A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding | Paper Citation Record

Observation b78001bd-079e-4453-a279-eb51dabebb7d · outbound

This paper cites Communication, Simulation, and Intelligent Agents: Implications of Personal Intelligent Machines for Medical Education.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Communication, Simulation, and Intelligent Agents: Implications of Personal Intelligent Machines for Medical Education

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.685796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5249efb-0a1d-438c-a971-5e9d4f56aa5c · outbound

This paper cites Classification Problem Solving.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Classification Problem Solving

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.690685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3950e816-c7f8-4fed-99ee-dc506280ef8a · outbound

This paper cites , title =.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding , title =

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.693874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ee90744-8d65-4dbd-9560-ccc9954c74df · outbound

This paper cites New Ways to Make Microcircuits Smaller---Duplicate Entry.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding New Ways to Make Microcircuits Smaller---Duplicate Entry

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.696750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b6cee3e-e2d5-4467-b253-beded9e48d1d · outbound

This paper cites Clancey and Glenn Rennels , abstract =.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Clancey and Glenn Rennels , abstract =

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.699800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fdb6238-b6d3-42b6-ac6e-65afab9fe0ba · outbound

This paper cites and Rennels, Glenn R.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding and Rennels, Glenn R

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.703165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee80a098-5fdc-454e-b18c-1b55c9cdf08f · outbound

This paper cites Poligon: A System for Parallel Problem Solving.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Poligon: A System for Parallel Problem Solving

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.706316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ace8db4-d389-48de-96ca-11f93128e46d · outbound

This paper cites Transfer of Rule-Based Expertise through a Tutorial Dialogue.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Transfer of Rule-Based Expertise through a Tutorial Dialogue

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.709251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d962f515-521a-4d50-8ee9-ccabadf057fd · outbound

This paper cites The Engineering of Qualitative Models.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding The Engineering of Qualitative Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.712600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8927db2-45a2-46ca-acf2-ec7208ed61e3 · outbound

This paper cites 2023 , eprint=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding 2023 , eprint=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.715367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 857768a7-5095-4343-90a6-febcfd26f0cd · outbound

This paper cites Pluto: The 'Other' Red Planet.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Pluto: The 'Other' Red Planet

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.718224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34dcf76b-da2c-4530-8be9-4a7a4f09813b · outbound

This paper cites OpenAI GPT-5 System Card.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding OpenAI GPT-5 System Card

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.720989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b3548c2-06b9-46ea-9d58-99149f477545 · outbound

This paper cites arXiv preprint arXiv:2601.11659 , year=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding arXiv preprint arXiv:2601.11659 , year=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.724133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fdef4bb-ad22-44df-abfe-383407aafd8a · outbound

This paper cites Advances in neural information processing systems , volume=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Advances in neural information processing systems , volume=

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.726858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f095b3c9-a935-4a28-8283-51f049bc1536 · outbound

This paper cites Advances in neural information processing systems , volume=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Advances in neural information processing systems , volume=

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.729841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d29ef71c-a039-4495-97ed-11aa9025a937 · outbound

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

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Fast Transformer Decoding: One Write-Head is All You Need

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.732407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5df6728f-23cf-4202-af4e-6ab08bfc3134 · outbound

This paper cites Proceedings of the 29th symposium on operating systems principles , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Proceedings of the 29th symposium on operating systems principles , pages=

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.735907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01beb76c-3809-4cff-9bf5-43da98132362 · outbound

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

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Accelerating Large Language Model Decoding with Speculative Sampling

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.738593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 847a6e12-d6e8-4c29-acbe-1a5ac423ab69 · outbound

This paper cites International Conference on Machine Learning , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding International Conference on Machine Learning , pages=

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.741803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9221c421-821a-4065-91aa-4c81f4ae347a · outbound

This paper cites Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3 , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3 , pages=

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.744653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e71874ae-f797-46f6-b80d-4b82e329605a · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Advances in Neural Information Processing Systems , volume=

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.747331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4231b8d1-eb2a-42bc-a6bf-0e6abc901ac4 · outbound

This paper cites Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.750071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff023fc6-d25c-48e4-906e-b4c6542fc948 · outbound

This paper cites Advances in neural information processing systems , volume=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Advances in neural information processing systems , volume=

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.753012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9adf66fa-fa70-452a-9719-71bc02c33e52 · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Efficient Streaming Language Models with Attention Sinks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.755862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01181eb5-b951-4be9-bcaa-2264d4d27346 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Advances in Neural Information Processing Systems , volume=

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.759285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7bebff3-3a4f-4bd9-bf5e-50bb492d3501 · outbound

This paper cites 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24) , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24) , pages=

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.761927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1cf1ce2-a857-4359-bc30-740dec244d6c · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Advances in Neural Information Processing Systems , volume=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.764546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09376490-6931-4b09-b849-a35fe24c8cc9 · outbound

This paper cites EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.767168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 717c86fc-242b-4dea-8406-f5364976aade · outbound

This paper cites EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.770082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a46b54ec-6ab4-4f90-8565-bbb28108d61c · outbound

This paper cites Better & Faster Large Language Models via Multi-token Prediction.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Better & Faster Large Language Models via Multi-token Prediction

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.772880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44627741-e9ec-4b81-a030-9d8a93c10901 · outbound

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

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.775717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34685473-2c52-4ada-8074-33d15d87d7c5 · outbound

This paper cites Online Speculative Decoding.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Online Speculative Decoding

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.778477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63f985f8-6ca4-4e31-b1bf-ad2607abdc89 · outbound

This paper cites RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding RAPID: Long-Context Inference with Retrieval-Augmented Speculative Decoding

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.781491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c7ba51d-07d8-42be-9d79-0aa6fcac4444 · outbound

This paper cites MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.784269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1666edf-d0fa-49f7-a70e-a030627fb026 · outbound

This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.787128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64863c10-0eac-4a3a-a0d8-8c760b7ad4b6 · outbound

This paper cites Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.789765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 586059d7-eb61-48cd-ba0c-75d5edefabbd · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.792566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c1f8247-a94b-4dcd-9d0f-bc8e9c11d4d6 · outbound

This paper cites Advances in neural information processing systems , volume=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Advances in neural information processing systems , volume=

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.795320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a56c88a4-e5c5-47d3-9db5-576379693dde · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.797987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 986d81b0-5350-4d83-adb7-b1ab4f274df0 · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2024 , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Findings of the Association for Computational Linguistics: ACL 2024 , pages=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.800851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11d286cb-7345-43a3-b217-d4b87c47c28b · outbound

This paper cites The Llama 3 Herd of Models.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding The Llama 3 Herd of Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.804140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4772a483-45c4-41c5-8126-2f02c4003b83 · outbound

This paper cites Qwen2.5-Coder Technical Report.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Qwen2.5-Coder Technical Report

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.807023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a8edb0c-f290-4ee3-b545-af735fa225d4 · outbound

This paper cites Advances in neural information processing systems , volume=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Advances in neural information processing systems , volume=

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.809898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 664647d4-b938-4171-9588-a309a5a4455c · outbound

This paper cites Advances in neural information processing systems , volume=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Advances in neural information processing systems , volume=

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.812427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aab47e77-9905-4e3b-8755-0e33208a28a6 · outbound

This paper cites Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations , pages=

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.815153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ebe6b02-9723-4de0-8acb-d61a06759eb1 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.817897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d915841-15af-42c6-9abb-d5fcebcf4438 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.820426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e9bfc5b-40a7-4b91-bce5-5bd1552012a3 · outbound

This paper cites PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.823026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c50ed756-db11-4cfe-bac4-210dbe89662d · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2024 , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Findings of the Association for Computational Linguistics: ACL 2024 , pages=

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.826169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18c996a0-48e2-4ed0-9777-aaed2d894823 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Advances in Neural Information Processing Systems , volume=

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.828798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7633c5e8-3293-4749-ac5a-d0fd741a5434 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Advances in Neural Information Processing Systems , volume=

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.831386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c1aa857-587a-4a6c-975c-7ccedd3094b7 · outbound

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

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.834122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c90dd767-134c-4b35-8e69-c481f9e5ddb5 · outbound

This paper cites arXiv preprint arXiv:2512.01278 , year=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding arXiv preprint arXiv:2512.01278 , year=

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.836964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 032fd074-5a64-481b-86ca-32e9d84ba27d · outbound

This paper cites Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Vegas: Self-Speculative Decoding with Verification-Guided Sparse Attention

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.839586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1525fea9-3a33-47b0-b838-9c9f3d06f47d · outbound

This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.842350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 696f17bb-ccea-4c23-8eea-c00687e69305 · outbound

This paper cites AdaEDL: Early Draft Stopping for Speculative Decoding of Large Language Models via an Entropy-based Lower Bound on Token Acceptance Probability.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding AdaEDL: Early Draft Stopping for Speculative Decoding of Large Language Models via an Entropy-based Lower Bound on Token Acceptance Probability

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.845296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12eca8ac-832f-4b00-b9ec-1bfd7669900a · outbound

This paper cites Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding Dynamic Speculation Lookahead Accelerates Speculative Decoding of Large Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.848394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f83ae6e1-016a-4640-ba94-e8d7910eb051 · outbound

This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.

A Sparse Glimpse of the Whole: Train-Free Self-Speculative Decoding RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-01T02:28:04.851282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers