Paper Citation Record · LEDGER

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

As of 18 August 2026, this Paper Citation Record lists 97 of 97 outbound references and 9 inbound Pith citation observations for arXiv:2504.17343.

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

pith.paper-citation-record.v1
2504.17343 v1

Coverage vector

measured 97 of 97 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:47:27.549539Z

measured 106 of 106 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 9 of 9 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:39:27.373948Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-17T05:39:06.193766Z

Reference resolution

97 of 97 outbound references displayed

verified exact1
verified fuzzy7
unresolved88
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 24a0a1e7-953d-4007-87f5-dc7bf1ba47c3 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.087191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85a5fc5a-74eb-4099-984c-0899177f66e3 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.093080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fee0551-b613-43b9-967e-82b676493a16 · outbound

This paper cites MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.098130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b5b40f2-6272-44bf-862d-235f66c09f47 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.103612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d9c1167-71c7-4f42-b00f-5b00f1cab400 · outbound

This paper cites Qwen2.5-VL Technical Report.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Qwen2.5-VL Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.108764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ac84183-2ef7-48fd-9733-2447b3d9865d · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.113974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7007f82a-40d8-4a84-a470-e257ef89e5f7 · outbound

This paper cites An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.119176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79510706-cb6d-427c-856e-91a79b51841e · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.123949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3498b3d3-2722-46cd-8122-063e95bc77d0 · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.129002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e91de8e-30fc-4eee-b29c-7cbea4208569 · outbound

This paper cites Don’tLookTwice:FasterVideoTransformerswithRun-Length Tokenization.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Don’tLookTwice:FasterVideoTransformerswithRun-Length Tokenization

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.134194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f5669c0-2d76-4292-8a3a-f65f1538cd52 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.138543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc077c45-0c18-4a3e-969c-81c362576fd5 · outbound

This paper cites Streaming Video Question-Answering with In-context Video KV-Cache Retrieval.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Streaming Video Question-Answering with In-context Video KV-Cache Retrieval

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.143082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 136859f5-7221-4d5e-b454-337be4e9179d · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.147664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 271c074c-959e-4b9d-80a0-4d6314b54eef · outbound

This paper cites The Llama 3 Herd of Models.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos The Llama 3 Herd of Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.152077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0dd4c32-5709-4aeb-bb97-694de14e23d8 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.156824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2802569c-fcd2-459d-a41a-4a35c42b31c3 · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.167772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc1e19d3-53d3-4cae-9bf8-742d4c5b998b · outbound

This paper cites Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.173037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3241c7b6-b5e8-4d60-ac65-25d3204c055e · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.177981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf4d288d-e789-4cb9-9982-8a91b8b4171d · outbound

This paper cites MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.182670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5360a405-d82a-49a2-9271-b8addb30d70c · outbound

This paper cites Multimodal Pretraining for Dense Video Captioning.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Multimodal Pretraining for Dense Video Captioning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.187274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b394037e-7de9-474e-b409-151741d0fbbd · outbound

This paper cites Online Video Understanding: OVBench and VideoChat-Online.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Online Video Understanding: OVBench and VideoChat-Online

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.192617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf94d745-1f9a-46bc-9f3a-71be881ee060 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.197269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64b3f170-e535-4655-88f8-119a944dfc66 · outbound

This paper cites QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.202370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d19ef454-21c6-4bc9-9061-57d80a06e500 · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos LLaVA-OneVision: Easy Visual Task Transfer

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.207400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 107b2991-8980-478d-8e55-612140f73ec1 · outbound

This paper cites LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.211905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4d8983a-6629-4941-bb5d-a0bee40abdd6 · outbound

This paper cites VideoChat: Chat-Centric Video Understanding.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos VideoChat: Chat-Centric Video Understanding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.217162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26940ab4-974a-4225-92ce-84f720a61896 · outbound

This paper cites In ICLR 2025.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos In ICLR 2025

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.221993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef6225a9-3859-4964-aab2-ccc56aaf5b35 · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.231104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0699005-bd32-4f9d-ba5f-281e2af5e08a · outbound

This paper cites OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.235208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d0739f2-593e-48a2-979e-b2d4127b843a · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.244381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63b43313-834b-48d5-8502-d609831f2d14 · outbound

This paper cites StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.248339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 971356b9-e82e-4666-aa5a-14d6f6f9974d · outbound

This paper cites Vila:Onpre-trainingforvisuallanguagemodels.In Proceedingsofthe IEEE/CVFconferenceoncomputervisionandpatternrecognition .26689–26699.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Vila:Onpre-trainingforvisuallanguagemodels.In Proceedingsofthe IEEE/CVFconferenceoncomputervisionandpatternrecognition .26689–26699

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.253023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae55f94a-be35-4c4c-9487-139c830393e3 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.257196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87dae969-c4b4-47cc-b626-ee06ddf7faae · outbound

This paper cites Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.261466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b479db0c-347e-4581-8db3-d260e003ecb7 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.266006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44e18775-1478-4541-9ebd-ebb3f46a1cb1 · outbound

This paper cites Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.274835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bc27a61-04d8-46e9-8af5-bb45ed83bb6a · outbound

This paper cites Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.279636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee3f9cc1-b145-44a8-af2b-cd83b855f63d · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.284240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43fce36b-8251-45e1-92f6-b3fde6fbfea7 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.288786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e27bea18-4da4-4852-8060-5857443d36e4 · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos DINOv2: Learning Robust Visual Features without Supervision

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.293093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dacafc79-a663-46f2-bd74-010f335527cb · outbound

This paper cites Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.297623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69f75cd8-91ae-477d-8580-404c88efe4ce · outbound

This paper cites Streaminglongvideounderstandingwithlargelanguagemodels.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Streaminglongvideounderstandingwithlargelanguagemodels

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:47:29.133826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 562f1fdf-064f-4014-a903-d8a630884241 · outbound

This paper cites TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.306650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60541043-5b6d-4494-a1be-439780edce04 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.310930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5409593-b7de-468c-ac8b-d76472e8e01f · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:29.108014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7cf0d026-9b17-497e-b7a5-daf9a3741aaf · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.320182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b352433f-0ce4-4808-a468-4c735059d1c8 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:29.093257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 26a2d857-9ee4-44ed-821f-7f1c35c99eee · outbound

This paper cites TVSum: Summarizingwebvideosusingtitles.In 2015IEEEConferenceonComputerVision and Pattern Recognition (CVPR).

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos TVSum: Summarizingwebvideosusingtitles.In 2015IEEEConferenceonComputerVision and Pattern Recognition (CVPR)

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.329403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 845c9174-609f-4f35-baab-bdb5e3309ced · outbound

This paper cites Iscosine-similarity of embeddings really about similarity?.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Iscosine-similarity of embeddings really about similarity?

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:47:29.078801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e2ef9b46-e4c6-411f-898f-bd6695096f11 · outbound

This paper cites COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.337707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93679d75-7309-4972-93c5-ec47c6176dcc · outbound

This paper cites DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.342314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e843b2fd-62ed-42d7-b04f-c7bf6e16da86 · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.346774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dd6115e-0687-4509-bae5-2814be6b5d52 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.352149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 363671ca-fd42-49a6-820a-314a63e3b0a7 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:29.063219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2eb589c2-a5ab-46aa-bfd5-4ffea80d4470 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.361147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a95bde9f-f54c-498b-a23b-4bfb19bc62b3 · outbound

This paper cites Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.365910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3bb6f10-c488-4529-aff5-d79133254972 · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.370415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e29ee4d-3e99-46e4-96fa-d91a28e12452 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:29.046512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 50934a88-cc54-4766-b40b-110efda1ead2 · outbound

This paper cites Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.379932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b1a58a0-8c95-4b50-97c1-074d47e3ba51 · outbound

This paper cites Qwen2.5-Omni Technical Report.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Qwen2.5-Omni Technical Report

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.384477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5077567d-e7e0-4f0b-96f3-5b718854d4d5 · outbound

This paper cites SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.389581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89ec4016-9523-4b04-9527-f730c20d6efa · outbound

This paper cites Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.394273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d393e25-0515-4edc-aafb-8cd701e3ff81 · outbound

This paper cites Qwen2 Technical Report.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Qwen2 Technical Report

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.399021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57884cf9-3f0e-4026-9fcf-f4b9369a722d · outbound

This paper cites PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.403604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2d0699b-afe2-43e0-bcf2-3868504c7088 · outbound

This paper cites TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.408169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b93f80f-18c6-4dcc-b3da-46e357c340b1 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.413010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15349772-bd33-4549-8eea-4463566cb1df · outbound

This paper cites DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.417308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ce5fbd6-9fdd-424c-9dd6-afb05a8886fb · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.421997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e1821e8-d26a-4325-9b71-2e41af93635f · outbound

This paper cites Movie101: A New Movie Understanding Benchmark.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Movie101: A New Movie Understanding Benchmark

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.427239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21c3152c-a3d7-417d-926c-827d6d988ec8 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:29.030799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9c628f04-1a0f-43c6-b7f7-b4af476d59e4 · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.436518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9071930c-4076-4d47-aca5-325f7cdc98be · outbound

This paper cites Video-LLaMA:AnInstruction-tuned Audio-Visual Language Model for Video Understanding.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Video-LLaMA:AnInstruction-tuned Audio-Visual Language Model for Video Understanding

Reference 74

Resolution: malformed identifier; raw_fallback, observed 2026-08-16T10:47:29.014354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 30fc1c39-01d4-4181-a788-ec5b79a5d8b9 · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.445344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1a55fc5-d6f7-4e78-b033-919f27341b42 · outbound

This paper cites Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.449972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4f1732d-a2a3-497c-926c-d717722e1696 · outbound

This paper cites InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.458880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f5f2872-5095-4f7b-a7df-799cb4c2d40a · outbound

This paper cites Long Context Transfer from Language to Vision.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Long Context Transfer from Language to Vision

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.463436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6021fd3-3cfe-4b2b-b3f8-d410c9d2a54d · outbound

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

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos LLaVA-Video: Video Instruction Tuning With Synthetic Data

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.468229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa139f51-bedf-4e4a-a790-677f64c4ab91 · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos H2o: Heavy-hitter oracle for efficient generative inference of large language models

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:47:28.998891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d8daf59c-8526-491b-9dbd-0689dabdc2b1 · outbound

This paper cites MLVU: Benchmarking Multi-task Long Video Understanding.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos MLVU: Benchmarking Multi-task Long Video Understanding

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.476958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c637bb6-c0e1-4365-aeb2-b2ce99df42c8 · outbound

This paper cites What specifically did the woman in red do?.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos What specifically did the woman in red do?

Reference 83

Resolution: verified exact; raw_fallback, observed 2026-08-16T10:47:27.742015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5dc0a291-a9f7-4628-9189-4c347f536942 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 86

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:28.982946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d6eaea5e-afe6-429f-8904-6d0a2612da66 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 87

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:28.968516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1468b03a-e953-474b-b861-c6c856c55aba · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 88

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:28.954233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ced68de9-e08b-4081-a72d-bd68d67b5088 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 89

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:28.938683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7e3bac44-c3d4-465d-8ca2-0103fc95d03e · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 90

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:28.924923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e48a6b4c-1d73-4729-9ef1-60a2868867e1 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 91

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:28.910631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3039ca9c-81b2-4b41-a577-32be2eb1fc4b · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 92

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:28.896498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2732f0f9-3674-4ef6-8e83-abdb1de8970e · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 93

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:28.882122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7e3784d1-1663-4669-a1f1-0c66b9cec03f · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 94

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:28.867776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2425f959-a61c-4b00-ad5e-37cfb23e3b2a · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 95

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:28.852937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c5b94f0f-d3da-417d-963a-ade005ceec62 · outbound

This paper cites an unresolved cited work.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Unresolved cited work

Reference 96

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:47:28.836442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 79ab746c-798b-42c2-8208-ebcd573c5ca5 · outbound

This paper cites In Frame 201.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos In Frame 201

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:47:28.821895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 02088992-95d2-40f0-9b7c-174722b03431 · outbound

This paper cites When the person was in the kitchen.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos When the person was in the kitchen

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:47:28.807224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cd0ae2ca-c005-415e-a6fb-d1f94523a7c7 · outbound

This paper cites At 1:20 in the video.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos At 1:20 in the video

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:47:28.790976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 38d34bd1-3ea3-43a7-ad4d-ec6e13aab2d3 · outbound

This paper cites question.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos question

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:47:28.776073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ecbbe075-d80b-46fb-9e5a-35ef8b9985ee · outbound

This paper cites InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.162648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 252a97bc-0ba7-4599-a60a-e63c344bbb2f · outbound

This paper cites Advances in Neural Information Processing Systems37 (2024), 32076–32110.

TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos Advances in Neural Information Processing Systems37 (2024), 32076–32110

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T10:47:27.270496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 46f8794c-4d6e-4420-8c39-7195e583ed0c · inbound

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

ProactiveVideoQA: A Comprehensive Benchmark Evaluating Proactive Interactions in Video Large Language Models TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T18:03:14.040372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d938463f-64c3-4ad2-8bb0-0f1ac0dd97a6 · inbound

EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent cites this paper.

EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T15:38:44.871097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61ad33aa-d5bb-43aa-bcbf-ce181d58f477 · inbound

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? cites this paper.

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance? TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-17T05:39:06.196486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 11abff98-bfa7-4491-9d0d-7670db5d6b1e · inbound

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding cites this paper.

HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:57:53.845048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c6459779-3754-4260-8941-caf8d2ac18f6 · inbound

Don't Pause! Every prediction matters in a streaming video cites this paper.

Don't Pause! Every prediction matters in a streaming video TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Reference 72

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:41:18.125769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9a56d4c2-d23a-4179-84b3-a42f9c4c4bc3 · inbound

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model cites this paper.

Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Reference 164

Resolution: unresolved; no resolver link, observed 2026-07-31T06:20:14.311583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f90c176-5427-4d24-8ab0-82d7e6cc4a71 · inbound

ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding cites this paper.

ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T03:21:48.087769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5571a5f0-8880-4e9d-8541-74175d42959c · inbound

CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models cites this paper.

CRAFT: Compression via Recursive Adaptive Fusion of Video Tokens for Vision-Language Models TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T23:46:51.620346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d082abc-cce4-4720-aa24-69bd9a10092c · inbound

Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation cites this paper.

Aero Realtime: Fully Aligned Input-Output Streams for Low-Latency Streaming Multimodal Generation TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-14T04:39:27.373948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.