VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding | Paper Citation Record

Observation 4a5ccee9-7d80-4eb4-980c-aedb59733c49 · outbound

This paper cites Qwen3-VL Technical Report.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Qwen3-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:40.263863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbcfc400-3eab-4288-add5-b74a12a64c15 · outbound

This paper cites InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:40.385436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7e61b8a-07a7-4a88-98f4-a78be078cb89 · outbound

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

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:40.495393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e667046c-a725-4642-b587-c2328b08047c · outbound

This paper cites PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:40.660990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89442b5b-01c1-4281-b165-e4ae54133cd4 · outbound

This paper cites Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:40.771026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef734fdc-7083-4879-a6ff-04ef4bbef4a0 · outbound

This paper cites Qwen2 Technical Report.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Qwen2 Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:40.831039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3002662-927d-4f41-84b7-8cd3dfe506a1 · outbound

This paper cites Qwen3 Technical Report.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Qwen3 Technical Report

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:40.939379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48755b6a-f903-4acc-923a-ccfe3364939c · outbound

This paper cites Videochat-r1.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Videochat-r1

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.103975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e95a7ad-809f-46f5-8825-6b314a59a3ec · outbound

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

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.162135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eb20e68-e4ab-472d-83e9-bc2fcebe7712 · outbound

This paper cites Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.221547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a14c559-b0a9-4999-89b1-aa7072fa0657 · outbound

This paper cites SpaceR: Reinforcing MLLMs in Video Spatial Reasoning.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding SpaceR: Reinforcing MLLMs in Video Spatial Reasoning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.291479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3971ffea-3617-48e5-a5ad-d0b190556c65 · outbound

This paper cites Timechat: A time-sensitive multimodal large language model for long video understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Timechat: A time-sensitive multimodal large language model for long video understanding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.382976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 896580a9-b2dd-4e5f-928b-d905b606de14 · outbound

This paper cites Timesuite: Improving mllms for long video understanding via grounded tuning.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Timesuite: Improving mllms for long video understanding via grounded tuning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.430131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ee61b8d-42f9-49b3-bdf3-4d68bfebf8cd · outbound

This paper cites Timelens: Rethinking video temporal grounding with multimodal llms.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Timelens: Rethinking video temporal grounding with multimodal llms

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.491845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a97708be-9b01-4dac-b427-131bd70fac0e · outbound

This paper cites Videollm-online: Online video large language model for streaming video.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Videollm-online: Online video large language model for streaming video

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.520198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e5440df-9915-40ca-8717-78f8973438bf · outbound

This paper cites Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.589936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a369fec-b7b9-4308-81b4-7288778b1d35 · outbound

This paper cites Online video understanding: Ovbench and videochat-online.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Online video understanding: Ovbench and videochat-online

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.682216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd5440ab-3792-4d09-8638-349f095ca67a · outbound

This paper cites Dispider: Enabling video llms with active real-time interaction via disentangled perception, decision, and reac- tion.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Dispider: Enabling video llms with active real-time interaction via disentangled perception, decision, and reac- tion

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.752189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98d24d20-5989-423a-807d-fd5b57368f76 · outbound

This paper cites Streamforest: Eﬀicient online video understanding with persistent event memory.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Streamforest: Eﬀicient online video understanding with persistent event memory

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.822857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e546c26-dd84-4100-afa7-2c56326fc8b1 · outbound

This paper cites Streaming Video Instruction Tuning.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Streaming Video Instruction Tuning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:41.892453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 993fd87c-d1d1-4a9c-9cb8-d355b9fc2d39 · outbound

This paper cites Streambridge: Turning your offline video large language model into a proactive streaming assistant.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Streambridge: Turning your offline video large language model into a proactive streaming assistant

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:42.000829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84c47551-8d13-4eb5-afe6-0ea131a643b8 · outbound

This paper cites Gemini 3: News and announcements.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Gemini 3: News and announcements

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:42.058308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdfce8b2-b132-4d59-be38-3009f0e0f2bf · outbound

This paper cites Kimi K2.5: Visual Agentic Intelligence.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Kimi K2.5: Visual Agentic Intelligence

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:42.146048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f292ffb8-0f86-4e74-879e-f18ccb366a37 · outbound

This paper cites Seed1.8 Model Card: Towards Generalized Real-World Agency.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Seed1.8 Model Card: Towards Generalized Real-World Agency

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:42.258052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e387c711-e657-4b7c-89db-b3d318a62123 · outbound

This paper cites How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites,.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:42.442107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68902810-0686-4fd3-a7f9-7b0fbb7bfd67 · outbound

This paper cites Llava-video: Video instruction tuning with synthetic data.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Llava-video: Video instruction tuning with synthetic data

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:42.626276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f310e039-88e8-4489-a3f5-4b83df3475d5 · outbound

This paper cites Spoken moments: Learning joint audio-visual representations from video descriptions.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Spoken moments: Learning joint audio-visual representations from video descriptions

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:42.674221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 696b1e40-7be9-4046-870a-3400740071da · outbound

This paper cites Vript: A Video Is Worth Thousands of Words.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Vript: A Video Is Worth Thousands of Words

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:42.744544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 348f95ff-4641-4035-9846-921b4270211e · outbound

This paper cites Kimi-VL Technical Report.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Kimi-VL Technical Report

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:42.862348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ad1ffdd-369f-409c-b585-466a4e9b6ca0 · outbound

This paper cites Visual instruction tuning.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Visual instruction tuning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:42.961347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fbbbd9f-5d8a-48f9-8681-349e8f704aba · outbound

This paper cites Caprl: Stimulating dense image caption capabilities via reinforcement learning.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Caprl: Stimulating dense image caption capabilities via reinforcement learning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.030845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc39791f-29a1-412a-8774-f3fba5cbe5e9 · outbound

This paper cites ShareGPT4V: Improving Large Multi-Modal Models with Better Captions.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.081065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adf665ae-a5d2-46df-a260-54c49dd84a5f · outbound

This paper cites Densefusion-1m: Merging vision experts for comprehensive multimodal perception, 2024.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Densefusion-1m: Merging vision experts for comprehensive multimodal perception, 2024

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.181761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e086231-e4f4-4f51-b110-bb8fb79de085 · outbound

This paper cites Conceptual captions: A cleaned, hyper- nymed, image alt-text dataset for automatic image captioning.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Conceptual captions: A cleaned, hyper- nymed, image alt-text dataset for automatic image captioning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.251365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04b79d1e-0edf-457b-bda4-415a13500e9f · outbound

This paper cites Frozen in time: A joint video and image encoder for end-to-end retrieval.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Frozen in time: A joint video and image encoder for end-to-end retrieval

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.345486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f1b7b9b-5867-4fee-917d-998c90074fef · outbound

This paper cites The Kinetics Human Action Video Dataset.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding The Kinetics Human Action Video Dataset

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.450847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9070223b-b3a6-407a-930f-bb3cadac97ad · outbound

This paper cites Perception Encoder: The best visual embeddings are not at the output of the network.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Perception Encoder: The best visual embeddings are not at the output of the network

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.511377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc8bdbe5-db5f-4970-bc1b-09f5f5777cae · outbound

This paper cites Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.581545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97b1d4bd-f720-4045-b127-9119a204ce99 · outbound

This paper cites Movie Description.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Movie Description

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.651420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2487f5b2-24d7-41e8-9d0e-57d5915cece2 · outbound

This paper cites Vatex: A large-scale, high-quality multilingual dataset for video-and-language research, 2020.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Vatex: A large-scale, high-quality multilingual dataset for video-and-language research, 2020

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.802803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d1616b3-84c4-4329-b3fc-b43ea5e67a88 · outbound

This paper cites Activitynet: A large-scale video benchmark for human activity understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Activitynet: A large-scale video benchmark for human activity understanding

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.836826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3a2e685-6b4c-491d-acd5-1ad19717cea8 · outbound

This paper cites Hollywood in homes: Crowdsourcing data collection for activity understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Hollywood in homes: Crowdsourcing data collection for activity understanding

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.888588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2722b1ba-4233-4f03-834d-c6f0f5029497 · outbound

This paper cites The” something something” video database for learning and evaluating visual common sense.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding The” something something” video database for learning and evaluating visual common sense

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:43.944633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb7ea558-f755-4e43-98a0-275f5ac5a278 · outbound

This paper cites Ego4d: Around the world in 3,000 hours of egocentric video.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Ego4d: Around the world in 3,000 hours of egocentric video

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:44.014790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5334e404-e128-4616-891d-a8d35781854c · outbound

This paper cites Sharegemini: Scaling up video caption data for multimodal large language models, June 2024.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Sharegemini: Scaling up video caption data for multimodal large language models, June 2024

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:44.154403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 434eb6fd-db63-4997-8139-4e4e8e4601b0 · outbound

This paper cites Sharegpt-4o: Comprehensive multimodal annotations with gpt-4o, 2024.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Sharegpt-4o: Comprehensive multimodal annotations with gpt-4o, 2024

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:44.322802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c212413-8de1-446d-97f7-3302e944f610 · outbound

This paper cites Bee: A high-quality corpus and full-stack suite to unlock advanced fully open mllms, 2026.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Bee: A high-quality corpus and full-stack suite to unlock advanced fully open mllms, 2026

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:44.416164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73f7c1a8-e954-4cd3-b94e-18816196ddd5 · outbound

This paper cites an unresolved cited work.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:44.524832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05740471-e970-4649-8eae-b3c488fdc495 · outbound

This paper cites TVQA: Localized, Compositional Video Question Answering.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding TVQA: Localized, Compositional Video Question Answering

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:44.781343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfe6d3b7-0d2d-478d-aad9-a23b8f8f4043 · outbound

This paper cites Finevideo.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Finevideo

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:44.904024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63fe83c7-4305-4236-8c2d-31689e10f41c · outbound

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

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding CinePile: A Long Video Question Answering Dataset and Benchmark

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:45.027159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44f6e26a-3390-417a-a7dc-68dcecdda5ec · outbound

This paper cites VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:45.094167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7aad7ba-4663-404f-86ec-3a64470c839f · outbound

This paper cites TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:45.137483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 933de6f8-6ff6-4e45-937e-4ccaa01c61c8 · outbound

This paper cites Tenenbaum.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Tenenbaum

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:45.214475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddffa66c-6b18-4507-8f6a-462f594e4986 · outbound

This paper cites Exo2ego: Exocentric knowledge guided mllm for egocentric video understanding, 2025.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Exo2ego: Exocentric knowledge guided mllm for egocentric video understanding, 2025

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:45.353879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29679ae7-b005-4d36-ab11-651511c0719a · outbound

This paper cites Motionbench: Benchmarking and improving fine-grained video motion understanding for vision language models.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Motionbench: Benchmarking and improving fine-grained video motion understanding for vision language models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:45.449671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12757dcf-7036-41ce-b4ac-9ceee6d0bd8b · outbound

This paper cites Lasot: A high-quality benchmark for large-scale single object tracking.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Lasot: A high-quality benchmark for large-scale single object tracking

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:45.524820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92921bda-1059-4880-aed9-db3eb7094c78 · outbound

This paper cites Got-10k: A large high-diversity benchmark for generic object tracking in the wild.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Got-10k: A large high-diversity benchmark for generic object tracking in the wild

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:45.610802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68d5b2d2-ca47-477e-9453-4f25bba290d2 · outbound

This paper cites Ross, Carl Vondrick, Caroline Pantofaru, Yeqing Li, Sudheendra Vijaya- narasimhan, George Toderici, Susanna Ricco, Rahul Sukthankar, Cordelia Schmid, and Jitendra Malik.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Ross, Carl Vondrick, Caroline Pantofaru, Yeqing Li, Sudheendra Vijaya- narasimhan, George Toderici, Susanna Ricco, Rahul Sukthankar, Cordelia Schmid, and Jitendra Malik

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:45.825885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 797fe49c-7856-46dc-a804-f06fab2fc2cd · outbound

This paper cites Egovqa-an egocentric video question answering benchmark dataset.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Egovqa-an egocentric video question answering benchmark dataset

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:45.896415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28367e16-b65d-4c7e-84da-1042e0956299 · outbound

This paper cites Learning transferable temporal primitives for video reasoning via synthetic videos, 2026.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Learning transferable temporal primitives for video reasoning via synthetic videos, 2026

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:45.961453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e21f2666-0810-4545-b42d-eb15d92e4cfc · outbound

This paper cites Tomato: Assessing visual temporal reasoning capabilities in multimodal foundation models.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Tomato: Assessing visual temporal reasoning capabilities in multimodal foundation models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:46.065996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e3ba013-2d83-496e-9ee5-82869176d604 · outbound

This paper cites Lost in Time: A New Temporal Benchmark for VideoLLMs.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Lost in Time: A New Temporal Benchmark for VideoLLMs

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:46.152973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc81c15b-8707-4181-a9b9-f212d9ff8779 · outbound

This paper cites Tempcompass: Do video llms really understand videos? In Findings of the Association for Computational Linguistics: ACL 2024 , pages 8731–8772.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Tempcompass: Do video llms really understand videos? In Findings of the Association for Computational Linguistics: ACL 2024 , pages 8731–8772

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:46.342096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57d2e2c4-13c4-4e1d-a7e6-9879a171b493 · outbound

This paper cites Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:46.436665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1af6863-d03b-4ec8-8da1-c04869640ed1 · outbound

This paper cites LVBench: An Extreme Long Video Understanding Benchmark.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding LVBench: An Extreme Long Video Understanding Benchmark

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:46.573335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84ee4e48-c29d-4129-aa2e-0182b72b4e4e · outbound

This paper cites VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:46.835407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a0e508e-08bc-41c5-a574-c1a893454cb8 · outbound

This paper cites Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:47.002048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c9669d4-2c06-4e4e-bba6-df62de1d7772 · outbound

This paper cites Mmvu: Measuring expert-level multi-discipline video understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Mmvu: Measuring expert-level multi-discipline video understanding

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:47.229883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cf8ffcd-ab76-4593-9b85-c9087da6b0f0 · outbound

This paper cites Minerva: Evaluating complex video reasoning.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Minerva: Evaluating complex video reasoning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:47.313301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f09832a2-f0ac-4d92-aefe-e83c8dbc9759 · outbound

This paper cites Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:47.434527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb923698-d405-4226-9789-6d1f8bdb5cc4 · outbound

This paper cites Tall: Temporal activity localization via language query.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Tall: Temporal activity localization via language query

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:47.600495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2685caf0-64d8-4b74-8a34-57bfd9f32434 · outbound

This paper cites Dense-captioning events in videos.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Dense-captioning events in videos

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:47.761237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ec15f71-9897-4104-ab87-3af549c81da9 · outbound

This paper cites Detecting moments and highlights in videos via natural language queries.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Detecting moments and highlights in videos via natural language queries

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:47.805666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8536bac6-8a77-49a4-be09-1afb22f38f08 · outbound

This paper cites Vidi: Large Multimodal Models for Video Understanding and Editing.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Vidi: Large Multimodal Models for Video Understanding and Editing

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:47.844379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40348e98-5b43-4527-8e75-a38ed0aeb684 · outbound

This paper cites Vidi2: Large multimodal models for video understanding and creation.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Vidi2: Large multimodal models for video understanding and creation

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:47.884749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54903a52-59db-465b-91bf-80471d354aa0 · outbound

This paper cites Momentseeker: A task-oriented benchmark for long-video moment retrieval.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Momentseeker: A task-oriented benchmark for long-video moment retrieval

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:47.923648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adf89ab0-e959-4a7b-84ad-7c967815939f · outbound

This paper cites GPT-5 system card.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding GPT-5 system card

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:47.963677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e079e2a-41aa-4261-81bf-284bf742459e · outbound

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

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:48.014595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 527104fb-143b-4554-aacb-595ec68ac764 · outbound

This paper cites Introducing claude sonnet 4.5.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Introducing claude sonnet 4.5

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:48.141435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29f11d55-cb24-4841-99a3-6ac23f236f6a · outbound

This paper cites MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:48.181447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bb62b33-3fc7-4574-9664-dd78ac3c8c3b · outbound

This paper cites Eagle 2.5: Boosting long-context post-training for frontier vision-language models.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Eagle 2.5: Boosting long-context post-training for frontier vision-language models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:48.248621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f6503ae-9746-4fe7-918f-cbccd66be913 · outbound

This paper cites VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:48.337537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34055a81-c4a9-4c9c-957e-3431b35f15f0 · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:48.427210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb5c00dc-8b5c-4208-a414-9e766e2d3148 · outbound

This paper cites an unresolved cited work.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Unresolved cited work

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:48.525948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45268e19-3c2e-44e5-8398-aa21ee8d91ec · outbound

This paper cites Streamingbench: Assessing the gap for mllms to achieve streaming video understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Streamingbench: Assessing the gap for mllms to achieve streaming video understanding

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:48.594780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7a17479-bc58-446d-8e99-0bea900400df · outbound

This paper cites River: A real-time interaction benchmark for video llms.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding River: A real-time interaction benchmark for video llms

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:48.759089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8ee7c1c-267d-4f8c-b05d-d9d00aca60ac · outbound

This paper cites Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Em-Garde: A Propose-Match Framework for Proactive Streaming Video Understanding

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:48.868441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7523c331-160b-4a39-b74a-911205ccb356 · outbound

This paper cites ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:48.909159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a95b4f6-12f8-44f1-b33f-20cffae494f8 · outbound

This paper cites Livecc: Learning video llm with streaming speech transcription at scale.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Livecc: Learning video llm with streaming speech transcription at scale

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.000448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eef673cb-ab0d-41eb-96c0-09b8a853e2c3 · outbound

This paper cites Timechat-online: 80% visual tokens are naturally redundant in streaming videos.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Timechat-online: 80% visual tokens are naturally redundant in streaming videos

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.159431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7dbb6e1-fc38-43aa-a75a-89864475aee9 · outbound

This paper cites StreamingVLM: Real-Time Understanding for Infinite Video Streams.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding StreamingVLM: Real-Time Understanding for Infinite Video Streams

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.226362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a57edb3-07ad-4d15-83ec-8fb67b370d25 · outbound

This paper cites Mm- duet2: Enhancing proactive interaction of video mllms with multi-turn reinforcement learning.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Mm- duet2: Enhancing proactive interaction of video mllms with multi-turn reinforcement learning

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.297464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43fc2d0a-4e5a-49ff-8900-0cd58958772e · outbound

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

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.338761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34cdd0cd-7ef9-42b9-8cc2-6c5f5665e243 · outbound

This paper cites VideoChat: Chat-Centric Video Understanding.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding VideoChat: Chat-Centric Video Understanding

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.393750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52d95c55-6cca-42a4-8338-c243094e56f0 · outbound

This paper cites Video-chatgpt: Towards detailed video understanding via large vision and language models.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Video-chatgpt: Towards detailed video understanding via large vision and language models

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.433839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a1eb399-e080-47c6-b0d6-af99858ce804 · outbound

This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.479276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2fcb43b-74dd-4bf0-bd01-d9d6382cb93f · outbound

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

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding LLaVA-OneVision: Easy Visual Task Transfer

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.528523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 916cc133-aeb9-4a69-85be-5014ca2f787c · outbound

This paper cites LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.651285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5939ccc1-f8be-42e1-91cf-a1dc4dec07c9 · outbound

This paper cites AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation.

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-02T00:44:49.747631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers