Paper Citation Record · LEDGER

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

As of 7 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 4 inbound Pith citation observations for arXiv:2506.03700.

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

pith.paper-citation-record.v1
2506.03700 v1

Coverage vector

measured 71 of 71 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:02:39.419910Z

measured 75 of 75 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T04:16:08.552840Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T08:44:27.295523Z

Reference resolution

71 of 71 outbound references displayed

verified exact0
verified fuzzy27
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4bbd273e-ae5b-44cd-b242-8d013d4217c0 · outbound

This paper cites write newline.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.111163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e876ddf6-366d-4099-a62e-a32c355c1ba1 · outbound

This paper cites GPT-4 Technical Report.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism GPT-4 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.117325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa0354e5-809f-4963-96b7-b4e489d0721f · outbound

This paper cites Hydra: Sequentially-dependent draft heads for medusa decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Hydra: Sequentially-dependent draft heads for medusa decoding

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.542572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cc87aa4a-3646-4859-b130-69d357c602d1 · outbound

This paper cites Anthropic: Introducing claude 3.5 sonnet, 2024.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Anthropic: Introducing claude 3.5 sonnet, 2024

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.526458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 19c0759c-be96-4050-8989-a97eb1fd32cd · outbound

This paper cites Program Synthesis with Large Language Models.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Program Synthesis with Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.131952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d12a47-2d5d-44d4-8aea-3aee6179fd5d · outbound

This paper cites Fast and robust early-exiting framework for autoregressive language models with synchronized parallel decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Fast and robust early-exiting framework for autoregressive language models with synchronized parallel decoding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.136964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8914505-6fde-4fe7-8f1d-0292bec2367d · outbound

This paper cites LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.141519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dad9f962-f222-425e-8389-f2f82e441797 · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.146799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6d50787-59f9-4d9b-9fde-cbfb998908a9 · outbound

This paper cites D., Chen, D., and Dao, T.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism D., Chen, D., and Dao, T

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.499957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d6f76329-635d-4bdd-8141-deb9541e6a9e · outbound

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

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Accelerating Large Language Model Decoding with Speculative Sampling

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.155905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 517a3181-d6a9-43b6-b6a7-e03263455086 · outbound

This paper cites WAPITI: A Watermark for Finetuned Open-Source LLMs.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism WAPITI: A Watermark for Finetuned Open-Source LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.160378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2995c851-694e-414b-8043-b2cf4dc76ec0 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Evaluating Large Language Models Trained on Code

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.164777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06865bfe-f5cb-4986-bc51-0c98ec6ac986 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Training Verifiers to Solve Math Word Problems

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.169280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5ab56a2-a86e-48d8-aeee-ffb48ab8ecca · outbound

This paper cites Flashattention-2: Faster attention with better parallelism and work partitioning.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Flashattention-2: Faster attention with better parallelism and work partitioning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.173568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5a98939-fdc4-4245-b86f-46aa7c54c832 · outbound

This paper cites DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.177936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18e49189-a87c-4c21-9a4e-6006e3a73a7f · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.182650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8387e030-7012-406e-b94c-0a712bcafefc · outbound

This paper cites SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.187286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38732595-4509-47ae-922b-34fc6e2a3a39 · outbound

This paper cites QLoRA : Efficient finetuning of quantized LLMs.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism QLoRA : Efficient finetuning of quantized LLMs

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.474491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7b6071e4-831a-43f8-8200-da6fc141262c · outbound

This paper cites Jump to Conclusions: Short-Cutting Transformers With Linear Transformations.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Jump to Conclusions: Short-Cutting Transformers With Linear Transformations

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.197592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ab443d8-4c37-4ed2-881b-a094f71fe195 · outbound

This paper cites Glide with a cape: A low-hassle method to accelerate speculative decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Glide with a cape: A low-hassle method to accelerate speculative decoding

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.459979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 15e11d1e-e8f8-4514-815f-f1ae43ebe166 · outbound

This paper cites The Llama 3 Herd of Models.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism The Llama 3 Herd of Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.206389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e86cd2b5-5a9a-440d-be4c-034879542cfd · outbound

This paper cites Depth-adaptive transformer.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Depth-adaptive transformer

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.445245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a80e998c-4443-4ea8-adbe-f0323b900831 · outbound

This paper cites L ayer S kip: Enabling early exit inference and self-speculative decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism L ayer S kip: Enabling early exit inference and self-speculative decoding

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.430525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 201dc01e-7564-4e6e-a3fa-9b6a8a11b585 · outbound

This paper cites Break the sequential dependency of LLM inference using lookahead decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Break the sequential dependency of LLM inference using lookahead decoding

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.415153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bb14de1f-0ab4-4afb-8f6a-818d935ffdca · outbound

This paper cites Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.399611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 94f56415-7df1-433c-b465-91a8350e4ce4 · outbound

This paper cites rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.226807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bed347e-7dc9-447c-a58b-b38a6354fe65 · outbound

This paper cites REST : Retrieval-based speculative decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism REST : Retrieval-based speculative decoding

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.383163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a12cfdc8-b27b-4192-a2d0-6e48d50e6eb5 · outbound

This paper cites Training Compute-Optimal Large Language Models.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Training Compute-Optimal Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.235113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daff1876-b4f7-4876-b4fd-120090b0c010 · outbound

This paper cites The curious case of neural text degeneration.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism The curious case of neural text degeneration

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.366794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b54c427-bdf2-4722-a5b0-6f787aff1049 · outbound

This paper cites SPEED: Speculative Pipelined Execution for Efficient Decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism SPEED: Speculative Pipelined Execution for Efficient Decoding

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.243484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8031e3f1-13b2-4eed-8dad-9b94ecfa7908 · outbound

This paper cites E., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., and Chen, W.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism E., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., and Chen, W

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.351586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 92faf0a8-b416-4acc-8d08-63636b1f2689 · outbound

This paper cites Efficient Test-Time Scaling via Self-Calibration.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Efficient Test-Time Scaling via Self-Calibration

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.251956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b37d04a-8585-4b7f-9845-86a22812cabb · outbound

This paper cites Multi-scale dense networks for resource efficient image classification.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Multi-scale dense networks for resource efficient image classification

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.336787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c6ba6a95-54c5-4eb3-b122-6a9b5d7193e7 · outbound

This paper cites SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.260580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 757b7c6c-b126-4ce0-84d0-6d6d96164eeb · outbound

This paper cites A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.321949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 411e6a88-6391-4fd9-b649-592e0f0e39da · outbound

This paper cites Mixtral of Experts.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Mixtral of Experts

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.268868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ef25ad9-1f64-4dba-a51a-44173e48128e · outbound

This paper cites Sigsoftmax: Reanalysis of the softmax bottleneck.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Sigsoftmax: Reanalysis of the softmax bottleneck

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.307036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1b63bef3-2853-4021-818a-d4ccc8d5b4e0 · outbound

This paper cites Scaling Laws for Neural Language Models.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Scaling Laws for Neural Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.277280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 471210c7-f1bc-4815-8654-554b09d948a9 · outbound

This paper cites A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.281273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2beb81a9-c3c8-4764-a4ce-583a06234c48 · outbound

This paper cites W., Gholami, A., and Keutzer, K.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism W., Gholami, A., and Keutzer, K

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.285634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb7f8bf5-bb5c-4c31-981c-8a06f41d05cf · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.289715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ef55932-148c-41f3-9398-670a7691f026 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Adam: A Method for Stochastic Optimization

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.294461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9866707e-911f-403d-8b81-2558603b726e · outbound

This paper cites Fast inference from transformers via speculative decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Fast inference from transformers via speculative decoding

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.298736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94acec46-634f-44f3-b2e3-ff75c53c7aaa · outbound

This paper cites EAGLE : Speculative sampling requires rethinking feature uncertainty.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism EAGLE : Speculative sampling requires rethinking feature uncertainty

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.268093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8c182b05-b6c8-49b4-9489-3bab0d4c6b74 · outbound

This paper cites EAGLE -2: Faster inference of language models with dynamic draft trees.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism EAGLE -2: Faster inference of language models with dynamic draft trees

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.252446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4a3730a1-1a9a-448b-b099-e8041ad0a0d7 · outbound

This paper cites Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.310757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3e6d8d3-1059-4a40-b3e0-6c887e8ac97c · outbound

This paper cites Speculative decoding via early-exiting for faster LLM inference with T hompson sampling control mechanism.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Speculative decoding via early-exiting for faster LLM inference with T hompson sampling control mechanism

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.236346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 392f706e-b5d3-4f78-8388-c4441d6cd354 · outbound

This paper cites Online Speculative Decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Online Speculative Decoding

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.319649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d65e517c-e34b-44ef-8000-15ee09bcc21e · outbound

This paper cites SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.324065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13b92ac1-0853-49ca-b29a-7b46567ace67 · outbound

This paper cites Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.328762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 524c374e-19b6-41cb-94cf-db6ad6372692 · outbound

This paper cites SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.332990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbeac526-b188-40c9-92ca-a53d9fd3eff2 · outbound

This paper cites B., and Lapata, M.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism B., and Lapata, M

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.220011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6dbb81cc-5103-41ad-b311-0f9705e9b60f · outbound

This paper cites Introducing OpenAI o1: Learning to reason with large language models, 2024.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Introducing OpenAI o1: Learning to reason with large language models, 2024

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.205186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b5b52e0b-3b03-412f-8a18-be2363e6336d · outbound

This paper cites Suri: Multi-constraint Instruction Following for Long-form Text Generation.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Suri: Multi-constraint Instruction Following for Long-form Text Generation

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.345559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 137b5722-76e6-45f9-93f9-7dd36980ffda · outbound

This paper cites Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inference.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inference

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.349604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7d2b5b6-ba6f-4ae0-bd91-d6335a15b7d7 · outbound

This paper cites Zero: Memory optimizations toward training trillion parameter models.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Zero: Memory optimizations toward training trillion parameter models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.354357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00f1598f-a45e-45c9-8378-1ca46fde6337 · outbound

This paper cites Mixture-of-Depths: Dynamically allocating compute in transformer-based language models.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.358502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5b092e6-bafb-4015-b99a-ff921311b22b · outbound

This paper cites Confident adaptive language modeling.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Confident adaptive language modeling

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.363381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a47a6e7-9004-4fb9-af90-21d5e8a57ec0 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.367516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80b9a603-75a1-4c5a-9dc0-d52cb414d087 · outbound

This paper cites Blockwise parallel decoding for deep autoregressive models.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Blockwise parallel decoding for deep autoregressive models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.371960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f90a9b21-851c-4a9f-957b-736288df6d89 · outbound

This paper cites Branchynet: Fast inference via early exiting from deep neural networks.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Branchynet: Fast inference via early exiting from deep neural networks

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.376015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91e438b8-eb7b-48b9-9186-9aea743e3c0b · outbound

This paper cites Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Accelerating LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with LITE

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.380095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc2d3b77-700d-4849-9bce-2a0b5b5c1298 · outbound

This paper cites Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T11:02:39.384667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a266fe9-7a37-46dd-ac7d-0d2d051c1307 · outbound

This paper cites SWIFT : On-the-fly self-speculative decoding for LLM inference acceleration.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism SWIFT : On-the-fly self-speculative decoding for LLM inference acceleration

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.146961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3c447bb5-cafd-47be-b11f-5fc3ac132133 · outbound

This paper cites Sheared LLaMA : Accelerating language model pre-training via structured pruning.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Sheared LLaMA : Accelerating language model pre-training via structured pruning

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.131589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1b1fd645-bab9-4770-a385-c6b917c22b62 · outbound

This paper cites Predictive pipelined decoding: A compute-latency trade-off for exact LLM decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Predictive pipelined decoding: A compute-latency trade-off for exact LLM decoding

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.114487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 21a3dae6-973a-4857-968f-03fbbd74d4bf · outbound

This paper cites an unresolved cited work.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:02:40.097652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 99ec4d90-e5a2-4bc7-9b00-edef53252766 · outbound

This paper cites C o S afe: Evaluating large language model safety in multi-turn dialogue coreference.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism C o S afe: Evaluating large language model safety in multi-turn dialogue coreference

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.082567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1ab76d82-5c3e-4c69-b777-6e309c525fb3 · outbound

This paper cites L., Ma, Z., Xue, Y., Zhai, J., Chen, W., Liu, Z., Zhang, P., Dong, Y., and Tang, J.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism L., Ma, Z., Xue, Y., Zhai, J., Chen, W., Liu, Z., Zhang, P., Dong, Y., and Tang, J

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.066657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b43b1424-d65b-4f94-b3e4-c5ea393af016 · outbound

This paper cites Draft & verify: Lossless large language model acceleration via self-speculative decoding.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism Draft & verify: Lossless large language model acceleration via self-speculative decoding

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.051401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 98a08fef-5fd2-4b5e-a4e8-127f583d7fcc · outbound

This paper cites SafetyBench : Evaluating the safety of large language models with multiple choice questions.

AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism SafetyBench : Evaluating the safety of large language models with multiple choice questions

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:02:40.035083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation f6daaf60-f3ba-4e44-b348-d33c26c2b93a · inbound

HiSpec: Hierarchical Speculative Decoding for LLMs cites this paper.

HiSpec: Hierarchical Speculative Decoding for LLMs AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T13:15:30.182708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 475e5a31-0525-44da-9544-e3508eba031d · inbound

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration cites this paper.

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:00:58.697801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 642cdc18-96fd-4579-97ce-916b42d78cd2 · inbound

Depth Exploration for LLM Decoding cites this paper.

Depth Exploration for LLM Decoding AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T08:44:27.297075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ca429a9b-ae99-4be2-b3ba-6fe0e5517d08 · inbound

ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs cites this paper.

ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism

Reference 115

Resolution: unresolved; no resolver link, observed 2026-08-05T04:16:08.552840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.