Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T12:37:24.588694Z
Paper Citation Record · LEDGER
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
As of 20 August 2026, this Paper Citation Record lists 84 of 84 outbound references and 3 inbound Pith citation observations for arXiv:2505.24158.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-15T14:39:08.699220Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-05-12T03:06:18.765685Z
Reference resolution
84 of 84 outbound references displayed
- verified exact1
- verified fuzzy52
- unresolved30
- parse uncertain0
- malformed identifier1
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 0b0f98ab-5ecc-4387-99bc-7583abcaa79a · outbound
This paper cites GPT-4 Technical Report.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders GPT-4 Technical Report
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:16.067831Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2a25c717-9def-4308-8ff1-c6049a818e78 · outbound
This paper cites Flamingo: a visual language model for few-shot learning.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Flamingo: a visual language model for few-shot learning
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:16.151840Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 68155e93-d9bf-49c6-b5da-6cad2496cd05 · outbound
This paper cites Vqa: Visual question answering.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Vqa: Visual question answering
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:16.236696Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5bc3e1f1-f3a4-4f92-a82e-04cd9341d2bc · outbound
This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:16.323580Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e7c4e58b-8675-472d-a7ed-ac3f59df9c45 · outbound
This paper cites Solving mixed-integer quadratic programming problems with ibm-cplex: a progress report.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Solving mixed-integer quadratic programming problems with ibm-cplex: a progress report
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:16.421314Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 02f8b0ea-6d17-4e2d-9aba-f79e9be26d52 · outbound
This paper cites On the Opportunities and Risks of Foundation Models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders On the Opportunities and Risks of Foundation Models
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:16.506733Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8b1037ce-82e4-47c4-a89d-2e18f8978df0 · outbound
This paper cites Language models are few-shot learners.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Language models are few-shot learners
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:16.620624Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 896ac7d1-7c57-4717-a50c-28a592b161b9 · outbound
This paper cites Hourvideo: 1-hour video-language understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Hourvideo: 1-hour video-language understanding
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:34.498288Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation c3568a3a-b413-41e3-88e1-e0f954ffb8ae · outbound
This paper cites Sharegpt4video: Improving video understanding and generation with better captions.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Sharegpt4video: Improving video understanding and generation with better captions
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:34.329297Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 27e4ed29-6118-42b5-b76a-559978453cd2 · outbound
This paper cites LongVILA: Scaling Long-Context Visual Language Models for Long Videos.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders LongVILA: Scaling Long-Context Visual Language Models for Long Videos
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:16.941581Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e3b44931-b510-4d07-8757-d9f2446ea122 · outbound
This paper cites Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:34.139239Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 762e141e-19cd-44e0-bc51-3a40d50f8291 · outbound
This paper cites VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:17.344219Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d484031f-54be-415b-940f-bb6fb78340da · outbound
This paper cites Patch n’pack: Navit, a vision transformer for any aspect ratio and resolution.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Patch n’pack: Navit, a vision transformer for any aspect ratio and resolution
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:33.935943Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 376adc86-d204-4089-8f9e-cecd44d61290 · outbound
This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders An image is worth 16x16 words: Transformers for image recognition at scale
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:33.752601Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 2676de86-cf63-4741-8c40-e4de5cae84b2 · outbound
This paper cites Vlmevalkit: An open-source toolkit for evaluating large multi- modality models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Vlmevalkit: An open-source toolkit for evaluating large multi- modality models
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:33.587582Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7f21be05-08c7-49b4-9be9-780019e38bd2 · outbound
This paper cites Slowfast networks for video recognition.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Slowfast networks for video recognition
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:33.431518Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 809b72ba-d3a4-41c5-8700-937a966fc819 · outbound
This paper cites Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:33.155237Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 47dd4bc0-84f5-4db0-b975-1d6a06d65372 · outbound
This paper cites The Llama 3 Herd of Models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders The Llama 3 Herd of Models
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:18.121807Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2381eef4-f583-4f76-94e7-c73d273512bf · outbound
This paper cites M-llm based video frame selection for efficient video understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders M-llm based video frame selection for efficient video understanding
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:32.959706Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 3750f7a5-fdfc-4ed9-aafa-7789b8c5546b · outbound
This paper cites Chat-univi: Unified visual representation empowers large language models with image and video understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Chat-univi: Unified visual representation empowers large language models with image and video understanding
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:32.786989Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation fa668bc0-cee4-43e7-b805-46e964487e50 · outbound
This paper cites Language repository for long video understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Language repository for long video understanding
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:32.625784Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation a8d39fa3-b1cf-4f27-b2a2-2587ffad92a7 · outbound
This paper cites An image grid can be worth a video: Zero-shot video question answering using a vlm.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders An image grid can be worth a video: Zero-shot video question answering using a vlm
Reference 22
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:32.441482Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 4241b8f0-2af6-46c9-9a51-1bf2b12aaab9 · outbound
This paper cites Lmms-eval: Accelerating the development of large multimoal models, March 2024.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Lmms-eval: Accelerating the development of large multimoal models, March 2024
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:32.178385Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 291baed7-2303-4cf2-977a-841f9a3c3bf3 · outbound
This paper cites LLaVA-OneVision: Easy Visual Task Transfer.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders LLaVA-OneVision: Easy Visual Task Transfer
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:18.912546Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5d203498-19e8-4011-bb17-7995405bec65 · outbound
This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:31.953262Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 60b66c9c-95ff-4c99-aa4f-806c7132fb93 · outbound
This paper cites VideoChat: Chat-Centric Video Understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders VideoChat: Chat-Centric Video Understanding
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:19.138328Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 01bfaaa7-1cec-48f4-8706-3dc35bce83d9 · outbound
This paper cites Llama-vid: An image is worth 2 tokens in large language models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Llama-vid: An image is worth 2 tokens in large language models
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:31.759563Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 5d5a836a-f36a-4515-98b8-f0983000e696 · outbound
This paper cites Video-llava: Learning united visual representation by alignment before projection.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Video-llava: Learning united visual representation by alignment before projection
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:31.614389Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 638b84e3-ccde-4770-8b05-ab1b71fd4652 · outbound
This paper cites Vila: On pre- training for visual language models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Vila: On pre- training for visual language models
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:31.426866Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation c00adb3d-44ed-426f-a8e7-1acd59c1535a · outbound
This paper cites Llava-next: Improved reasoning, ocr, and world knowledge, January 2024.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Llava-next: Improved reasoning, ocr, and world knowledge, January 2024
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:19.424939Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e16f8ea2-1456-4418-80ed-0254c24804d7 · outbound
This paper cites Visual instruction tuning.Advances in neural information processing systems (NeurIPS), 36:34892–34916, 2023.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Visual instruction tuning.Advances in neural information processing systems (NeurIPS), 36:34892–34916, 2023
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:31.189946Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 6954443f-d472-471a-ba74-4e194b2f62cf · outbound
This paper cites Timecraft: Navigate weakly-supervised temporal grounded video question answering via bi-directional reasoning.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Timecraft: Navigate weakly-supervised temporal grounded video question answering via bi-directional reasoning
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:30.918499Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation b426fb8e-9c4a-44d3-9d07-e7078607e366 · outbound
This paper cites Lost in the middle: How language models use long contexts.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Lost in the middle: How language models use long contexts
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:30.659000Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 2f4cc9f1-282b-41ed-9b30-625553421422 · outbound
This paper cites St-llm: Large language models are effective temporal learners.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders St-llm: Large language models are effective temporal learners
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:30.370543Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 81f55e11-6d72-4da8-a94c-73e27f7c50ec · outbound
This paper cites Bolt: Boost large vision-language model without training for long-form video understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Bolt: Boost large vision-language model without training for long-form video understanding
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:30.122315Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 5342c0cd-7585-46c2-a601-c2740e0a62c8 · outbound
This paper cites Drvideo: Document retrieval based long video understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Drvideo: Document retrieval based long video understanding
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:29.987173Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation d4d72409-db44-44cc-b222-457dff76e831 · outbound
This paper cites Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:19.932480Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ffbf24f6-cd17-462d-8bb0-3c82bb673924 · outbound
This paper cites Egoschema: A diagnostic benchmark for very long-form video language understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Egoschema: A diagnostic benchmark for very long-form video language understanding
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:29.773619Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation ae471a22-25b4-492d-a176-bca78cc195e3 · outbound
This paper cites Morevqa: Exploring modular reasoning models for video question answering.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Morevqa: Exploring modular reasoning models for video question answering
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:29.610912Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 0abc113c-9916-4985-825b-dc805945947b · outbound
This paper cites Branch-and-bound algorithms: A survey of recent advances in searching, branching, and pruning.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Branch-and-bound algorithms: A survey of recent advances in searching, branching, and pruning
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:29.526632Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation d1c22e62-5148-4f3c-bd01-6c185a24dec6 · outbound
This paper cites Chatgpt: Optimizing language models for dialogue, 2023.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Chatgpt: Optimizing language models for dialogue, 2023
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:29.389856Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 02da2d3a-496d-4709-bcc1-4a52e6737496 · outbound
This paper cites Too many frames, not all useful: Efficient strategies for long-form video qa.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Too many frames, not all useful: Efficient strategies for long-form video qa
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:29.235070Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation deb2fcb6-9589-4fa4-b275-b8777c51689d · outbound
This paper cites Momentor: Advancing video large language model with fine-grained temporal reasoning.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Momentor: Advancing video large language model with fine-grained temporal reasoning
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:29.090406Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 9347cb9c-82d3-4a9e-bf0e-53f2dcf2f7f3 · outbound
This paper cites Learning transferable visual models from natural language supervision.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Learning transferable visual models from natural language supervision
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:28.954666Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 3bc64dc1-212e-4d68-9cf6-0e9ba1c2a852 · outbound
This paper cites The knapsack problem: a survey.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders The knapsack problem: a survey
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:20.635358Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 312e0497-9293-483e-9372-348a673c1466 · outbound
This paper cites LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:20.727692Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f19b5cbc-5429-425a-8010-6d84e9d4ed61 · outbound
This paper cites Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:20.806587Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fbd4598c-ac5d-4e0c-aeba-4bd4cc9806cf · outbound
This paper cites Two-stream convolutional networks for action recognition in videos.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Two-stream convolutional networks for action recognition in videos
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:28.843270Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation d462dcf3-d607-4bff-9bed-dd3901c0c289 · outbound
This paper cites Moviechat: From dense token to sparse memory for long video understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Moviechat: From dense token to sparse memory for long video understanding
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:28.689205Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7b755651-2206-48b2-9d89-86b81dba6344 · outbound
This paper cites Mdp3: A training-free approach for list-wise frame selection in video-llms.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Mdp3: A training-free approach for list-wise frame selection in video-llms
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:21.085807Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 542d090a-bde5-476e-93c8-631aaba47c51 · outbound
This paper cites Adaptive keyframe sampling for long video understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Adaptive keyframe sampling for long video understanding
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:28.544301Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation fb5be959-6296-4046-9e8b-69de40a997a2 · outbound
This paper cites Gemma: Open Models Based on Gemini Research and Technology.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Gemma: Open Models Based on Gemini Research and Technology
Reference 52
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:21.246351Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0bb7053e-8653-4f74-a8ed-f522d94005a6 · outbound
This paper cites Cambrian-1: A fully open, vision- centric exploration of multimodal llms.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Cambrian-1: A fully open, vision- centric exploration of multimodal llms
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:28.389747Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation a09a5b92-a3c3-46d7-9c28-29122d677e3c · outbound
This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 54
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:21.439956Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 46bcfb17-ae86-4fea-9e96-e026cddb3bfc · outbound
This paper cites Attention is all you need.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Attention is all you need
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:28.221238Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation a9736535-42eb-4e5f-8817-6603449fa2e5 · outbound
This paper cites Show and tell: A neural image caption generator.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Show and tell: A neural image caption generator
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:28.070943Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation cf88f0d5-6501-4dae-b17b-c9deec7298aa · outbound
This paper cites Efficient large language models: A survey.Transactions on Machine Learning Research (TMLR), 2024.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Efficient large language models: A survey.Transactions on Machine Learning Research (TMLR), 2024
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:27.896903Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 8e98f985-ca8e-4fc2-a759-67f3c756a9be · outbound
This paper cites Weakly supervised gaussian contrastive grounding with large multimodal models for video question answering.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Weakly supervised gaussian contrastive grounding with large multimodal models for video question answering
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:27.715659Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 88731b3a-d85e-4308-ab9d-076a50bdcc2a · outbound
This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
Reference 59
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:21.942911Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 26926a99-6fe9-4763-ae56-44f168a64c7d · outbound
This paper cites ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding
Reference 60
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:22.035335Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ae110e84-5baf-4ba8-94c9-2236d33e803d · outbound
This paper cites Videoagent: Long-form video under- standing with large language model as agent.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Videoagent: Long-form video under- standing with large language model as agent
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:27.552815Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation eb9742ac-5b10-4d64-a3ed-357f9bcc1d79 · outbound
This paper cites Videotree: Adaptive tree-based video representation for llm reasoning on long videos.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Videotree: Adaptive tree-based video representation for llm reasoning on long videos
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:27.342292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7cd90885-7735-4b77-8764-6ba6759e772e · outbound
This paper cites Dibs: Enhancing dense video captioning with unlabeled videos via pseudo boundary enrichment and online refinement.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Dibs: Enhancing dense video captioning with unlabeled videos via pseudo boundary enrichment and online refinement
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:27.171688Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 061e4745-6e27-4634-a3ca-076def2997d1 · outbound
This paper cites Longvideobench: A benchmark for long-context interleaved video-language understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Longvideobench: A benchmark for long-context interleaved video-language understanding
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:26.974968Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 7998ee8f-53e2-406a-944f-7d9d6e446f8b · outbound
This paper cites Next-qa: Next phase of question-answering to explaining temporal actions.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Next-qa: Next phase of question-answering to explaining temporal actions
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:26.807231Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 519ac6c8-ad9d-415d-bb49-44f01783acce · outbound
This paper cites Can i trust your answer? visually grounded video question answering.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Can i trust your answer? visually grounded video question answering
Reference 66
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:26.664010Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation c3b083f2-ee51-4cb1-a99d-b3b5c2ef56c0 · outbound
This paper cites Effective long-context scaling of foundation models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Effective long-context scaling of foundation models
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:26.500839Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation a990e067-485f-4cf9-852f-ee77af800c35 · outbound
This paper cites PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
Reference 68
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:22.900514Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cba55f33-db7f-408d-99fa-78317f5baaca · outbound
This paper cites SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
Reference 69
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:23.032653Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cb3d9dd3-06aa-45e8-bdb6-fdb75c4eda2e · outbound
This paper cites Zero-shot video question answering via frozen bidirectional language models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Zero-shot video question answering via frozen bidirectional language models
Reference 70
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:26.332155Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 51652350-edb5-4a59-8448-5a2ab454b129 · outbound
This paper cites Vid2seq: Large-scale pretraining of a visual language model for dense video captioning.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Vid2seq: Large-scale pretraining of a visual language model for dense video captioning
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:26.186839Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 9298836e-13e0-461f-ab6c-1abfb7ea459e · outbound
This paper cites Dense connector for mllms.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Dense connector for mllms
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:26.019452Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 0ef5db10-d2dc-4306-898f-c0a74ce8d362 · outbound
This paper cites Generative Frame Sampler for Long Video Understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Generative Frame Sampler for Long Video Understanding
Reference 73
- Resolution
- verified exact
- local_arxiv, observed 2026-08-07T12:37:24.889986Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation e9d53f51-3628-4ccd-8161-bafbb69f4d9a · outbound
This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders MiniCPM-V: A GPT-4V Level MLLM on Your Phone
Reference 74
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:23.584263Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1388fada-bbd9-4c81-83ce-e5b474ed503f · outbound
This paper cites Self-chained image-language model for video localization and question answering.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Self-chained image-language model for video localization and question answering
Reference 75
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:25.913672Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation a2d295cf-2c3e-4d3b-864f-226d08d397da · outbound
This paper cites Frame-voyager: Learning to query frames for video large language models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Frame-voyager: Learning to query frames for video large language models
Reference 76
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:25.779824Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 49e98b79-f970-452f-9e47-f1468db5e4da · outbound
This paper cites Sigmoid loss for language image pre-training.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Sigmoid loss for language image pre-training
Reference 77
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:25.554077Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation 842a74e2-9b22-453c-b188-65da3f3cc9e1 · outbound
This paper cites A simple llm framework for long-range video question-answering.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders A simple llm framework for long-range video question-answering
Reference 78
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T12:37:25.380735Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation d0f16f33-24b5-4af9-ad4e-4b8e07355c6d · outbound
This paper cites Long Context Transfer from Language to Vision.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Long Context Transfer from Language to Vision
Reference 79
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:24.093163Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 79b9db04-5fc5-48b4-aadf-697adeb8f07e · outbound
This paper cites Llava-next: A strong zero-shot video understanding model, April 2024.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Llava-next: A strong zero-shot video understanding model, April 2024
Reference 80
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:24.190869Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b30ebedc-b77a-4463-b3a6-ef8c7a773f6d · outbound
This paper cites LLaVA-Video: Video Instruction Tuning With Synthetic Data.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders LLaVA-Video: Video Instruction Tuning With Synthetic Data
Reference 81
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:24.258273Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b028f069-8365-4ff5-903f-0d9928d4f313 · outbound
This paper cites MLVU: Benchmarking Multi-task Long Video Understanding.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders MLVU: Benchmarking Multi-task Long Video Understanding
Reference 82
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:24.363162Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4793def1-2e8a-4082-a776-2a2c5df55d59 · outbound
This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Reference 83
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T12:37:24.461768Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 447bbede-b0be-4fbc-9feb-22827ba5a7bd · outbound
This paper cites Apollo: An Exploration of Video Understanding in Large Multimodal Models.
Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders Apollo: An Exploration of Video Understanding in Large Multimodal Models
Reference 84
- Resolution
- malformed identifier
- no resolver link, observed 2026-08-07T12:37:24.588694Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
Observation 76dbb3a0-84e8-434c-9c6f-48b3029920af · inbound
Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs cites this paper.
Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
Reference 2019
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T13:27:56.359929Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 767c7c7e-b77e-4aeb-8c50-e2dfe77869ac · inbound
CREST: Curvature-Regulated Event-Centric Sampling for Efficient Long-Video Understanding cites this paper.
CREST: Curvature-Regulated Event-Centric Sampling for Efficient Long-Video Understanding Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T03:06:18.772638Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.
Observation df5b6b56-6f9f-4886-9414-484068385707 · inbound
One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding cites this paper.
One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T14:39:08.699220Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.