Paper Citation Record · LEDGER

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning

As of 12 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2605.31457.

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

pith.paper-citation-record.v1
2605.31457 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T23:13:15.593994Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

24 of 24 outbound references displayed

verified exact17
verified fuzzy0
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fd4d505e-01e1-42d6-975f-b038b984bff1 · outbound

This paper cites Qwen3-VL Technical Report.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Qwen3-VL Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.578005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 997dde5f-5dcc-44bc-9f54-065a0fbd3774 · outbound

This paper cites Think Clearly: Improving Reasoning via Redundant Token Pruning.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Think Clearly: Improving Reasoning via Redundant Token Pruning

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T00:12:50.580956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 31b1ba56-24a3-49a8-92b8-a5e6d4485e5e · outbound

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

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.586292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5c8640b3-9191-4a69-8019-a3f804756657 · outbound

This paper cites OpenAI o1 System Card.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning OpenAI o1 System Card

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.586463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 494d7288-de93-4018-834a-47fb4884390c · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning LLaVA-OneVision: Easy Visual Task Transfer

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.584225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c000258d-a7ff-47ae-9c8c-a15336907d71 · outbound

This paper cites Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:12:50.564283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0cacf445-a2be-4995-a822-07bc6d941093 · outbound

This paper cites HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.588896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d5c5d5ae-8a3d-4f3c-b403-ef3e649f7a75 · outbound

This paper cites L., Tan, J.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning L., Tan, J

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T23:13:15.593994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6f59feb-9fda-4e9d-bea5-f7a375758e55 · outbound

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

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.541483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ecfb1240-c0a0-4fb5-a808-9049115ef076 · outbound

This paper cites Kimi-VL Technical Report.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Kimi-VL Technical Report

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.569596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1c2908e8-a975-435b-a5e8-182033b85bd2 · outbound

This paper cites LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:12:50.575478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 392264aa-5eb5-4da6-a67e-93caf0c54a51 · outbound

This paper cites ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:12:50.561358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 78efca44-1cf1-48dc-9efd-9bf72f00011b · outbound

This paper cites VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.573182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a664e121-c2e0-42cc-9158-cf2bd93c1ac6 · outbound

This paper cites Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.581682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6fd908c0-611d-4160-adf7-a299b677d698 · outbound

This paper cites LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.596604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b9586db2-5c1a-4ebe-ade8-410680ee40f5 · outbound

This paper cites Tokenskip: Controllable chain-of-thought compression in llms.arXiv preprint arXiv:2502.12067.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Tokenskip: Controllable chain-of-thought compression in llms.arXiv preprint arXiv:2502.12067

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:12:50.578033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2ac26f35-e0db-4748-85dd-67f48dec80ee · outbound

This paper cites arXiv preprint arXiv:2504.18458 , year=.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning arXiv preprint arXiv:2504.18458 , year=

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T00:12:50.567176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 85b4cc93-84c7-4410-802e-2f00d4df2a9e · outbound

This paper cites PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.569823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 141616eb-2574-40b2-8685-dae74dd5d590 · outbound

This paper cites Look-Back: Implicit Visual Re-focusing in MLLM Reasoning.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T00:12:50.591396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d9a5c939-091c-4390-9be3-727c6c91a4dd · outbound

This paper cites Demystifying Long Chain-of-Thought Reasoning in LLMs.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Demystifying Long Chain-of-Thought Reasoning in LLMs

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.561905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e4e7d9a4-4ab9-404c-aa76-6d5a1505cf3c · outbound

This paper cites Unified Visual Transformer Compression.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Unified Visual Transformer Compression

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:12:50.553383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4c923cbf-ef0c-43e1-9256-0d4e6636c162 · outbound

This paper cites AdaptThink: Reasoning Models Can Learn When to Think.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning AdaptThink: Reasoning Models Can Learn When to Think

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T00:12:50.594042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e2b5de62-db43-45a2-97aa-08f36abe5aaa · outbound

This paper cites Additional Analysis A.1.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Additional Analysis A.1

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-28T23:13:15.593994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c041c2ca-250b-4483-a790-3a80bbab479c · outbound

This paper cites This suggests that VisionPulse is orthogonal to static visual token pruning methods such as FastV and can be combined with them for additional efficiency improvements.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning This suggests that VisionPulse is orthogonal to static visual token pruning methods such as FastV and can be combined with them for additional efficiency improvements

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-28T23:13:15.593994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.