Training-Free Hashing-Based Attention via Binary Principal Components | Paper Citation Record

Observation 98bd1211-0457-40bf-8c2d-bd5821c1b941 · outbound

This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=.

Training-Free Hashing-Based Attention via Binary Principal Components Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.566385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3e34aa05-262a-4fff-b25f-0ed524695119 · outbound

This paper cites Claude-3 Model Card , volume=.

Training-Free Hashing-Based Attention via Binary Principal Components Claude-3 Model Card , volume=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:44.671883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1329a8a8-27d4-4f34-913e-85536512e153 · outbound

This paper cites Proceedings of machine learning and systems , volume=.

Training-Free Hashing-Based Attention via Binary Principal Components Proceedings of machine learning and systems , volume=

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:44.838100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f68cde1-2560-4273-8b87-52d868cac273 · outbound

This paper cites Model Tells You What to Discard: Adaptive.

Training-Free Hashing-Based Attention via Binary Principal Components Model Tells You What to Discard: Adaptive

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:45.019470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dac62c12-18bc-4900-9fd3-b24fa6d62178 · outbound

This paper cites an unresolved cited work.

Training-Free Hashing-Based Attention via Binary Principal Components Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:45:49.524891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ae09cead-d01e-4dde-b7df-fe84a405500a · outbound

This paper cites an unresolved cited work.

Training-Free Hashing-Based Attention via Binary Principal Components Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:45:49.510510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 87db65a8-a421-4b90-b996-bdee82f935d2 · outbound

This paper cites an unresolved cited work.

Training-Free Hashing-Based Attention via Binary Principal Components Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:45:49.489837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3e43558a-cc1c-4f6e-8fdd-6ded987c46b0 · outbound

This paper cites Thirty-seventh Conference on Neural Information Processing Systems , year=.

Training-Free Hashing-Based Attention via Binary Principal Components Thirty-seventh Conference on Neural Information Processing Systems , year=

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:45.340059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eb4dbe8-d238-4a5c-b6ef-387b04cc12a6 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year=.

Training-Free Hashing-Based Attention via Binary Principal Components The Twelfth International Conference on Learning Representations , year=

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:45.509378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d64bcbe5-ad45-470b-a8a0-ebfd482cd988 · outbound

This paper cites Proceedings of Machine Learning and Systems , volume=.

Training-Free Hashing-Based Attention via Binary Principal Components Proceedings of Machine Learning and Systems , volume=

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.456470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a983a3d5-76b3-4114-a28d-332c51f31587 · outbound

This paper cites an unresolved cited work.

Training-Free Hashing-Based Attention via Binary Principal Components Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:45:49.442209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b36d195e-eb79-44ea-b867-9c4b4a0b61b1 · outbound

This paper cites an unresolved cited work.

Training-Free Hashing-Based Attention via Binary Principal Components Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:45:49.429414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bef283cd-a4c6-4a8d-a680-4c2923e4a5e5 · outbound

This paper cites Spotlight Attention: Towards Efficient.

Training-Free Hashing-Based Attention via Binary Principal Components Spotlight Attention: Towards Efficient

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.416295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cef7a563-2c41-4001-b4ec-366481c6ce39 · outbound

This paper cites FlashAttention: Fast and Memory-Efficient Exact Attention with.

Training-Free Hashing-Based Attention via Binary Principal Components FlashAttention: Fast and Memory-Efficient Exact Attention with

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:45.836639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bb71fa0-ea82-451e-a745-8b98a46e61e7 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year=.

Training-Free Hashing-Based Attention via Binary Principal Components The Twelfth International Conference on Learning Representations , year=

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:45.931473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 492a6cd4-c8a6-4357-92c8-d9c51657d321 · outbound

This paper cites International Conference on Learning Representations , year=.

Training-Free Hashing-Based Attention via Binary Principal Components International Conference on Learning Representations , year=

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:45.999066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9771ca1-8f7a-447a-b98e-8ef91035aa19 · outbound

This paper cites 2023 , eprint=.

Training-Free Hashing-Based Attention via Binary Principal Components 2023 , eprint=

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:46.124148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f2597f7-6c5f-4a31-8fa9-67b54193540a · outbound

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

Training-Free Hashing-Based Attention via Binary Principal Components Proceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:46.352439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd6ef8b9-09e9-45a3-aeec-89fc978e05f0 · outbound

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

Training-Free Hashing-Based Attention via Binary Principal Components Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:46.426634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 702c9da4-8052-40ea-a6db-2a3c05463a4a · outbound

This paper cites International Conference on Learning Representations , year=.

Training-Free Hashing-Based Attention via Binary Principal Components International Conference on Learning Representations , year=

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:46.532884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0b8689c-2a56-412b-9596-6032009fe2c4 · outbound

This paper cites Transactions of the Association for Computational Linguistics , volume=.

Training-Free Hashing-Based Attention via Binary Principal Components Transactions of the Association for Computational Linguistics , volume=

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:46.601006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d373459a-e353-4141-9c04-78f0841c5c15 · outbound

This paper cites an unresolved cited work.

Training-Free Hashing-Based Attention via Binary Principal Components Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:45:49.326839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f53e6ef9-51b0-4d9c-ac96-765af8e13b58 · outbound

This paper cites Forty-second International Conference on Machine Learning , year=.

Training-Free Hashing-Based Attention via Binary Principal Components Forty-second International Conference on Machine Learning , year=

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:46.848913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0429fe5-2587-461a-8efb-c96b9c003402 · outbound

This paper cites Github repository: hoskison-center/proof-pile.

Training-Free Hashing-Based Attention via Binary Principal Components Github repository: hoskison-center/proof-pile

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.303081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2ab00192-8e2d-46c0-b242-74b42dcc2205 · outbound

This paper cites Huggingface dataset: namespace-pt/long-llm-data.

Training-Free Hashing-Based Attention via Binary Principal Components Huggingface dataset: namespace-pt/long-llm-data

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.289011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 62f3b984-ea25-4934-bb55-47ea276c57c6 · outbound

This paper cites doi:10.5281/zenodo.12608602 , url =.

Training-Free Hashing-Based Attention via Binary Principal Components doi:10.5281/zenodo.12608602 , url =

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:47.235596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82347311-c9ee-4eb5-adc6-c99fd737f4a9 · outbound

This paper cites Needle In A Haystack - Pressure Testing LLMs.

Training-Free Hashing-Based Attention via Binary Principal Components Needle In A Haystack - Pressure Testing LLMs

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.275138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ca7ac0a0-b7a3-4214-8ef9-16af23f6ba61 · outbound

This paper cites GPT-4 Technical Report.

Training-Free Hashing-Based Attention via Binary Principal Components GPT-4 Technical Report

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:47.445113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5de07a54-a4da-4290-8108-891ec18b6d44 · outbound

This paper cites J., Soloveychik, I., and Kamath, P.

Training-Free Hashing-Based Attention via Binary Principal Components J., Soloveychik, I., and Kamath, P

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.261734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 487b2b72-6cff-4e2c-9f99-534e5777f3da · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.

Training-Free Hashing-Based Attention via Binary Principal Components The claude 3 model family: Opus, sonnet, haiku

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.247793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0c80b8ad-8250-4faf-a108-1d1451c2b132 · outbound

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

Training-Free Hashing-Based Attention via Binary Principal Components Longbench: A bilingual, multitask benchmark for long context understanding

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:47.723353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3c744f0-b0f9-480e-bcf0-c39315548fc2 · outbound

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

Training-Free Hashing-Based Attention via Binary Principal Components Longbench v2: Towards deeper understanding and reasoning on realistic long-context multitasks

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:47.847487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bb237ad-973d-452e-9a08-e2fbb38702ed · outbound

This paper cites Pyramid KV : Dynamic KV cache compression based on pyramidal information funneling.

Training-Free Hashing-Based Attention via Binary Principal Components Pyramid KV : Dynamic KV cache compression based on pyramidal information funneling

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.213802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2eabe147-6e65-4048-8950-a6f1379915e2 · outbound

This paper cites Magic PIG : LSH sampling for efficient LLM generation.

Training-Free Hashing-Based Attention via Binary Principal Components Magic PIG : LSH sampling for efficient LLM generation

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.198514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 081e11f3-47ef-4eed-8037-03d30156e423 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Training-Free Hashing-Based Attention via Binary Principal Components Training Verifiers to Solve Math Word Problems

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.223022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a4b8387-d5da-4c51-afe2-882926edbced · outbound

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

Training-Free Hashing-Based Attention via Binary Principal Components Flashattention-2: Faster attention with better parallelism and work partitioning

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.185400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b48affb5-10e3-47a4-87b4-0c3cc6309661 · outbound

This paper cites Y., Ermon, S., Rudra, A., and Re, C.

Training-Free Hashing-Based Attention via Binary Principal Components Y., Ermon, S., Rudra, A., and Re, C

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.171609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 80239adc-7d65-4ef2-a647-7b0d7c13390a · outbound

This paper cites E., and Stoica, I.

Training-Free Hashing-Based Attention via Binary Principal Components E., and Stoica, I

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.156512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5a18a2d2-dc12-4945-946f-2c00ee6ca851 · outbound

This paper cites The language model evaluation harness, 07 2024.

Training-Free Hashing-Based Attention via Binary Principal Components The language model evaluation harness, 07 2024

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.448707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58c60a82-6cd4-4d20-94f8-7afa6c2ec18c · outbound

This paper cites Model tells you what to discard: Adaptive KV cache compression for LLM s.

Training-Free Hashing-Based Attention via Binary Principal Components Model tells you what to discard: Adaptive KV cache compression for LLM s

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.142226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8a1c847a-d352-4183-97c4-ee08663a825b · outbound

This paper cites HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference.

Training-Free Hashing-Based Attention via Binary Principal Components HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:45:48.754100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ecb4448e-00e0-4300-b69f-cffade0e387f · outbound

This paper cites The Llama 3 Herd of Models.

Training-Free Hashing-Based Attention via Binary Principal Components The Llama 3 Herd of Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.463249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3cec5c8-1849-4e2e-89b7-01434f9dcc5b · outbound

This paper cites FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines.

Training-Free Hashing-Based Attention via Binary Principal Components FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.467163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78a83260-f28a-49ce-9f21-f6a2dc2b3004 · outbound

This paper cites Measuring massive multitask language understanding.

Training-Free Hashing-Based Attention via Binary Principal Components Measuring massive multitask language understanding

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.471650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af515b52-0466-49a6-8ffc-be5556a2a259 · outbound

This paper cites RULER : What s the real context size of your long-context language models? In First Conference on Language Modeling, 2024.

Training-Free Hashing-Based Attention via Binary Principal Components RULER : What s the real context size of your long-context language models? In First Conference on Language Modeling, 2024

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.118630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 58a95e18-6567-4c32-a3be-aeea0733e726 · outbound

This paper cites Mistral 7B.

Training-Free Hashing-Based Attention via Binary Principal Components Mistral 7B

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.481136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7402952-de9f-4da5-8708-0afa1115235f · outbound

This paper cites Needle in a haystack - pressure testing llms, 2023.

Training-Free Hashing-Based Attention via Binary Principal Components Needle in a haystack - pressure testing llms, 2023

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.103843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0fa777ee-833e-484c-9c35-80b797d84d9b · outbound

This paper cites Spotlight attention: Towards efficient LLM generation via non-linear hashing-based KV cache retrieval.

Training-Free Hashing-Based Attention via Binary Principal Components Spotlight attention: Towards efficient LLM generation via non-linear hashing-based KV cache retrieval

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.088165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 82e90470-43f2-4d55-bff8-d3af616edfb5 · outbound

This paper cites Snap KV : LLM knows what you are looking for before generation.

Training-Free Hashing-Based Attention via Binary Principal Components Snap KV : LLM knows what you are looking for before generation

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.074517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5cbfbc9c-57d0-48b7-a240-4400d564416c · outbound

This paper cites CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation.

Training-Free Hashing-Based Attention via Binary Principal Components CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.497849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21c45e05-256e-4f45-aed1-31751a9dd61c · outbound

This paper cites Transformers are Multi-State RNNs.

Training-Free Hashing-Based Attention via Binary Principal Components Transformers are Multi-State RNNs

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.501586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1364e24-a837-4295-bdfd-bf2b475f3031 · outbound

This paper cites Efficiently scaling transformer inference.

Training-Free Hashing-Based Attention via Binary Principal Components Efficiently scaling transformer inference

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.061315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2b8a0f5d-41b5-492c-bf41-e9545623b29b · outbound

This paper cites CAKE : Cascading and adaptive KV cache eviction with layer preferences.

Training-Free Hashing-Based Attention via Binary Principal Components CAKE : Cascading and adaptive KV cache eviction with layer preferences

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.047179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6e7fe64e-838a-4376-a26f-6baea2f56420 · outbound

This paper cites W., Potapenko, A., Jayakumar, S.

Training-Free Hashing-Based Attention via Binary Principal Components W., Potapenko, A., Jayakumar, S

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.034216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a8de4fdf-ea70-4e67-9314-c46683f0b3df · outbound

This paper cites an unresolved cited work.

Training-Free Hashing-Based Attention via Binary Principal Components Unresolved cited work

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.518314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c3d5672-c45b-439e-9be5-eb4d52a46fb3 · outbound

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

Training-Free Hashing-Based Attention via Binary Principal Components QUEST : Query-aware sparsity for efficient long-context LLM inference

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:49.009542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e2ff1f98-d88e-4d4a-9fbe-e8888981a4f5 · outbound

This paper cites Leave no document behind: Benchmarking long-context llms with extended multi-doc qa.

Training-Free Hashing-Based Attention via Binary Principal Components Leave no document behind: Benchmarking long-context llms with extended multi-doc qa

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:48.980227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b29bbc48-98eb-4259-93d1-198f95f2a2c9 · outbound

This paper cites Efficient streaming language models with attention sinks.

Training-Free Hashing-Based Attention via Binary Principal Components Efficient streaming language models with attention sinks

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:48.948921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b4faa074-20e7-49af-8243-627b6f5d711d · outbound

This paper cites Qwen3 Technical Report.

Training-Free Hashing-Based Attention via Binary Principal Components Qwen3 Technical Report

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.534839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de6a2277-4edb-46d0-8692-8e3ee5b02e44 · outbound

This paper cites Qwen2.5-1M Technical Report.

Training-Free Hashing-Based Attention via Binary Principal Components Qwen2.5-1M Technical Report

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.538584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f30f609-ae21-4631-9c75-dde604bf68b6 · outbound

This paper cites Huggingface dataset: namespace-pt/long-llm-data, 2024.

Training-Free Hashing-Based Attention via Binary Principal Components Huggingface dataset: namespace-pt/long-llm-data, 2024

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:48.934585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b76b7076-7ac9-4a03-9408-1683c1071703 · outbound

This paper cites $\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens.

Training-Free Hashing-Based Attention via Binary Principal Components $\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T00:45:48.547366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d79c0a7-586d-448d-9c59-dd60a5a3eb40 · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.

Training-Free Hashing-Based Attention via Binary Principal Components H2o: Heavy-hitter oracle for efficient generative inference of large language models

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:45:48.921189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 774a348e-c6a2-43f5-a710-fe32e610019e · outbound

This paper cites an unresolved cited work.

Training-Free Hashing-Based Attention via Binary Principal Components Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:45:48.907002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers