DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention | Paper Citation Record

Observation 6d5ba521-272d-448a-8673-71cacd619d3a · outbound

This paper cites Is it really long context if all you need is retrieval? towards genuinely difficult long context NLP.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Is it really long context if all you need is retrieval? towards genuinely difficult long context NLP

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.146562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 929d89d6-30cd-40ee-8a68-1b6381af3f11 · outbound

This paper cites an unresolved cited work.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-05-20T10:53:26.135459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 60e5711f-49c1-4cba-a6b4-9e445e33c176 · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Attention is all you need.Advances in neural information processing systems, 30

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.133698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7cde45ae-baeb-4fda-b8f7-8d05985f8c39 · outbound

This paper cites Softmax is not enough (for sharp size generalisation).

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Softmax is not enough (for sharp size generalisation)

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.144002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c3e2f403-7f6e-4f7d-8a65-294a897559f5 · outbound

This paper cites Native sparse attention: Hardware-aligned and natively trainable sparse attention.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Native sparse attention: Hardware-aligned and natively trainable sparse attention

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.129008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 03f36460-b66b-4402-8a46-86c456e2fb4f · outbound

This paper cites InfLLM-v2: Dense-sparse switchable attention for seamless short-to-long adaptation.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention InfLLM-v2: Dense-sparse switchable attention for seamless short-to-long adaptation

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.137533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0068619b-f1ab-4ccf-b610-bbd56a088321 · outbound

This paper cites an unresolved cited work.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-05-20T10:53:26.141925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 13a84dfa-7a41-42fd-85bd-749ddcd466e9 · outbound

This paper cites Long-context generalization with sparse attention.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Long-context generalization with sparse attention

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.133509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f54f691a-91c0-4bc2-8ee2-a6fdd31a56a4 · outbound

This paper cites MoBA: Mixture of block attention for long-context LLMs.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention MoBA: Mixture of block attention for long-context LLMs

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.102675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 96437640-d12c-414b-a20d-477cfe944867 · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with IO-awareness.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Flashattention: Fast and memory-efficient exact attention with IO-awareness

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.094757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c1e71adb-e692-4559-91b5-c1e49de57ea7 · outbound

This paper cites From softmax to sparsemax: A sparse model of attention and multi-label classification.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention From softmax to sparsemax: A sparse model of attention and multi-label classification

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.090382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6d29233f-6a4b-4841-bc28-040776463dbf · outbound

This paper cites Adasplash: Adaptive sparse flash attention.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Adasplash: Adaptive sparse flash attention

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.122761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 28d35cc7-d532-45bc-bb60-7d3e98144cba · outbound

This paper cites Adasplash-2: Faster differentiable sparse attention.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Adasplash-2: Faster differentiable sparse attention

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.092660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 411b1c93-e3a7-4f79-8df0-f8e783e4eea6 · outbound

This paper cites Gqa: Training generalized multi-query transformer models from multi-head checkpoints.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Gqa: Training generalized multi-query transformer models from multi-head checkpoints

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.109441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6c096a2f-2461-42cd-a942-6d7e043880d6 · outbound

This paper cites Learning classifiers with fenchel-young losses: Generalized entropies, margins, and algorithms.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Learning classifiers with fenchel-young losses: Generalized entropies, margins, and algorithms

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.135662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2127a77a-bee5-4144-8add-8b4dc98c9bba · outbound

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

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Flashattention-2: Faster attention with better parallelism and work partitioning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.107670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 745df542-c48f-46b2-90d7-bb65983a9acf · outbound

This paper cites an unresolved cited work.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-05-20T10:53:26.107447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 382caca0-f26e-4ce1-a1d1-42e43378e158 · outbound

This paper cites Infllm-v2-data-5b dataset.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Infllm-v2-data-5b dataset

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.111009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a219ed25-0cbd-4564-a9bb-26d52baf25a1 · outbound

This paper cites MiniCPM4: Ultra-Efficient LLMs on End Devices.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention MiniCPM4: Ultra-Efficient LLMs on End Devices

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.541414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5c9972ef-8e6a-4392-8a57-6ab1c3edf280 · outbound

This paper cites RULER: What’s the real context size of your long-context language models? InFirst Conference on Language Modeling.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention RULER: What’s the real context size of your long-context language models? InFirst Conference on Language Modeling

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.112768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c454c62d-091b-4d39-a19f-f9b27fb03b8f · outbound

This paper cites HELMET: How to evaluate long-context models effectively and thoroughly.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention HELMET: How to evaluate long-context models effectively and thoroughly

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.109072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1e11a913-1c19-45e9-b9e3-b527eda3301f · outbound

This paper cites Mmlu-pro: A more robust and challenging multi-task language understanding benchmark.Advances in Neural Information Processing Systems, 37:95266–95290.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Mmlu-pro: A more robust and challenging multi-task language understanding benchmark.Advances in Neural Information Processing Systems, 37:95266–95290

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.142415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 066a030b-ac45-4354-b6a3-e1b65e8d6471 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Measuring Massive Multitask Language Understanding

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.574632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2ea2c98e-808c-43b1-8933-551ad4bf317a · outbound

This paper cites Commonsenseqa: A question answering challenge targeting commonsense knowledge.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Commonsenseqa: A question answering challenge targeting commonsense knowledge

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.124815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4c26b643-b332-4ed3-92a0-779477d99aff · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Instruction-Following Evaluation for Large Language Models

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.559200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 721e1ca2-1129-40ab-a4fa-c36d7c65a36c · outbound

This paper cites Hellaswag: Can a machine really finish your sentence? InProceedings of the 57th annual meeting of the association for computational linguistics, pages 4791–4800.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Hellaswag: Can a machine really finish your sentence? InProceedings of the 57th annual meeting of the association for computational linguistics, pages 4791–4800

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.116548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 51b7de01-03e3-4df9-820f-149602f4de4c · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Training Verifiers to Solve Math Word Problems

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.502184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4fce58cb-1e38-4b55-9c22-2bccc3a88622 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Measuring Mathematical Problem Solving With the MATH Dataset

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.577323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6af8292c-5eeb-4c28-a865-35a21d11dbfe · outbound

This paper cites Drop: A reading comprehension benchmark requiring discrete reasoning over paragraphs.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Drop: A reading comprehension benchmark requiring discrete reasoning over paragraphs

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.126760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4431f30c-6e91-48fc-8b48-4d39681f5306 · outbound

This paper cites Program Synthesis with Large Language Models.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Program Synthesis with Large Language Models

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.556324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b9bd9f9c-2486-4072-8da8-92df5d05d670 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Evaluating Large Language Models Trained on Code

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.519507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d210fddf-4bd7-43fc-9f7c-54e5f20d2873 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Efficient memory management for large language model serving with pagedattention

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.118486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 308a8b91-229c-4f72-a63b-f3d9af120b49 · outbound

This paper cites Sglang: Efficient execution of structured language model programs.Advances in neural information processing systems, 37:62557–62583.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Sglang: Efficient execution of structured language model programs.Advances in neural information processing systems, 37:62557–62583

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.144440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 61c50e82-deb7-4d3b-83e3-0f96536ea180 · outbound

This paper cites Flashattention-3: Fast and accurate attention with asynchrony and low-precision.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Flashattention-3: Fast and accurate attention with asynchrony and low-precision

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.119438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5991786b-911d-483f-b8fe-2a03898e7ed1 · outbound

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

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.596117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7fd93b9f-ad9a-46b0-a97e-c4efac714fa1 · outbound

This paper cites Pyramidinfer: Pyramid kv cache compression for high-throughput llm inference.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Pyramidinfer: Pyramid kv cache compression for high-throughput llm inference

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.115897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 89fc6086-267b-4d24-960d-16c253156d00 · outbound

This paper cites Efficient streaming language models with attention sinks.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Efficient streaming language models with attention sinks

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.075215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 856ad4ff-07df-434d-8a66-40f646d9527c · outbound

This paper cites Longformer: The Long-Document Transformer.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Longformer: The Long-Document Transformer

Reference 38

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T10:53:13.553401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fcd1287e-80be-43f2-bb8a-2b4996452c3e · outbound

This paper cites Big bird: Transformers for longer sequences.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Big bird: Transformers for longer sequences

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.073490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4af70864-ffa5-4506-b5c9-9afcf20246bf · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems, 36:34661–34710.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention H2o: Heavy-hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems, 36:34661–34710

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.114210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 44cbbdd6-45e9-46b0-93d7-d27c7a5d104e · outbound

This paper cites MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

Reference 41

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T10:53:13.547437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f444d31c-07f9-4262-a33b-523a679281c1 · outbound

This paper cites Reformer: The efficient transformer.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Reformer: The efficient transformer

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.117767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 61ed1033-3856-4c6c-932f-6bc89d8bd961 · outbound

This paper cites Spargeattn: Accurate sparse attention accelerating any model inference.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Spargeattn: Accurate sparse attention accelerating any model inference

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.565342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2de1d86a-f818-4c0c-924d-118e52d8a62a · outbound

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

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.550501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f76f756c-f240-4be3-b87e-f23f48ce80e8 · outbound

This paper cites Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.571507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a4ec7517-e142-4d4d-be6b-264149bff7ed · outbound

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

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.580322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5bea1bae-d609-4e79-8070-001742a9a948 · outbound

This paper cites Lycheedecode: Accelerating long-context llm inference via hybrid-head sparse decoding.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Lycheedecode: Accelerating long-context llm inference via hybrid-head sparse decoding

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.568362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0a4c63d7-30fd-4472-a06f-48ab893eb12c · outbound

This paper cites Snapkv: Llm knows what you are looking for before generation.Advances in Neural Information Processing Systems, 37:22947–22970.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Snapkv: Llm knows what you are looking for before generation.Advances in Neural Information Processing Systems, 37:22947–22970

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.105830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 242bae82-e641-4f8c-994f-c90ba31b61d1 · outbound

This paper cites R-KV: Redundancy-aware KV cache compression for reasoning models.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention R-KV: Redundancy-aware KV cache compression for reasoning models

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.583802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 84c5d80e-72f7-430f-b5f6-4a638ee239d4 · outbound

This paper cites Indexcache: Accelerating sparse attention via cross-layer index reuse.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Indexcache: Accelerating sparse attention via cross-layer index reuse

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.529441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5aa1b51d-5b99-4871-8de2-8d4d7dc237ee · outbound

This paper cites Infllm: Training-free long-context extrapolation for llms with an efficient context memory.Advances in neural information processing systems, 37:119638–119661.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Infllm: Training-free long-context extrapolation for llms with an efficient context memory.Advances in neural information processing systems, 37:119638–119661

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.121386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2de173d6-f8da-40a1-b937-7a2692db3acb · outbound

This paper cites ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.593270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0a017d96-554a-4abc-852f-ab2b4b2a37fe · outbound

This paper cites Nosa: Native and offloadable sparse attention.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Nosa: Native and offloadable sparse attention

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.589945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 178987df-f6f3-4739-a48d-eabf26415659 · outbound

This paper cites an unresolved cited work.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-05-20T10:53:26.112291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d5245d6c-a565-4287-8f3e-f21f15e45ead · outbound

This paper cites Inference-time hyper-scaling with KV cache compression.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Inference-time hyper-scaling with KV cache compression

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.148533Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6be08aa3-d628-42e7-8402-535a22e41e32 · outbound

This paper cites Kvquant: Towards 10 million context length llm inference with kv cache quantization.Advances in Neural Information Processing Systems, 37:1270–1303.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Kvquant: Towards 10 million context length llm inference with kv cache quantization.Advances in Neural Information Processing Systems, 37:1270–1303

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.140118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4b0f79cf-da3a-4097-840d-827433bdaddb · outbound

This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.598927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d54f0181-1c18-4a4f-b48f-72eeb58fc5ae · outbound

This paper cites Pqcache: Product quantization-based kvcache for long context llm inference.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Pqcache: Product quantization-based kvcache for long context llm inference

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.114446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a8990c60-f268-4918-920b-394a6500e38c · outbound

This paper cites MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention MTraining: Distributed Dynamic Sparse Attention for Efficient Ultra-Long Context Training

Reference 59

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.513638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 015213c6-84eb-4fbb-bb4f-1b04d4a97998 · outbound

This paper cites SeerAttention-R: Sparse Attention Adaptation for Long Reasoning.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention SeerAttention-R: Sparse Attention Adaptation for Long Reasoning

Reference 60

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.586873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 22512576-7a2a-4be3-8518-2108e49e5c76 · outbound

This paper cites SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.535272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8c463151-981c-4626-9282-0d893fa8f0bc · outbound

This paper cites Flash sparse attention: An alternative efficient implementation of native sparse attention kernel.arXiv e-prints, pages arXiv–2508.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Flash sparse attention: An alternative efficient implementation of native sparse attention kernel.arXiv e-prints, pages arXiv–2508

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.099196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 523dda38-9d8c-4fb4-bf91-921b201947fe · outbound

This paper cites Hsa: Head-wise sparse attention for efficient and accurate long-context inference.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Hsa: Head-wise sparse attention for efficient and accurate long-context inference

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.065707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8bc6fa7f-847b-4318-b89a-b5337e39fa49 · outbound

This paper cites DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.538082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 28691fa5-f1df-4e3a-a74a-f9d6191c0ed2 · outbound

This paper cites Deepseek-v4: Towards highly efficient million-token context in- telligence.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Deepseek-v4: Towards highly efficient million-token context in- telligence

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.063949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a06cb1cf-cf5e-4d2e-ac87-937f1b96d7e7 · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 66

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.562151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6840e049-0ae7-4fbc-92b4-1063b144f783 · outbound

This paper cites Spargeattention2: Trainable sparse attention via hybrid top-k+ top-p masking and distillation fine-tuning.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Spargeattention2: Trainable sparse attention via hybrid top-k+ top-p masking and distillation fine-tuning

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.510469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b802fea6-bcc7-4764-a155-64c75f823508 · outbound

This paper cites Double-p: Hierarchical top-p sparse attention for long-context llms.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Double-p: Hierarchical top-p sparse attention for long-context llms

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.526500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b387206a-3673-41b1-9161-664b978492c4 · outbound

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

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.523245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5e5eac3a-8f1c-4e36-af15-f69d8cda4fb0 · outbound

This paper cites Possible generalization of boltzmann-gibbs statistics.Journal of statistical physics, 52(1):479–487.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Possible generalization of boltzmann-gibbs statistics.Journal of statistical physics, 52(1):479–487

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.102971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 52831df3-351c-45eb-bef1-1cf126c01724 · outbound

This paper cites MiniCPM: Unveiling the potential of small language models with scalable training strategies.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention MiniCPM: Unveiling the potential of small language models with scalable training strategies

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.077431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8909391e-6eb6-4e71-bdd6-9f125bc24e1b · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 72

Resolution: verified exact; local_arxiv, observed 2026-05-20T10:53:13.516609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 15a95ccd-30b8-4cc5-a967-a66f05443e93 · outbound

This paper cites Olmes: A standard for language model evaluations.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Olmes: A standard for language model evaluations

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.110754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0ae6d7d9-f2eb-44a5-81e2-f604dafe161f · outbound

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

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention The language model evaluation harness, 07 2024

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.101138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1a315cbe-b00b-4ae8-90bf-c80d01e79514 · outbound

This paper cites Hardware-aligned hierarchical sparse attention for efficient long-term memory access.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Hardware-aligned hierarchical sparse attention for efficient long-term memory access

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-20T10:53:13.544336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 63a076b0-92e8-4a4b-ae1c-c3535cfb464d · outbound

This paper cites Every to- ken counts: Generalizing 16m ultra-long context in large language models.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Every to- ken counts: Generalizing 16m ultra-long context in large language models

Reference 76

Resolution: malformed identifier; arxiv_id, observed 2026-05-20T10:53:13.532290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a1a735b0-6b28-4105-9879-e05470164930 · outbound

This paper cites lim n→∞ H aggrsoftmax z(1),z (2),· · ·,z (H);θ logn = 1.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention lim n→∞ H aggrsoftmax z(1),z (2),· · ·,z (H);θ logn = 1

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T10:53:26.060183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 92d0096f-f18d-4542-a5a9-224759a06778 · outbound

This paper cites Proof.We first prove that softmax head aggregation is dispersive.

DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention Proof.We first prove that softmax head aggregation is dispersive

Reference 78

Resolution: malformed identifier; raw_fallback, observed 2026-05-20T10:53:26.066170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers