Paper Citation Record · LEDGER

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

As of 22 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 6 inbound Pith citation observations for arXiv:2603.12262.

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

pith.paper-citation-record.v1
2603.12262 v2

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T18:23:40.253289Z

measured 64 of 64 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:39:27.532772Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T22:13:59.645900Z

Reference resolution

58 of 58 outbound references displayed

verified exact0
verified fuzzy0
unresolved58
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8e99e725-5aba-4973-95bb-5b827d8b9968 · outbound

This paper cites Qwen2.5-VL Technical Report.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Qwen2.5-VL Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:02.801199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fa8bfbf-cd7a-476c-a2ff-7c48ef810cf4 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:02.896774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fb0e1da-a186-4b5b-820d-a58f17688270 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:03.042987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16375c65-2451-4d75-bd99-38517820b9e9 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:03.207568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f92a6c42-4279-4756-8420-41100ac8d108 · outbound

This paper cites Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:03.335839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99168848-cf7b-4027-a768-d24086c0f006 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:03.424022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1fee58d-f469-49b4-9e72-a85e7e68d802 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:03.518008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c72ab13-0577-4f88-a581-07e4a7487e32 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:03.591350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 028f37a1-77bf-4f2e-ac3e-2a6c2a2c2042 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:03.655309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47763309-2012-4156-a915-91fa64c3dc9e · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:03.752540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf1c0c1d-f70c-400b-838d-1f7cd07f688a · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:03.857472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5526f41-df96-4ebb-bff9-010e3381e6d0 · outbound

This paper cites Nature645(8081), 633–638 (2025) 2, 6, 14.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Nature645(8081), 633–638 (2025) 2, 6, 14

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:03.976140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32b92905-4f1d-4a62-afa9-5ebd1ace1835 · outbound

This paper cites an unresolved cited work.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:04.131937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08981e30-eabf-42a2-991d-a7c7d7ff0a15 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:04.237471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ba576f9-8857-43c3-9b7c-5ef813fde984 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:04.405864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5d4ebb6-26f7-4eeb-a9e0-0467d261e7ed · outbound

This paper cites Science303(5664), 1634–1640 (2004) 2.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Science303(5664), 1634–1640 (2004) 2

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.109989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 249a6e22-db5f-4a94-b3bf-afeb4c81ac55 · outbound

This paper cites TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.113299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7519dacb-3655-4ef2-9502-174ce9c2aa74 · outbound

This paper cites In: Conference on Language Modeling (2024) 9.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Conference on Language Modeling (2024) 9

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.116176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b9d569d-d45c-43e7-ab14-28b970535730 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.119257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9842174-17e6-41ff-a497-2c2acc7f7b2d · outbound

This paper cites Transactions on Machine Learning Research (2025) 9, 10.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Transactions on Machine Learning Research (2025) 9, 10

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.123177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37605bc5-0511-4e44-a6f5-1880f380f181 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.126992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06fb706d-f82e-496b-9c16-5b23dfc26711 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.131101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c876c8c-a4d4-4c90-86f2-4aadd3f71d03 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.134636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 603103ea-43d9-415d-bf97-d1e4e8b8de3c · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.138682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba4e8fd2-6dc9-40b6-bc49-ac1e434198d4 · outbound

This paper cites arXiv preprint arXiv:2506.05332 (2025) 8.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously arXiv preprint arXiv:2506.05332 (2025) 8

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.141551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43fbf30b-2bc3-4141-acc6-7f7e6f52eb0c · outbound

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

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.145298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eeaa6a5-e445-400b-9385-6b0efe8a078b · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Understanding R1-Zero-Like Training: A Critical Perspective

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.150154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a787925b-3547-40fe-a0ab-1d223b5bdd5b · outbound

This paper cites LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.153348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ef3eaa8-dc97-44ed-a05b-83347f69bbd7 · outbound

This paper cites of IEEE Intl.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously of IEEE Intl

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.156849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ac425e6-b7fc-4c72-8a16-5ece88df5a14 · outbound

This paper cites an unresolved cited work.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.160190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce4040bc-7a43-4085-bcc8-ccd3d4750369 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.163671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ebedc6a-c44c-435b-aed7-210ff96b805a · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.166571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d9e2c63-a623-4d8e-b402-fb736f7e1f07 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.169742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2327916-b436-447f-ae81-ba7fa6a31119 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously HybridFlow: A Flexible and Efficient RLHF Framework

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.173085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23384fb8-4222-42eb-ad90-62701a1e7ec3 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.176485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b891dee8-37f4-4094-9450-dd94180386f5 · outbound

This paper cites an unresolved cited work.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Unresolved cited work

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.179373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e5de503-2d4c-413e-b1aa-2adfc31810ed · outbound

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

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.182278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56bd85b8-86da-40f9-877e-1ee68aa6a68b · outbound

This paper cites arXiv preprint arXiv:2510.17238 (2025) 14.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously arXiv preprint arXiv:2510.17238 (2025) 14

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.186722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07771565-0721-4142-a347-b54346456de8 · outbound

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

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.190950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d83f4acc-3e22-4766-90ae-a86c4b3a65b0 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.195799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f87b8b52-fcc2-4b2a-8cc9-3a36a9037d49 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.198709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5a03ee2-3b6c-4f01-8854-9e487e50d187 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.202031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b38036f5-c116-493d-a122-0f3157f40406 · outbound

This paper cites Streaming Video Instruction Tuning.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Streaming Video Instruction Tuning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.205595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9e4c72d-81f5-4bfc-a8f3-0f6278605829 · outbound

This paper cites an unresolved cited work.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.209790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31584e5b-92ad-44c4-b4e8-c1c05919e38c · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.212990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a951be6-03a1-47bd-8a3d-01c2883e52e5 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.216451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 904f1110-43dc-427e-8456-3c38a3bdbf4b · outbound

This paper cites StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.219397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c58e2022-8e51-4fd1-963f-ab6233c9cf15 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.222589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 374fc4d2-eb00-456a-94f7-50d2f7e101c2 · outbound

This paper cites MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.225391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7143764-37ba-4f83-9dee-69c86b8320f0 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.228889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baa60924-c3fe-42b0-83bf-7789178e828b · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.231532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation befe0f0b-9765-41fa-bce1-312fc6b69e6e · outbound

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

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.234499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1004fbd7-14df-4823-ad14-d38faca58c76 · outbound

This paper cites In: Proc.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously In: Proc

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.238144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c767cd13-4442-4d46-b57d-9660c9126f67 · outbound

This paper cites LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.241140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd5198ee-f38b-406a-992e-ae58d66e7e35 · outbound

This paper cites Transactions on Machine Learning Research (2025) 9, 10.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Transactions on Machine Learning Research (2025) 9, 10

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.244264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d5f4557-4b8d-4c53-9427-7e7dd722cb53 · outbound

This paper cites Transactions on Machine Learning Research (2025) 8, 10.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Transactions on Machine Learning Research (2025) 8, 10

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.247203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9f1a70e-3ada-4f53-85b9-c40cc55358d4 · outbound

This paper cites PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.250047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e494b35-bdee-45cd-9699-62b6d0bc0ed1 · outbound

This paper cites HUB-AND-SPOKE.

Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously HUB-AND-SPOKE

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T18:23:40.253289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 393a6d2c-8ec2-4bae-a1c3-04800cbabd82 · inbound

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

LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-20T02:18:27.127261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 107746f8-e14a-43c1-b43d-b04548dc1879 · inbound

FOLIO: Focused Semantic Memory for Streaming Video Understanding cites this paper.

FOLIO: Focused Semantic Memory for Streaming Video Understanding Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T05:40:42.117347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd75dc3c-dec7-44b0-9bb4-998d17613aa3 · inbound

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

ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T03:21:44.527117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce204b9c-a39a-47c6-85d5-c11a4fc3e4c7 · inbound

StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding cites this paper.

StreamArena: Toward Continuous, Interactive, and Long-Horizon Agentic Streaming Video Understanding Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T00:50:24.292417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06a774ac-2a5a-4184-96d6-fc7a78049db5 · 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 Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-14T04:39:27.532772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a28ddb3-19d6-4c3b-b438-6432bc1232cc · inbound

StreamFlow: Dynamic Memory Flows for Streaming Video Understanding cites this paper.

StreamFlow: Dynamic Memory Flows for Streaming Video Understanding Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T13:41:18.272347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.