Training Transformers for KV Cache Compressibility | Paper Citation Record

Observation 1cbf67cf-30da-48db-9871-2b97be1dc410 · outbound

This paper cites Can Foundation Models Help Us Achieve Perfect Secrecy?.

Training Transformers for KV Cache Compressibility Can Foundation Models Help Us Achieve Perfect Secrecy?

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:21.987477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation aef4b139-e3c5-4177-9b93-3923e41c6c8d · outbound

This paper cites Longbench v2: Towards deeper understanding and reason- ing on realistic long-context multitasks.

Training Transformers for KV Cache Compressibility Longbench v2: Towards deeper understanding and reason- ing on realistic long-context multitasks

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.294421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation b4d5c7da-b73d-4ec3-a51a-c821f65cb593 · outbound

This paper cites Longformer: The Long-Document Transformer.

Training Transformers for KV Cache Compressibility Longformer: The Long-Document Transformer

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:21.990094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 3493bf0e-5511-4291-a28e-3e97eaa32b7a · outbound

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

Training Transformers for KV Cache Compressibility PIQA: Reasoning about physical commonsense in natural language

Reference 4

Resolution: verified exact; doi, observed 2026-05-13T06:02:21.793734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 7be11d93-61c2-4889-b04b-0795f160ba40 · outbound

This paper cites an unresolved cited work.

Training Transformers for KV Cache Compressibility Unresolved cited work

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.289944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 9936c8c6-164c-45d0-93f7-f81526078cb2 · outbound

This paper cites PyramidKV: Dynamic kv cache compression based on pyramidal information funneling.

Training Transformers for KV Cache Compressibility PyramidKV: Dynamic kv cache compression based on pyramidal information funneling

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.287922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 66d1b34d-c5f2-42f7-8b5e-bc7920e8e19c · outbound

This paper cites Doc-to-lora: Learning to instantly internalize contexts.

Training Transformers for KV Cache Compressibility Doc-to-lora: Learning to instantly internalize contexts

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:21.959138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation a658111a-bcc5-49ea-9152-d1f6504481de · outbound

This paper cites Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models.

Training Transformers for KV Cache Compressibility Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:21.981495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 1eba9c7d-de47-40c9-8bcf-90e758f08cbd · outbound

This paper cites Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass.

Training Transformers for KV Cache Compressibility Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:21.953195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 3c77b851-8b43-40e8-9fbd-2e4dda0c619b · outbound

This paper cites Adapting language models to compress contexts.

Training Transformers for KV Cache Compressibility Adapting language models to compress contexts

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.285790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation d9c843de-99c1-4fab-9c12-28c8a18157f2 · outbound

This paper cites Rethinking Attention with Performers.

Training Transformers for KV Cache Compressibility Rethinking Attention with Performers

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:21.943990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 4db62a8c-2dd1-455a-a48d-c04e2aa53630 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Training Transformers for KV Cache Compressibility Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:21.967996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation f93f265d-ef37-4145-ac87-3a3901e4034c · outbound

This paper cites InProceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers).

Training Transformers for KV Cache Compressibility InProceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Reference 13

Resolution: metadata mismatch; doi, observed 2026-05-13T06:02:21.797274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation f84f24d0-bfe3-49f4-9a63-c1def112e4f3 · outbound

This paper cites Approximation by superpositions of a sigmoidal function.Mathematics of control, signals and systems, 2(4):303–314.

Training Transformers for KV Cache Compressibility Approximation by superpositions of a sigmoidal function.Mathematics of control, signals and systems, 2(4):303–314

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.278883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation dae1ed25-d9e0-412f-9bfd-c30c20856816 · outbound

This paper cites The centered convex body whose marginals have the heaviest tails.

Training Transformers for KV Cache Compressibility The centered convex body whose marginals have the heaviest tails

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:21.946969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 9e953d73-6031-42fc-9a30-726e1da7f055 · outbound

This paper cites Cartridges: Lightweight and general-purpose long context representations via self-study.

Training Transformers for KV Cache Compressibility Cartridges: Lightweight and general-purpose long context representations via self-study

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.283639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation b5a6d708-345a-4c78-bccf-c14a19e9d834 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Training Transformers for KV Cache Compressibility Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:21.997183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation fa307a39-d96e-414a-895a-048eb46a3527 · outbound

This paper cites Efficiently Modeling Long Sequences with Structured State Spaces.

Training Transformers for KV Cache Compressibility Efficiently Modeling Long Sequences with Structured State Spaces

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:21.984721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation af3ae607-84bb-4fd7-bb85-7ca3fc615b42 · outbound

This paper cites Lighte- val: A lightweight framework for llm evaluation.

Training Transformers for KV Cache Compressibility Lighte- val: A lightweight framework for llm evaluation

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.281046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 90d9039f-cf5f-484a-8221-1c221834db3b · outbound

This paper cites Delta-net: Real-time network verification using atoms.

Training Transformers for KV Cache Compressibility Delta-net: Real-time network verification using atoms

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.296958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 7eec02fd-e121-411b-a8aa-89dbac8dd5cb · outbound

This paper cites Approximation capabilities of multilayer feedforward networks.Neural networks, 4(2):251–257.

Training Transformers for KV Cache Compressibility Approximation capabilities of multilayer feedforward networks.Neural networks, 4(2):251–257

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.274052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 68a00469-4c6f-486a-9f23-033449813713 · outbound

This paper cites Dynamic Chunking for End-to-End Hierarchical Sequence Modeling.

Training Transformers for KV Cache Compressibility Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:02:21.965287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 9a326a7c-54ae-4f48-bf4c-838d0e8a0510 · outbound

This paper cites FinanceBench: A New Benchmark for Financial Question Answering.

Training Transformers for KV Cache Compressibility FinanceBench: A New Benchmark for Financial Question Answering

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-16T05:01:13.018607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 452ddc86-650e-4627-9d2e-738e064716b8 · outbound

This paper cites LLMLingua: Com- pressing prompts for accelerated inference of large language models.

Training Transformers for KV Cache Compressibility LLMLingua: Com- pressing prompts for accelerated inference of large language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.271575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 147a14f9-4813-44e6-8fc8-36fa5f80ccbd · outbound

This paper cites LongLLMLingua: Accelerating and enhancing llms in long context scenarios via prompt compression.

Training Transformers for KV Cache Compressibility LongLLMLingua: Accelerating and enhancing llms in long context scenarios via prompt compression

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.276579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 7b6c23f3-f5ff-4d25-a284-f34b0ee6cc09 · outbound

This paper cites Optimal experimental designs.The Annals of Mathemat- ical Statistics, 37(4):783–815.

Training Transformers for KV Cache Compressibility Optimal experimental designs.The Annals of Mathemat- ical Statistics, 37(4):783–815

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.269453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 7677d385-0243-47cc-85d4-c0dc0da6fdd1 · outbound

This paper cites Tchebycheff systems: With applications in analysis and statistics.(No Title).

Training Transformers for KV Cache Compressibility Tchebycheff systems: With applications in analysis and statistics.(No Title)

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.264839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 14256ac9-4194-45c5-81a1-37e532fa0702 · outbound

This paper cites Chebyshevian spline functions.Siam Journal on Numerical Analysis, 3(3):514–543.

Training Transformers for KV Cache Compressibility Chebyshevian spline functions.Siam Journal on Numerical Analysis, 3(3):514–543

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.267004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation dc366d46-17fc-4c89-9a35-3a056296534a · outbound

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

Training Transformers for KV Cache Compressibility Transformers are rnns: Fast autoregressive transformers with linear attention

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.260987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 265f9aee-8bae-4477-8744-baafd32ad3aa · outbound

This paper cites Kvzip: Query-agnostic kv cache compression with context reconstruction.

Training Transformers for KV Cache Compressibility Kvzip: Query-agnostic kv cache compression with context reconstruction

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:21.971227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 0c3ab234-0bc3-47c1-a830-35e95aba6680 · outbound

This paper cites Lexico: Extreme KV cache compression via sparse coding over universal dictionaries.

Training Transformers for KV Cache Compressibility Lexico: Extreme KV cache compression via sparse coding over universal dictionaries

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.254451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation d9c0c9a0-9b89-4abd-a86b-dc07dc7fb28c · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive NLP tasks.

Training Transformers for KV Cache Compressibility Retrieval-augmented generation for knowledge-intensive NLP tasks

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.256522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation b36181d0-9a4f-491d-9dbb-4544c41064c2 · outbound

This paper cites Compressing context to enhance inference efficiency of large language models.

Training Transformers for KV Cache Compressibility Compressing context to enhance inference efficiency of large language models

Reference 33

Resolution: malformed identifier; raw_fallback, observed 2026-05-13T06:02:24.258780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 0d344f97-1b95-470f-8156-b066ee485948 · outbound

This paper cites SnapKV: Llm knows what you are looking for before generation.

Training Transformers for KV Cache Compressibility SnapKV: Llm knows what you are looking for before generation

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.262982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation ced269bf-c1b2-4443-959a-8fa0189b7ab3 · outbound

This paper cites LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence.

Training Transformers for KV Cache Compressibility LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:21.993912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 89401e05-302f-4574-9d6f-221366601686 · outbound

This paper cites SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass.

Training Transformers for KV Cache Compressibility SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-05-21T03:03:41.308564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 628d164d-0462-476f-9b91-c95e952b6feb · outbound

This paper cites Pointer sentinel mixture models.

Training Transformers for KV Cache Compressibility Pointer sentinel mixture models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.292079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 8976502a-1931-45cc-a261-2796fd872c02 · outbound

This paper cites an unresolved cited work.

Training Transformers for KV Cache Compressibility Unresolved cited work

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.250037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation bd3951d8-cdd7-41c6-9b01-43f233d1d814 · outbound

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

Training Transformers for KV Cache Compressibility Can a suit of armor conduct electricity? a new dataset for open book question answering

Reference 39

Resolution: verified exact; doi, observed 2026-05-13T06:02:21.790714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation e313e9fa-7d48-4e25-b6fe-6b3a50bef301 · outbound

This paper cites Learning to compress prompts with gist tokens.

Training Transformers for KV Cache Compressibility Learning to compress prompts with gist tokens

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.235100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation e5718b8d-1ccb-478e-8d9b-d9a69704d022 · outbound

This paper cites Using an llm to help with code understanding.

Training Transformers for KV Cache Compressibility Using an llm to help with code understanding

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.220818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation c076a8b2-29b6-4f6a-a674-b13ac4d9bd53 · outbound

This paper cites Context Engineering - Short-Term Memory Management with Sessions from OpenAI Agents SDK, September 2025.

Training Transformers for KV Cache Compressibility Context Engineering - Short-Term Memory Management with Sessions from OpenAI Agents SDK, September 2025

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.223236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 436b9803-9b50-47e7-8d5a-f49bbe585cbc · outbound

This paper cites Transformers are multi-state RNNs.

Training Transformers for KV Cache Compressibility Transformers are multi-state RNNs

Reference 43

Resolution: verified exact; doi, observed 2026-05-13T06:02:21.803106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 393bdcbc-4be4-4d49-99d4-95bf24436637 · outbound

This paper cites The fineweb datasets: Decanting the web for the finest text data at scale.Advances in Neural Information Processing Systems, 37:30811–30849.

Training Transformers for KV Cache Compressibility The fineweb datasets: Decanting the web for the finest text data at scale.Advances in Neural Information Processing Systems, 37:30811–30849

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.227937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 4c76dc23-6216-4dfa-b833-1a6b6a2f153f · outbound

This paper cites Compressive Transformers for Long-Range Sequence Modelling.

Training Transformers for KV Cache Compressibility Compressive Transformers for Long-Range Sequence Modelling

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:46:17.004740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 40abb738-a348-46b4-aa94-045157a1adbb · outbound

This paper cites Effective context engi- neering for ai agents, September 2025.

Training Transformers for KV Cache Compressibility Effective context engi- neering for ai agents, September 2025

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.218665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 59cfac00-a8e9-4f9b-a166-4993e0673cf3 · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , author=.

Training Transformers for KV Cache Compressibility Proceedings of the AAAI Conference on Artificial Intelligence , author=

Reference 47

Resolution: verified exact; doi, observed 2026-05-13T06:02:21.786005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 1d3aa75c-7184-4ffb-8779-6622470094bd · outbound

This paper cites Representational strengths and limitations of transformers.Advances in Neural Information Processing Systems, 36:36677–36707.

Training Transformers for KV Cache Compressibility Representational strengths and limitations of transformers.Advances in Neural Information Processing Systems, 36:36677–36707

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.213905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation fe83771e-4d4a-471c-89e7-526400e0d2da · outbound

This paper cites Social IQa: Commonsense reasoning about social interactions.

Training Transformers for KV Cache Compressibility Social IQa: Commonsense reasoning about social interactions

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.225530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 3f357129-8531-4ade-8248-1d2c178f607b · outbound

This paper cites Social IQ a: Commonsense reasoning about social interactions.

Training Transformers for KV Cache Compressibility Social IQ a: Commonsense reasoning about social interactions

Reference 50

Resolution: metadata mismatch; doi, observed 2026-05-13T06:02:21.800181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation ce7ad80b-0f42-46bf-8ae6-71a8d92048bd · outbound

This paper cites QUEST: Query-aware sparsity for efficient long-context LLM inference.

Training Transformers for KV Cache Compressibility QUEST: Query-aware sparsity for efficient long-context LLM inference

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.252230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 3080a2c0-cb92-4ffd-81ed-a3fcae3bda5f · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Training Transformers for KV Cache Compressibility Qwen2.5: A party of foundation models, September 2024

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.204011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 8a2a4e3b-5597-493d-bd83-ac4725c3f36a · outbound

This paper cites Efficient streaming language models with attention sinks.

Training Transformers for KV Cache Compressibility Efficient streaming language models with attention sinks

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.208978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 0bd4eb5c-44b2-47f3-b70f-859d0874db08 · outbound

This paper cites DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads.

Training Transformers for KV Cache Compressibility DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:49:16.947404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 6113bfcc-ac39-448c-a9d4-21b8a1d1bba4 · outbound

This paper cites Gated Delta Networks: Improving Mamba2 with Delta Rule.

Training Transformers for KV Cache Compressibility Gated Delta Networks: Improving Mamba2 with Delta Rule

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-13T14:50:25.025022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation dc536cf1-3d8d-4043-b146-f4033d7e12e7 · outbound

This paper cites arXiv preprint arXiv:2407.15160 , year =.

Training Transformers for KV Cache Compressibility arXiv preprint arXiv:2407.15160 , year =

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:22.000080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 2bb92f07-362e-4e28-b0da-f1f7bf28eabe · outbound

This paper cites Deep sets.Advances in neural information processing systems, 30.

Training Transformers for KV Cache Compressibility Deep sets.Advances in neural information processing systems, 30

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.237288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 5cffa41d-2c43-4d58-931e-df3ed14a0102 · outbound

This paper cites Big bird: Transformers for longer sequences.Advances in neural information processing systems, 33: 17283–17297.

Training Transformers for KV Cache Compressibility Big bird: Transformers for longer sequences.Advances in neural information processing systems, 33: 17283–17297

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.230077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 6557247c-93a1-4764-9f98-24dfbadeb32a · outbound

This paper cites URL https:// doi.org/10.18653/v1/p19-1472.

Training Transformers for KV Cache Compressibility URL https:// doi.org/10.18653/v1/p19-1472

Reference 59

Resolution: verified exact; doi, observed 2026-05-13T06:02:21.806038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 78c43fa5-9a10-49a3-84fc-d3d4cf794a20 · outbound

This paper cites H2O: Heavy-hitter oracle for efficient generative inference of large language models.

Training Transformers for KV Cache Compressibility H2O: Heavy-hitter oracle for efficient generative inference of large language models

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.216232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 7444f49f-cb4e-4adb-83e3-5f870f1a0af6 · outbound

This paper cites Lifelong learning of large language model based agents: A roadmap.IEEE Transactions on Pattern Analysis and Machine Intelligence.

Training Transformers for KV Cache Compressibility Lifelong learning of large language model based agents: A roadmap.IEEE Transactions on Pattern Analysis and Machine Intelligence

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.232644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 7b4e5337-878f-4ec0-a002-6601849bdb1c · outbound

This paper cites Fast kv compaction via attention matching.

Training Transformers for KV Cache Compressibility Fast kv compaction via attention matching

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.244984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation c6758ec7-0854-4dcb-8ee1-936b6165bf6a · outbound

This paper cites an)∈A n withn≤N, ∥f(a)−M(a)∥< ε.(70).

Training Transformers for KV Cache Compressibility an)∈A n withn≤N, ∥f(a)−M(a)∥< ε.(70)

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.247803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 65356efd-af18-492c-b640-be94d32de4c7 · outbound

This paper cites an unresolved cited work.

Training Transformers for KV Cache Compressibility Unresolved cited work

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.206400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation 7ac604d7-f5e5-41b1-a5f0-4b3f2221255f · outbound

This paper cites an)∈A n withn≤N, ∥f(a)−M(a)∥< ε.(97).

Training Transformers for KV Cache Compressibility an)∈A n withn≤N, ∥f(a)−M(a)∥< ε.(97)

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T06:02:24.211502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Observation a0c110ff-ee9b-45a9-8cad-83a1c8769821 · outbound

This paper cites By the same argument as in the proof of Lemma A.7, there exist functions ϕ:R d0 →R d1 andρ:R d1 →R dout such that for everya= (a 1.

Training Transformers for KV Cache Compressibility By the same argument as in the proof of Lemma A.7, there exist functions ϕ:R d0 →R d1 andρ:R d1 →R dout such that for everya= (a 1

Reference 66

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:21.950355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-22T06:31:00.163083+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers