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Improving neural network quantization without retraining using outlier channel splitting

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.698829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 87979139-e97b-4295-a87a-55ae02c0691f · outbound

This paper cites Pruning Convolutional Neural Networks for Resource Efficient Inference.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Pruning Convolutional Neural Networks for Resource Efficient Inference

Reference 59

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.530175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 25be5d4e-4748-42ae-a472-95f6c5e6d6b7 · outbound

This paper cites Rethinking the Value of Network Pruning.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Rethinking the Value of Network Pruning

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.533939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a05d7b55-b29d-4282-8852-ffbf71d4d74e · outbound

This paper cites Filter pruning via geometric median for deep convolutional neural networks acceleration.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Filter pruning via geometric median for deep convolutional neural networks acceleration

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.570428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 98d11d86-9fde-4f7d-bfae-0aeb5bedddd1 · outbound

This paper cites Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.577163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a009c789-57d3-490f-bf16-f8e6b17d94bd · outbound

This paper cites Distilling the Knowledge in a Neural Network.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Distilling the Knowledge in a Neural Network

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.537885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8aa88b96-59ea-429f-bb79-fd8912b2d21e · outbound

This paper cites On the efficacy of knowledge distillation.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models On the efficacy of knowledge distillation

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.582813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a9712fad-1422-4898-8d0e-7367cbdc2d1b · outbound

This paper cites Distilling Task-Specific Knowledge from BERT into Simple Neural Networks.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Distilling Task-Specific Knowledge from BERT into Simple Neural Networks

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.542178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c2c8b5e1-66a5-4ce5-9a41-efc7531c18d1 · outbound

This paper cites Training data-efficient image transformers & distillation through attention.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Training data-efficient image transformers & distillation through attention

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.591420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e8390ad4-7635-44b2-8896-d1cc38e39fa3 · outbound

This paper cites Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.596617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4c65e2f0-e722-4d16-84e1-9b0103f0ab98 · outbound

This paper cites Xlnet: Generalized autoregressive pretraining for language understanding.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Xlnet: Generalized autoregressive pretraining for language understanding

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.599309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4ab4ba32-40c3-4997-9fb8-2dd2edc23213 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 69

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.545885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 703db5f6-1c1f-4b45-b083-da9089f4ab36 · outbound

This paper cites CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge

Reference 70

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.549413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation efd5aa8f-f9b2-41f0-a21d-cf3c29ae43bc · outbound

This paper cites Radbert-cl: Factually-aware contrastive learning for radiology report classification.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Radbert-cl: Factually-aware contrastive learning for radiology report classification

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.607408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e76e8d3a-f596-4325-90de-809355d75a96 · outbound

This paper cites End-to-End Open-Domain Question Answering with BERTserini.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models End-to-End Open-Domain Question Answering with BERTserini

Reference 72

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.553208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 903a2c9d-2541-4e64-862f-7847b969b636 · outbound

This paper cites Cognitive Graph for Multi-Hop Reading Comprehension at Scale.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Cognitive Graph for Multi-Hop Reading Comprehension at Scale

Reference 73

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.157037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6fb9e946-9fdd-4fd8-84e5-501129283dac · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 74

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.164706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d25f4ad0-005d-4fdc-88b0-cc0173297700 · outbound

This paper cites Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.172211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dfeee84d-d826-487a-80c6-cc94337c6bac · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 76

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.178213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7d9be3ae-ad1f-485c-92b8-b9df6d7a6523 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Exploring the limits of transfer learning with a unified text-to-text transformer

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.626351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 16a09e60-44b7-4f4d-b57c-4a5c073adfef · outbound

This paper cites Language models are unsupervised multitask learners.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Language models are unsupervised multitask learners

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.629254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4aab7ce4-0c33-4628-910d-f61c63394e0a · outbound

This paper cites Language Models are Few-Shot Learners.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Language Models are Few-Shot Learners

Reference 79

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.185268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d482c76c-b353-463d-9ad6-509f7517b362 · outbound

This paper cites BLOOM: A 176B-Parameter Open-Access Multilingual Language Model.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Reference 80

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.191596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6ffdfec1-49ee-4537-b1be-83306ce40955 · outbound

This paper cites Why {adam} beats {sgd} for attention models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Why {adam} beats {sgd} for attention models

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.650074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 760fe633-d1de-41b2-9955-934cca7e5fef · outbound

This paper cites On the Variance of the Adaptive Learning Rate and Beyond.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models On the Variance of the Adaptive Learning Rate and Beyond

Reference 82

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.197627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 66847ad0-6d38-4560-ae74-b30dcff183ab · outbound

This paper cites Understanding the Difficulty of Training Transformers.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Understanding the Difficulty of Training Transformers

Reference 83

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.203271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cce7173d-6953-47a0-a782-e30cc4dd70f2 · outbound

This paper cites Sequence Length is a Domain: Length-based Overfitting in Transformer Models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Sequence Length is a Domain: Length-based Overfitting in Transformer Models

Reference 84

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.209655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2dbe6057-7d62-4600-8a9d-bd05107a1a9f · outbound

This paper cites MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecture.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models MixUp Training Leads to Reduced Overfitting and Improved Calibration for the Transformer Architecture

Reference 85

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.214877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7104600b-ecd1-47a6-b49e-23e38e36686c · outbound

This paper cites Very Deep Transformers for Neural Machine Translation.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Very Deep Transformers for Neural Machine Translation

Reference 86

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.219314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e471c91d-0620-49ac-8792-e22d2245e466 · outbound

This paper cites Optimizing Deeper Transformers on Small Datasets.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Optimizing Deeper Transformers on Small Datasets

Reference 87

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.223556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8d5c11b2-09c0-4f78-bf7f-96fdc1b07d41 · outbound

This paper cites Gradinit: Learning to initialize neural networks for stable and efficient training.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Gradinit: Learning to initialize neural networks for stable and efficient training

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.559772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0032da27-34b3-4abb-8f56-06ff0d7d7351 · outbound

This paper cites Adaptive Gradient Methods at the Edge of Stability.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Adaptive Gradient Methods at the Edge of Stability

Reference 89

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.228327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1298970c-a84f-4672-b77e-b7ccfaab61fa · outbound

This paper cites DeepNet: Scaling Transformers to 1,000 Layers.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models DeepNet: Scaling Transformers to 1,000 Layers

Reference 90

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.233161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9dfd760a-94af-45f0-a775-31971bab2e40 · outbound

This paper cites Unified Normalization for Accelerating and Stabilizing Transformers.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Unified Normalization for Accelerating and Stabilizing Transformers

Reference 91

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.238049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8f15ad49-108f-414b-a021-0a9611ce5088 · outbound

This paper cites Decoupled Weight Decay Regularization.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Decoupled Weight Decay Regularization

Reference 92

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.242148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 79a0ca9e-7588-42ed-94d0-45a741b57356 · outbound

This paper cites Texygen: A benchmarking platform for text generation models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Texygen: A benchmarking platform for text generation models

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T18:00:50.604446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c51fca5b-dc7f-40a9-9e39-e2dbd71c9b94 · outbound

This paper cites The case for 4-bit precision: k-bit Inference Scaling Laws.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models The case for 4-bit precision: k-bit Inference Scaling Laws

Reference 94

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.246733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 74fdee36-718d-4b7e-8127-48c05911f74e · outbound

This paper cites Lost in the Middle: How Language Models Use Long Contexts.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Lost in the Middle: How Language Models Use Long Contexts

Reference 95

Resolution: verified exact; local_arxiv, observed 2026-05-17T18:00:50.250976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9fa8c444-9829-4561-96ed-f8386aa535ac · outbound

This paper cites Improving Length-Generalization in Transformers via Task Hinting.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Improving Length-Generalization in Transformers via Task Hinting

Reference 96

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.255634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c781432c-cef1-452d-82e3-29929cc02250 · outbound

This paper cites KDEformer: Accelerating Transformers via Kernel Density Estimation.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models KDEformer: Accelerating Transformers via Kernel Density Estimation

Reference 97

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.259821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8fcd0d75-f433-47f3-9578-adac114f591d · outbound

This paper cites Fast Attention Requires Bounded Entries.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Fast Attention Requires Bounded Entries

Reference 98

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.263908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ba6430af-b61a-43c7-a14b-c1bd2c02d4b1 · outbound

This paper cites Superiority of softmax: Unveiling the perfor- mance edge over linear attention.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Superiority of softmax: Unveiling the perfor- mance edge over linear attention

Reference 99

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.268087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c20b00c4-9a48-4ab4-958e-49065139ff25 · outbound

This paper cites Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Algorithm and Hardness for Dynamic Attention Maintenance in Large Language Models

Reference 100

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.272467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bda7a126-8e8f-4c3f-ab0f-1e5290c0f36f · outbound

This paper cites Differentially Private Attention Computation.

H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models Differentially Private Attention Computation

Reference 101

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.277018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation feec9525-6ab2-4663-a649-4715699ec7d0 · inbound

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs cites this paper.

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 101

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4a3d8252-327e-4618-adde-2316e5aa7c97 · inbound

Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security cites this paper.

Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 267

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4e85d65c-a956-4369-a51a-b622d8611508 · inbound

Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads cites this paper.

Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 79

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7ef0a24a-5659-407d-ab9e-8d7e56027071 · inbound

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache cites this paper.

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e0d93067-594e-4c67-b3e8-1669083c43a0 · inbound

ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference cites this paper.

ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 85

Resolution: verified exact; local_arxiv, observed 2026-05-18T22:06:52.199866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 451a3792-123c-43ed-b4ce-a1a3e8bebde6 · inbound

EvolKV: Evolutionary KV Cache Compression for LLM Inference cites this paper.

EvolKV: Evolutionary KV Cache Compression for LLM Inference H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T20:53:30.705096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9edb87ef-4250-4a67-a241-c844189226b9 · inbound

AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs cites this paper.

AQUA: Attention via QUery mAgnitudes for Memory and Compute Efficient Inference in LLMs H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T17:05:55.044993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fedd7ea-92bc-4172-b79e-759a2ae14825 · inbound

StreamingVLM: Real-Time Understanding for Infinite Video Streams cites this paper.

StreamingVLM: Real-Time Understanding for Infinite Video Streams H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 460379ee-66f2-47ce-81a0-e9e4a38deb76 · inbound

SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators cites this paper.

SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 29

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T02:00:39.309134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dc8779f5-f211-470a-889f-0b7d1b844a05 · inbound

HieraSparse: Hierarchical Semi-Structured Sparse KV Attention cites this paper.

HieraSparse: Hierarchical Semi-Structured Sparse KV Attention H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 612e23a0-667f-4f2a-bfe7-d5a5e68a4096 · inbound

How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers cites this paper.

How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d9778a5d-f037-45b5-b7ed-275fd99b1dc1 · inbound

Sub-Token Routing in LoRA for Adaptation and Query-Aware KV Compression cites this paper.

Sub-Token Routing in LoRA for Adaptation and Query-Aware KV Compression H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 20

Resolution: malformed identifier; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6dcc36c8-7868-417d-9fa1-a832b85e323b · inbound

StreamIndex: Memory-Bounded Compressed Sparse Attention via Streaming Top-k cites this paper.

StreamIndex: Memory-Bounded Compressed Sparse Attention via Streaming Top-k H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4d9dd0f4-fb30-44b7-9600-e0670087ea54 · inbound

Sparse Prefix Caching for Hybrid and Recurrent LLM Serving cites this paper.

Sparse Prefix Caching for Hybrid and Recurrent LLM Serving H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f81c267e-9c5d-4df2-bddb-5efb08b6efc4 · inbound

Long Context Pre-Training with Lighthouse Attention cites this paper.

Long Context Pre-Training with Lighthouse Attention H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dfad0d42-ad98-4020-aff9-51d351f176ac · inbound

Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache cites this paper.

Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d1d313f6-5cca-4500-9a0b-e416e8a8d1de · inbound

MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference cites this paper.

MISA: Mixture of Indexer Sparse Attention for Long-Context LLM Inference H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 33

Resolution: malformed identifier; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8e979098-7055-442d-a249-2c94874684ca · inbound

Non-Monotonic Latency in Apple MPS Decoding: KV Cache Interactions and Execution Regimes cites this paper.

Non-Monotonic Latency in Apple MPS Decoding: KV Cache Interactions and Execution Regimes H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0f4dbb63-9d6e-4509-8090-2d4d91a71451 · inbound

Non-Monotonic Latency in Apple MPS Decoding: KV Cache Interactions and Execution Regimes cites this paper.

Non-Monotonic Latency in Apple MPS Decoding: KV Cache Interactions and Execution Regimes H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 70027ab9-2e09-4423-9509-cbeefd78c14b · inbound

KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving cites this paper.

KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dea92b0b-2cbf-4eae-b4a6-dfbcbf9ba75e · inbound

KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving cites this paper.

KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-07-01T08:15:32.399312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8da5e788-22d0-48ef-a47e-460901d27162 · inbound

Position: LLM Inference Should Be Evaluated as Energy-to-Token Production cites this paper.

Position: LLM Inference Should Be Evaluated as Energy-to-Token Production H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:00:50.699870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e1d1c753-1418-44e1-8c4f-16c66ae0c223 · inbound

Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction cites this paper.

Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-20T12:13:15.965477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ec502985-6103-4f4b-9e68-e96be8bde6e2 · inbound

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference cites this paper.

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T20:33:43.310155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c4e11073-0340-4e64-b1c0-b709f818a6e9 · inbound

Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression cites this paper.

Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-22T05:11:06.211932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 50ad4cce-033e-47b6-893d-fc662222f88f · inbound

Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression cites this paper.

Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-06-30T17:34:57.893200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1c2dbe2b-80bc-4848-8abb-ef09bc172cc9 · inbound

Asymmetric Virtual Memory Paging for Hybrid Mamba-Transformer Inference cites this paper.

Asymmetric Virtual Memory Paging for Hybrid Mamba-Transformer Inference H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:31:14.075975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1603240a-9912-424e-ab77-2db49318c433 · inbound

Tensor Cache: Eviction-conditioned Associative Memory for Transformers cites this paper.

Tensor Cache: Eviction-conditioned Associative Memory for Transformers H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-05-25T05:50:23.556008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c04370de-e76b-4b16-8202-3badc1fea4f4 · inbound

MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference cites this paper.

MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 21

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T21:56:15.437700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 79088eaa-ddf6-4dc8-9e64-dce54cd198cb · inbound

When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics cites this paper.

When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 29

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:36:26.502044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 528a05d2-c0aa-4009-bd68-960d11539a7f · inbound

STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control cites this paper.

STAR-KV: Low-Rank KV Cache Compression via Soft Thresholding for Adaptive Rank Control H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 24

Resolution: malformed identifier; local_arxiv, observed 2026-07-02T22:57:26.313384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e178fdff-db1e-43b1-b8e4-da8a5d514253 · inbound

From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs cites this paper.

From Rigid to Dynamic: Entropy-Guided Adaptive Inference for Long-Context LLMs H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-07-03T00:57:30.007634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e68c5b3e-86f5-43f5-b8a5-4fc28c006116 · inbound

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation cites this paper.

Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 46

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T22:16:16.031827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 158ebb36-a992-4fba-b6c1-450109e9e29d · inbound

Token-Operations-Oriented Inference Optimization Techniques for Large Models cites this paper.

Token-Operations-Oriented Inference Optimization Techniques for Large Models H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 119

Resolution: verified exact; local_arxiv, observed 2026-07-04T05:09:36.855256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 449ab3a9-829e-4209-ba79-2af93b3ce3ef · inbound

Token-Operations-Oriented Inference Optimization Techniques for Large Models cites this paper.

Token-Operations-Oriented Inference Optimization Techniques for Large Models H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 110

Resolution: unresolved; no resolver link, observed 2026-08-02T10:49:12.058991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3c1369b-9407-4761-857c-b34878ea43e1 · inbound

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems cites this paper.

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-07-04T11:09:46.366239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c2f2d99f-2b15-4d10-955b-2c12a5c545c5 · inbound

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems cites this paper.

The Hitchhiker's Guide to Agentic AI: From Foundations to Systems H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T10:27:16.272956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0a77d25-2fbb-4b60-8ebd-f1a608df33a8 · inbound

NLL-Guided Full-Attention Layer Selection for Training-Free Sliding-Window Adaptation cites this paper.

NLL-Guided Full-Attention Layer Selection for Training-Free Sliding-Window Adaptation H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T19:03:51.729138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation caca74ed-c51c-42e8-8073-eb52580cc987 · inbound

Self-GC: Self-Governing Context for Long-Horizon LLM Agents cites this paper.

Self-GC: Self-Governing Context for Long-Horizon LLM Agents H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-07-02T12:56:56.663672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 518fc120-1384-4891-97de-dfdf2b68554d · inbound

GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache cites this paper.

GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T15:57:06.413990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c635fc2e-1e08-43e7-aa12-e6e9b082e89f · inbound

A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets cites this paper.

A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 24

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T13:48:20.293431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation aadfd6ac-ad9f-4737-b53e-48ee66b6a92c · inbound

Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference cites this paper.

Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-11T12:14:57.342551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbabba66-681d-49da-94ca-209ab0006f30 · inbound

Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference cites this paper.

Fractal KV-Cache Archives: Lossless Symbolic Storage with In-Place Retrieval for Long-Context LLM Inference H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-09T19:16:27.755940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 746bd06e-4681-41d0-b4cd-74fc75a0c1c4 · inbound

Uncertainty-gated selection for block-sparse attention cites this paper.

Uncertainty-gated selection for block-sparse attention H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-11T22:15:14.580916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81edba1d-7309-4633-8653-88a48aef7398 · inbound

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents cites this paper.

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 152

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:36:44.151971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a0f4ba99-644a-4282-85a3-61dd127e2510 · inbound

COBS: Cumulant Order Block Sparse Attention cites this paper.

COBS: Cumulant Order Block Sparse Attention H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T00:42:31.008284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ad4a6c5-85d4-4cb3-8215-f8d4301d8a90 · inbound

Remembering Distinct Items, Not Tokens: A Learnable Dirichlet-Process Cache Between State-Space Models and Attention cites this paper.

Remembering Distinct Items, Not Tokens: A Learnable Dirichlet-Process Cache Between State-Space Models and Attention H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-14T14:50:03.831572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b3217b3-2592-4f26-b2a9-99c0ed3ca0af · inbound

Context by Distinct Information: An Auditable Dirichlet-Process Working Memory for Long, Redundant Context Streams cites this paper.

Context by Distinct Information: An Auditable Dirichlet-Process Working Memory for Long, Redundant Context Streams H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T11:45:09.424370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8da6e20-ac4c-47cb-a616-0b2d1539a9c7 · inbound

High-accuracy Low-Bit KV-Cache Quantization via Local Distribution Restoration cites this paper.

High-accuracy Low-Bit KV-Cache Quantization via Local Distribution Restoration H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T09:50:33.867996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afda2078-55a6-4cc4-8611-c8a56bff268e · inbound

Spectral-LSH: Sub-Quadratic Prompt Compression via Krylov-Projected Locality-Sensitive Hashing cites this paper.

Spectral-LSH: Sub-Quadratic Prompt Compression via Krylov-Projected Locality-Sensitive Hashing H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T11:37:06.681833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef1acaea-990d-4edb-a626-0a6250f2280b · inbound

Error Certificates for KV-Cache Eviction via Randomized Design cites this paper.

Error Certificates for KV-Cache Eviction via Randomized Design H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T07:23:41.286874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55408385-768d-40a8-beac-d6fba92b60d5 · inbound

Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV cites this paper.

Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-30T15:53:12.297457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8c939d8-4bd1-4484-ab15-52c782c9758d · inbound

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems cites this paper.

KAP: Bridging the Knowledge Selection-Runtime Consumption Gap in LLM Systems H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T19:52:42.379821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da916699-c32f-4568-b4f2-e95af5ce6ffa · inbound

GLIDE: Guided Layerwise Hybrid Attention for Efficient LLM Inference cites this paper.

GLIDE: Guided Layerwise Hybrid Attention for Efficient LLM Inference H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T09:52:42.742462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f88a5294-26f9-47bc-a198-3f1b586d5ccc · inbound

Beyond KV Reconstruction: Functional Reconstruction for MLA Draft Models in Speculative Decoding cites this paper.

Beyond KV Reconstruction: Functional Reconstruction for MLA Draft Models in Speculative Decoding H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T10:55:32.054239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8167e744-39cf-4f6a-ae47-76757129dbbe · inbound

WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization cites this paper.

WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T00:43:53.157830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.