Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding | Paper Citation Record

Observation 88193e5c-508a-4353-a368-0423a0a7db08 · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:34.967551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 322731e2-edaa-4f28-8a97-e0626bd31fe9 · outbound

This paper cites 2025 IEEE/CVF International Conference on Computer Vision (ICCV) , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding 2025 IEEE/CVF International Conference on Computer Vision (ICCV) , pages=

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:34.972401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95c97b24-1dcf-4dab-98bd-8c7ddd47d332 · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:34.976757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe9af7a0-9666-432a-bea8-55eb0c103604 · outbound

This paper cites PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T23:42:38.263471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 95e3be72-963b-4e16-8dc1-e63d4aaedbf0 · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:34.986046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91da7fbf-cf4c-42e8-859b-57cdbc5c4565 · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:34.990368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1468d980-9e42-4d3b-9c1b-9749f003a400 · outbound

This paper cites Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:34.994738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da832fe9-bd47-4155-84ab-af0c83ea644c · outbound

This paper cites Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:34.999140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 791ff586-6a7d-43bc-80a3-1bcf324214ed · outbound

This paper cites arXiv preprint arXiv:2507.07966 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2507.07966 , year=

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.003049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1632a862-58f5-49aa-adfd-28d2d8552ee2 · outbound

This paper cites UI-TARS: Pioneering Automated GUI Interaction with Native Agents.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.006944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aece37f1-91a7-455a-af84-5edb8d9f13be · outbound

This paper cites Qwen2.5-VL Technical Report.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Qwen2.5-VL Technical Report

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.011144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e7d020c-7a32-4010-9062-a055c58b0abf · outbound

This paper cites Journal of Visual Communication and Image Representation , volume=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Journal of Visual Communication and Image Representation , volume=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.019850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93f062a9-c40d-4f58-b11d-11d09aa7a2b2 · outbound

This paper cites Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.024660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 076c26d2-d334-4f85-ace0-5774c15b4a2e · outbound

This paper cites CinePile: A Long Video Question Answering Dataset and Benchmark.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding CinePile: A Long Video Question Answering Dataset and Benchmark

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.029043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6977576-efe3-4033-b901-1ae2ef49a408 · outbound

This paper cites CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.033889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49e25a13-f186-45c8-85a8-c1ed82e9cc6e · outbound

This paper cites Describe Anything: Detailed Localized Image and Video Captioning.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Describe Anything: Detailed Localized Image and Video Captioning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.038915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40435e09-dda2-458e-b446-000310e5d923 · outbound

This paper cites Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.044026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b18ccfcd-fb5a-49d3-a109-90f2e479835f · outbound

This paper cites Proceedings of the IEEE/CVF winter conference on applications of computer vision , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the IEEE/CVF winter conference on applications of computer vision , pages=

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.047867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a50bf22f-14fb-4ea0-bc91-1d05444a9348 · outbound

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

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Advances in Neural Information Processing Systems , volume=

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.051735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67558f6b-def8-4ec3-9a80-11676bf87a67 · outbound

This paper cites arXiv e-prints , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv e-prints , pages=

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.055629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 532e0f22-be28-400e-b515-63fca5abadf7 · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.060058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc3329b6-0a19-48fe-9578-f8319e3a2843 · outbound

This paper cites Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.063900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b1d950f-353f-427b-b794-37e0b9e0cecf · outbound

This paper cites arXiv preprint arXiv:2508.04369 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2508.04369 , year=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.067606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 577608bd-94de-4b36-a3c6-6450c71c66ed · outbound

This paper cites an unresolved cited work.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.071742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fc0d62d-9555-459d-94bf-0351f54c83b0 · outbound

This paper cites an unresolved cited work.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.075368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1df357a6-03e0-4789-a052-6628592dcd04 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.079279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5af1714-1c85-4d3d-8b9e-8d47f4503caf · outbound

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

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Advances in neural information processing systems , volume=

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.083243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2faaf74f-9daf-450d-a617-3a4466d330b6 · outbound

This paper cites International conference on machine learning , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding International conference on machine learning , pages=

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.086792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a542cce-ab43-4480-b6da-baf3ac9d6403 · outbound

This paper cites LongVILA: Scaling Long-Context Visual Language Models for Long Videos.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding LongVILA: Scaling Long-Context Visual Language Models for Long Videos

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.091644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 308c53c7-5f8d-4242-8dec-85a3af4acfb3 · outbound

This paper cites Long Context Transfer from Language to Vision.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Long Context Transfer from Language to Vision

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.096042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a34726a-c37f-4148-b236-4e7398ac6ccc · outbound

This paper cites arXiv preprint arXiv:2502.05177 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2502.05177 , year=

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.100870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62eb75a8-496f-4c5b-9297-5a32e09166bc · outbound

This paper cites European Conference on Computer Vision , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding European Conference on Computer Vision , pages=

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.104559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d0d5924-46e1-4636-bc0c-4ef0ccd7060d · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.108718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23615e5f-63f5-473a-ae1e-29277313f056 · outbound

This paper cites LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.112820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a363538-f653-4df9-86c7-043fdc5295c8 · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding DINOv2: Learning Robust Visual Features without Supervision

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.116786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2528b329-713a-44be-acd8-f0ffde781769 · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.120837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31af810c-b90a-453a-8506-cbaa23064c22 · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:42:38.438990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fc745383-719e-47c8-9c37-c19f8d4f6247 · outbound

This paper cites PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.128973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd591fcd-b595-4d6b-8978-6099f1586b65 · outbound

This paper cites arXiv preprint arXiv:2510.27280 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2510.27280 , year=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.133666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83ce1718-bef9-4d79-a24a-13456167b10f · outbound

This paper cites Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.137666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b80a305-06b8-4a90-b461-e9b9d104db82 · outbound

This paper cites FlexSelect: Flexible Token Selection for Efficient Long Video Understanding.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding FlexSelect: Flexible Token Selection for Efficient Long Video Understanding

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.141746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d680571f-867a-4a75-881e-03ebc212f6d2 · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:42:38.426552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 104a7dd4-af46-47c8-989c-76bb7ba2552c · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:42:38.413824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9a674896-953e-4cc1-aae0-29c2ccddcae7 · outbound

This paper cites arXiv preprint arXiv:2510.13891 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2510.13891 , year=

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.154446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 949b5c8a-2cf7-4ce3-a17a-63fc99fbed09 · outbound

This paper cites Frame-Voyager: Learning to Query Frames for Video Large Language Models.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Frame-Voyager: Learning to Query Frames for Video Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.158387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9026e97-5b11-4dc2-88ff-3fe443f527e5 · outbound

This paper cites Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.162434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ac55cbc-22b6-42bd-9fff-474e2edde272 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.166581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a341499c-793e-48c2-9e41-3b2136d50295 · outbound

This paper cites arXiv preprint arXiv:2512.11534 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2512.11534 , year=

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.170212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f24d6f3c-e584-445e-93d1-99d3b7bafd5b · outbound

This paper cites Proximal Policy Optimization Algorithms.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proximal Policy Optimization Algorithms

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.173910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 454c92c5-a9de-4550-9945-7fb52ba7f392 · outbound

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

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Advances in neural information processing systems , volume=

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.177728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca11859a-759c-41e5-a5f9-85d0663ace74 · outbound

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

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Advances in neural information processing systems , volume=

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.181274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef3320d5-b85e-4927-9168-7fd73b355b84 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.185360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9acbfab0-4321-4bc9-b2a6-ab619266c7e4 · outbound

This paper cites Proceedings of the 2024 conference on empirical methods in natural language processing , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the 2024 conference on empirical methods in natural language processing , pages=

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.190392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dfa2b5b-5896-496c-ba1e-69fde5afd8e0 · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.195518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3fbdcb7-97d9-4efe-8d32-f232731bec8c · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:42:38.376340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b44f048c-53c6-4815-8e91-8912f439fc1a · outbound

This paper cites VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.203009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dce91058-7b8c-47d8-99cd-fdaad28ec38e · outbound

This paper cites an unresolved cited work.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Unresolved cited work

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.207163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 108275d8-c8cc-4622-9a7c-4a52af0a8537 · outbound

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

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding LLaVA-OneVision: Easy Visual Task Transfer

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.211189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2adaf088-b632-4f60-a978-61943e5b8a5f · outbound

This paper cites Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.215228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 735d3b90-9c25-467b-b563-83d0b51517eb · outbound

This paper cites Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.219360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ff40cdd-5706-4348-972a-deb5b3b8976f · outbound

This paper cites GPT-4V(ision) system card , url=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding GPT-4V(ision) system card , url=

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:42:38.353966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e7ee0b09-26c2-494a-9af5-f554f2efc499 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Gemini: A Family of Highly Capable Multimodal Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.228769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acfb088c-807c-40ce-a2ea-8892e3ff6b96 · outbound

This paper cites Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.233288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29663a2e-d21d-4b52-8965-a6238af709bf · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:42:38.343764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d3ac00bb-b2ca-4bee-bfe6-89ec6ab877b7 · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:42:38.333721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1b31cd46-dfdf-4aac-94d0-baf39675fb3c · outbound

This paper cites mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.246208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b778ed7-8140-41ab-a1f1-b6e80088b44b · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.250414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8be2849b-f821-4698-84c7-b874683bd49a · outbound

This paper cites LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.254789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2adc3bb7-81f2-47ca-942d-a0b06f11b82b · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.259354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3caf4fb-be58-49e2-ac26-315351eaeb75 · outbound

This paper cites Findings of the Association for Computational Linguistics: NAACL 2025 , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Findings of the Association for Computational Linguistics: NAACL 2025 , pages=

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.263951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce3af3d7-e684-4f93-85a3-4ea4f6cb84df · outbound

This paper cites arXiv preprint arXiv:2510.20622 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2510.20622 , year=

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.267788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5d5aada-913e-4dd2-af7c-e63665cd10d5 · outbound

This paper cites KeyVideoLLM: Towards Large-scale Video Keyframe Selection.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding KeyVideoLLM: Towards Large-scale Video Keyframe Selection

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.271317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3edf887e-ae98-487f-8ca2-118820cb80a6 · outbound

This paper cites MoBA: Mixture of Block Attention for Long-Context LLMs.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding MoBA: Mixture of Block Attention for Long-Context LLMs

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.275164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea224450-abc1-42c2-b9ae-bca17a4f097c · outbound

This paper cites ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.279225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64354bbb-8bc1-43d1-8297-6a99e744addb · outbound

This paper cites European Conference on Computer Vision , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding European Conference on Computer Vision , pages=

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.282895Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70505639-07af-4d2d-ac65-935bf4ad9567 · outbound

This paper cites arXiv preprint arXiv:2512.04000 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2512.04000 , year=

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.286834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7231cc6d-7072-4e4c-bb8f-8dc3ddd4dd39 · outbound

This paper cites Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.290721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f75b74b-7551-4bf3-a952-b6523142cad7 · outbound

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

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Findings of the Association for Computational Linguistics: ACL 2024 , pages=

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:42:38.302472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3f747f0b-d0cf-4dcc-9a4d-28bae416a214 · outbound

This paper cites arXiv preprint arXiv:2512.06866 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2512.06866 , year=

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.298403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e82103f8-687e-4358-be36-fd9b36733719 · outbound

This paper cites International conference on machine learning , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding International conference on machine learning , pages=

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.302345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 386423a4-cb6a-4ec6-9647-fab143900a02 · outbound

This paper cites DeepSeek-OCR: Contexts Optical Compression.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding DeepSeek-OCR: Contexts Optical Compression

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.306068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8e0168f-e7cf-496b-be61-0b99e380d554 · outbound

This paper cites arXiv preprint arXiv:2502.02770 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2502.02770 , year=

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.310474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8651f988-a6eb-478d-9397-9933409b53f1 · outbound

This paper cites VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.314074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c39dbf2-088b-4d6a-9299-72b5745b961d · outbound

This paper cites arXiv preprint arXiv:2601.22582 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2601.22582 , year=

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.318166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89644a61-823b-477b-9050-d893594e292f · outbound

This paper cites CoS: Chain-of-Shot Prompting for Long Video Understanding.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding CoS: Chain-of-Shot Prompting for Long Video Understanding

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.322337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f00d2cd-5d32-4612-8501-582a08c55afb · outbound

This paper cites LLaVA-Video: Video Instruction Tuning With Synthetic Data.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding LLaVA-Video: Video Instruction Tuning With Synthetic Data

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.326390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e9bdbae-b87b-4365-9025-a400c1fbc98a · outbound

This paper cites Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.330473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef3c325f-9b54-45f3-b907-81c8326c3dbb · outbound

This paper cites Group-in-Group Policy Optimization for LLM Agent Training.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Group-in-Group Policy Optimization for LLM Agent Training

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.334661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a46cfd20-1e86-4467-b0c4-b3d875e8158c · outbound

This paper cites On the Emergence of Position Bias in Transformers.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding On the Emergence of Position Bias in Transformers

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.338843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df6bbcc7-9e88-4fbf-96b0-9b851f16bda6 · outbound

This paper cites Proceedings of the Computer Vision and Pattern Recognition Conference , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the Computer Vision and Pattern Recognition Conference , pages=

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:42:38.284992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8aace232-8f19-4705-b6a3-084255d68645 · outbound

This paper cites Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T23:42:38.274866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8a677408-6190-4db3-9c70-bd63b83027e4 · outbound

This paper cites arXiv preprint arXiv:2504.18579 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2504.18579 , year=

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.351819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f91a1cdf-23b2-4ce0-b2ec-332e7591b29c · outbound

This paper cites arXiv preprint arXiv:2603.06199 , year=.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding arXiv preprint arXiv:2603.06199 , year=

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.355809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6083fe37-9c5f-40e6-97e3-d61f110a605a · outbound

This paper cites FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference.

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T23:42:35.360123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers