Paper Citation Record · LEDGER

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding

As of 8 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 4 inbound Pith citation observations for arXiv:2505.22135.

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

pith.paper-citation-record.v1
2505.22135 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:20:31.702035Z

measured 55 of 55 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T18:22:45.702572Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T18:25:00.050125Z

Reference resolution

51 of 51 outbound references displayed

verified exact1
verified fuzzy18
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b1d6a737-a5a7-4442-9199-b5d0eb899580 · outbound

This paper cites LongBench: A bilingual, multitask benchmark for long context understanding.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding LongBench: A bilingual, multitask benchmark for long context understanding

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:36.060030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3d0bfba0-6fbf-47d1-865a-ba680d1ea225 · outbound

This paper cites Puzzle: Distillation-Based NAS for Inference-Optimized LLMs.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Puzzle: Distillation-Based NAS for Inference-Optimized LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:26.989808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c9f6219-ef5a-41ae-815f-b24b6efb8679 · outbound

This paper cites On attention redundancy: A comprehensive study.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding On attention redundancy: A comprehensive study

Reference 3

Resolution: verified exact; doi, observed 2026-08-07T13:20:35.760682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 37df9508-f6c9-4ea0-a92a-8dd431c00551 · outbound

This paper cites Xing, J Zico Kolter, and Albert Gu.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Xing, J Zico Kolter, and Albert Gu

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:35.505508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b38696a6-12dd-4325-b989-cdd99ed49a36 · outbound

This paper cites Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:27.356000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff0ac070-64ca-4102-9d9f-9fcba4d176da · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Accelerating Large Language Model Decoding with Speculative Sampling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:27.450977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 363d877d-4e92-41a7-ac51-4bbce35aff6f · outbound

This paper cites GenQA: Generating Millions of Instructions from a Handful of Prompts.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding GenQA: Generating Millions of Instructions from a Handful of Prompts

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:27.547714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59bef50d-e274-414d-ab60-f4a43793b7e6 · outbound

This paper cites Streamlining redundant layers to compress large language models.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Streamlining redundant layers to compress large language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:27.628183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8753613a-08b4-4139-ba3d-9870820ea493 · outbound

This paper cites Stuffed mamba: State collapse and state capacity of rnn-based long-context modeling, 2024.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Stuffed mamba: State collapse and state capacity of rnn-based long-context modeling, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:27.719920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c5c7f89-39fa-4751-8e52-9cbae0213827 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Training Verifiers to Solve Math Word Problems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:27.892094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 384e185f-0837-47e5-b562-9587a6e48c20 · outbound

This paper cites Analyzing redundancy in pretrained transformer models.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Analyzing redundancy in pretrained transformer models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:28.023710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 583648ac-4682-4bdd-9aff-17ef39464327 · outbound

This paper cites Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Transformers are SSMs: Generalized models and efficient algorithms through structured state space duality

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:35.041855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cc73098e-1da3-4970-97b0-e7bf48a4461d · outbound

This paper cites Born again neural networks.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Born again neural networks

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:34.845967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 71bc3d20-18fb-46f7-8624-67b907939de3 · outbound

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

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding A framework for few-shot language model evaluation, September 2021

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:28.465318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10680adf-502b-468a-802e-fa5f7ad8fe13 · outbound

This paper cites Zamba: A Compact 7B SSM Hybrid Model.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Zamba: A Compact 7B SSM Hybrid Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:28.522002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ae875eb-0f81-4bda-88bb-554d104e26fd · outbound

This paper cites RADLADS: Rapid attention distillation to linear attention decoders at scale, 2025.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding RADLADS: Rapid attention distillation to linear attention decoders at scale, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:28.654716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c2edfd2-3690-4b7b-a3bf-b2f719c17cbf · outbound

This paper cites an unresolved cited work.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:20:34.597696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 505045e6-a7dd-4d84-98fe-510186747f4a · outbound

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

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:28.862191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 792ca933-5ff7-49ee-826d-caf3319ca0ea · outbound

This paper cites Combining recurrent, convolutional, and continuous-time models with linear state space layers.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Combining recurrent, convolutional, and continuous-time models with linear state space layers

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:28.974218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15bcccc1-c910-4cdc-baed-262a36cc83da · outbound

This paper cites Efficiently modeling long sequences with structured state spaces.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Efficiently modeling long sequences with structured state spaces

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:29.130322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04ea52e9-2045-47f9-9246-077abb6e75e4 · outbound

This paper cites CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:29.178468Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7e90854-c69a-4f0a-a85f-233c2ebb1f1e · outbound

This paper cites What Matters in Transformers? Not All Attention is Needed.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding What Matters in Transformers? Not All Attention is Needed

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:29.224634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc3a4e75-a77d-4ce1-9059-a8989c4d24dd · outbound

This paper cites Query-key normal- ization for transformers.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Query-key normal- ization for transformers

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:34.313400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation abe84c62-093f-46ab-8521-57e4a50b91b5 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Distilling the Knowledge in a Neural Network

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:29.459790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e47c749d-e5bd-42bd-983c-2e4954533252 · outbound

This paper cites Kakade, and Eran Malach.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Kakade, and Eran Malach

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:34.069698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 09b28262-294c-4137-b3e3-0ad36e27f9bb · outbound

This paper cites Fast inference from transformers via speculative decoding.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Fast inference from transformers via speculative decoding

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:33.771256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 75c86232-ff5e-4dd8-a5a0-b90bd121581f · outbound

This paper cites Jamba: A Hybrid Transformer-Mamba Language Model.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Jamba: A Hybrid Transformer-Mamba Language Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:29.796292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dda98709-d7ab-4e42-859f-828c0bf10a46 · outbound

This paper cites ZeroEval: A unified framework for evaluating language models, 2024.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding ZeroEval: A unified framework for evaluating language models, 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:33.495066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f53e4d36-c4fd-4546-b2f3-19cc08572a2b · outbound

This paper cites Longhorn: State Space Models are Amortized Online Learners.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Longhorn: State Space Models are Amortized Online Learners

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:29.988143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ad9e62b-be82-4353-ae17-d2abbba95ad4 · outbound

This paper cites ShortGPT: Layers in large language models are more redundant than you expect, 2024.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding ShortGPT: Layers in large language models are more redundant than you expect, 2024

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:33.250157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 889c22b1-ed36-471e-a1aa-f6dedd4dd1b1 · outbound

This paper cites Are sixteen heads really better than one? In Advances in Neural Information Processing Systems, volume 32, 2019.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Are sixteen heads really better than one? In Advances in Neural Information Processing Systems, volume 32, 2019

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:33.150611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7f12d9e6-c704-420a-933c-0f6509bec4c7 · outbound

This paper cites Compact Language Models via Pruning and Knowledge Distillation.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Compact Language Models via Pruning and Knowledge Distillation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:30.255508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ee686fd-fb30-4a8d-ae89-6a29e4acba5a · outbound

This paper cites Bayesian Optimization: Open source constrained global optimization tool for Python, 2014–.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Bayesian Optimization: Open source constrained global optimization tool for Python, 2014–

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:33.044723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d6b35deb-f0e0-445e-9e10-a7ed99dbd88e · outbound

This paper cites Infinity instruct.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Infinity instruct

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:32.936382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 72ced6b8-b35b-453a-b537-264ad8ee29d0 · outbound

This paper cites RWKV-7 "Goose" with Expressive Dynamic State Evolution.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding RWKV-7 "Goose" with Expressive Dynamic State Evolution

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:30.438474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 019756d4-33e6-40b8-8be0-e74ef74e8d78 · outbound

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

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Compressive Transformers for Long-Range Sequence Modelling

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:30.491759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1eaacc1-e7b1-4749-876b-ef971285a3f2 · outbound

This paper cites Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:30.608844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea3d994-b524-4a3b-b4c1-63a1a747d507 · outbound

This paper cites TAID: Temporally adaptive interpo- lated distillation for efficient knowledge transfer in language models.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding TAID: Temporally adaptive interpo- lated distillation for efficient knowledge transfer in language models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:32.852697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ec1d226a-ee4e-4caa-8427-5d7dc4317c79 · outbound

This paper cites TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:30.755203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 610db4f9-7003-4e02-a179-f5376252a4f0 · outbound

This paper cites Transformer Layers as Painters.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Transformer Layers as Painters

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:30.828566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab900abb-5524-4b8b-8cf8-d262fa74d6a1 · outbound

This paper cites OpenHermes 2.5: An open dataset of synthetic data for generalist LLM assistants, 2023.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding OpenHermes 2.5: An open dataset of synthetic data for generalist LLM assistants, 2023

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:32.764491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b904818a-7db9-4b9f-9bc3-172616b79537 · outbound

This paper cites Attention is all you need.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Attention is all you need

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:31.059850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 663bb92a-f0a8-4a5e-95a5-02ed4cb3d922 · outbound

This paper cites Rush, and Tri Dao.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Rush, and Tri Dao

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:32.646348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 35d6f519-5f1e-4140-8bb9-330f78d21323 · outbound

This paper cites an unresolved cited work.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:20:32.538808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 03735d46-1613-48b5-970a-3f4fed6f6db8 · outbound

This paper cites Parallelizing linear transformers with the delta rule over sequence length.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Parallelizing linear transformers with the delta rule over sequence length

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:32.403849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1aa69c5a-6049-4b7c-bf0f-4ca029f51e12 · outbound

This paper cites Gated delta networks: Improving Mamba2 with delta rule.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Gated delta networks: Improving Mamba2 with delta rule

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:32.287914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f5f05cd6-5fe4-4479-b4c4-e5edecafde18 · outbound

This paper cites KV cache compression, but what must we give in return? a comprehensive benchmark of long context capable approaches.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding KV cache compression, but what must we give in return? a comprehensive benchmark of long context capable approaches

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:20:32.147055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 893308ac-ba7d-42ad-97ec-976addc14d2c · outbound

This paper cites Root mean square layer normalization.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Root mean square layer normalization

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:31.661089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bdbaa1d-2463-486a-abd3-f3156652c70c · outbound

This paper cites Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:31.702035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06fca4ef-0e7b-4b0e-b5cd-da60bcd63155 · outbound

This paper cites an unresolved cited work.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding Unresolved cited work

Reference 398

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:20:35.277833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b9a285ad-0920-4b57-a372-21208309bb95 · outbound

This paper cites doi: 10.18653/v1/2024.acl-long.172.

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding doi: 10.18653/v1/2024.acl-long.172

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T13:20:26.876727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1979501e-7fdf-4a9e-a710-451b31732a64 · inbound

Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling cites this paper.

Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:01:10.802659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 697489d4-87b9-4603-9952-c15806008e35 · inbound

Component-Aware Self-Speculative Decoding in Hybrid Language Models cites this paper.

Component-Aware Self-Speculative Decoding in Hybrid Language Models RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:06:40.749250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bd2fc1fd-38a6-409a-8940-04dabbe38e7e · inbound

Post-Trained MoE Can Skip Half Experts via Self-Distillation cites this paper.

Post-Trained MoE Can Skip Half Experts via Self-Distillation RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:03:15.184871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6c0ae147-ab2a-483c-9629-e5dca0897884 · inbound

Post-Trained MoE Can Skip Half Experts via Self-Distillation cites this paper.

Post-Trained MoE Can Skip Half Experts via Self-Distillation RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-06-30T18:25:00.051504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.