VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization | Paper Citation Record

Observation 5a2fa8c7-61f6-4b38-ae2a-31187f5485ff · outbound

This paper cites Sora: Openai’s text-to-video model,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Sora: Openai’s text-to-video model,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.216709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation df3ae0ed-6b8b-46a7-8275-2f5ebfeadd13 · outbound

This paper cites Seedance 2.0: Advancing Video Generation for World Complexity.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Seedance 2.0: Advancing Video Generation for World Complexity

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.779852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 622bcf36-6bb3-4297-a3cc-b22d6688253d · outbound

This paper cites Wan: Open and Advanced Large-Scale Video Generative Models.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Wan: Open and Advanced Large-Scale Video Generative Models

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.772082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e574146b-899b-42f2-95b0-b6c82a161f70 · outbound

This paper cites Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.835287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9d02e978-32b1-4e9d-9df2-7d149f67a710 · outbound

This paper cites Are video models ready as zero-shot reasoners? an empirical study with the mme-cof benchmark.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Are video models ready as zero-shot reasoners? an empirical study with the mme-cof benchmark

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.832891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 24c078e5-54b2-410e-9357-bfcbc492cb9d · outbound

This paper cites Flow Matching for Generative Modeling.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Flow Matching for Generative Modeling

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.792383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a407398a-a8a4-40fa-a16f-6b1b61e21558 · outbound

This paper cites an unresolved cited work.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-07-09T13:16:16.269187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b0840d1f-42bd-44c0-8618-b1a7428c19c0 · outbound

This paper cites Video models reason early: Exploiting plan commitment for maze solving,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Video models reason early: Exploiting plan commitment for maze solving,

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.797446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 14a746e8-15b1-4688-bed2-edcefb425a13 · outbound

This paper cites CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.787534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 51ef78b7-f091-4243-bd50-ccc4ea019782 · outbound

This paper cites arXiv preprint arXiv:2511.13704 , year=.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization arXiv preprint arXiv:2511.13704 , year=

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.790002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 35d6a021-b51d-49c9-872d-514c85372ff3 · outbound

This paper cites arXiv preprint arXiv:2511.16669 , year=.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization arXiv preprint arXiv:2511.16669 , year=

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T10:44:36.767125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation dfb1f9f1-2e1a-4432-bbab-dd308b928e20 · outbound

This paper cites Lora: Low-rank adaptation of large language models.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Lora: Low-rank adaptation of large language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.267470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a2c75988-ad05-4032-a963-5674dd0776c9 · outbound

This paper cites A very big video reasoning suite.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization A very big video reasoning suite

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.769740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d9a28caa-ad9a-4c37-82d9-3f1cab962ede · outbound

This paper cites Ruler-bench: Probing rule-based reasoning abilities of next-level video generation models for vision foundation intelligence.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Ruler-bench: Probing rule-based reasoning abilities of next-level video generation models for vision foundation intelligence

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T10:44:36.777391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 03485d67-da83-4cf9-ae76-b395e2a1373a · outbound

This paper cites Denoising diffusion probabilistic models.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Denoising diffusion probabilistic models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.258550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f76dfe5a-055e-4e9e-8482-b6884179adbd · outbound

This paper cites Scalable diffusion models with trans- formers,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Scalable diffusion models with trans- formers,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.247404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1b455d70-6016-400a-93e6-7534c910b243 · outbound

This paper cites Motiondiffuse: Text-driven human motion generation with diffusion model,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Motiondiffuse: Text-driven human motion generation with diffusion model,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.250957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3edddad3-9a20-4a86-8dfd-239324a462ec · outbound

This paper cites Movie Gen: A Cast of Media Foundation Models.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Movie Gen: A Cast of Media Foundation Models

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.794880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 117c5523-37b5-42f2-a964-a1bbddf04972 · outbound

This paper cites Veo 3.1,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Veo 3.1,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.270861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 364255a2-df29-48f6-aed3-827cbf2f0eb4 · outbound

This paper cites Seedance 1.0: Exploring the Boundaries of Video Generation Models.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Seedance 1.0: Exploring the Boundaries of Video Generation Models

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.764583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b99d2df6-a381-4f4e-9bbe-e844073b73ad · outbound

This paper cites Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.759022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5bd0b46a-0b1e-459d-be15-d28b1f3e4a0c · outbound

This paper cites CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.809274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 275e9e24-2158-44b2-a29b-f437e612f0ae · outbound

This paper cites HunyuanVideo: A Systematic Framework For Large Video Generative Models.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.851284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b087e749-a045-450c-b9db-470310e0685e · outbound

This paper cites Open-Sora: Democratizing Efficient Video Production for All.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Open-Sora: Democratizing Efficient Video Production for All

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.753689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c7613c32-de15-4a65-9b8c-368a5dd4464d · outbound

This paper cites VBench++: Comprehen- sive and versatile benchmark suite for video generative models,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization VBench++: Comprehen- sive and versatile benchmark suite for video generative models,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.241882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 32142a1a-3426-4ebd-8db3-d29d6ae8d294 · outbound

This paper cites Cosmos World Foundation Model Platform for Physical AI.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Cosmos World Foundation Model Platform for Physical AI

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.811680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 41590636-0f5c-4401-8ca2-229780b66fb2 · outbound

This paper cites VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T10:44:36.814378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c8ff8407-e7a4-47da-8347-731ba78d530f · outbound

This paper cites WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.751338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d18345d4-1910-4619-94ee-46522b58482a · outbound

This paper cites Towards physical understanding in video generation: A 3d point regularization approach,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Towards physical understanding in video generation: A 3d point regularization approach,

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.756367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8c7a2bda-205f-42fd-aa82-4477059e6694 · outbound

This paper cites Phyt2v: Llm-guided iterative self-refinement for physics-grounded text-to-video gen- TECHNICAL REPORT 13 eration,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Phyt2v: Llm-guided iterative self-refinement for physics-grounded text-to-video gen- TECHNICAL REPORT 13 eration,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.243871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 70840a70-1a89-4112-916a-1121188a7c13 · outbound

This paper cites Physdreamer: Physics-based interaction with 3d objects via video generation,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Physdreamer: Physics-based interaction with 3d objects via video generation,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.245713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7fb2f6b0-633b-45e7-9781-5d0fc4af74b1 · outbound

This paper cites Physgen: Rigid- body physics-grounded image-to-video generation,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Physgen: Rigid- body physics-grounded image-to-video generation,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.249088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d3f6ff42-94a8-4b30-bbd2-b3e871c46145 · outbound

This paper cites FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization FLIP: Flow-Centric Generative Planning as General-Purpose Manipulation World Model

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.762035Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8ac8ee76-331f-4870-958a-0b29d6df242d · outbound

This paper cites Physanimator: Physics- guided generative cartoon animation,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Physanimator: Physics- guided generative cartoon animation,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.253185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 666f42e0-a5f3-403c-bdc2-fead69cd7f24 · outbound

This paper cites Motioncraft: Physics-based zero-shot video genera- tion,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Motioncraft: Physics-based zero-shot video genera- tion,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.254965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 11d8ba6e-86b8-41fe-89f2-2c3e1440bad1 · outbound

This paper cites ProPhy: Progressive Physical Alignment for Dynamic World Simulation.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization ProPhy: Progressive Physical Alignment for Dynamic World Simulation

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.774617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b26f6c7c-b431-4a6b-ba84-c5792dcdcf64 · outbound

This paper cites MagicTime: Time-lapse video generation models as metamorphic simulators,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization MagicTime: Time-lapse video generation models as metamorphic simulators,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.256774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 78fdce5f-376a-420d-8d8c-78a1f6190846 · outbound

This paper cites Can world simulators reason? Gen-ViRe: A generative visual reasoning benchmark.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Can world simulators reason? Gen-ViRe: A generative visual reasoning benchmark

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.784916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 997a36fb-569a-42a8-b392-62f02be18087 · outbound

This paper cites Video models are zero-shot learners and reasoners.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Video models are zero-shot learners and reasoners

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.802140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 121abd1f-75c9-45b2-b55c-fbc99c161212 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Chain-of-thought prompting elicits reasoning in large language models

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.278041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f0134a95-3feb-4039-92fe-fed81733d72c · outbound

This paper cites Mme-cof-pro: Evaluating reasoning coherence in video generative models with text and visual hints.arXiv preprint arXiv:2603.20194, 2026.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Mme-cof-pro: Evaluating reasoning coherence in video generative models with text and visual hints.arXiv preprint arXiv:2603.20194, 2026

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.858653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 522a6245-66ba-4160-b948-fb59ee29d99c · outbound

This paper cites Demystifying Video Reasoning.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Demystifying Video Reasoning

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.848444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2913a767-29ff-4d2b-946d-8c264269f546 · outbound

This paper cites Reasoning via video: The first evaluation of video models’ reasoning abilities through maze-solving tasks.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Reasoning via video: The first evaluation of video models’ reasoning abilities through maze-solving tasks

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.840804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 49d4c909-9060-4831-97af-b6330ca43f6c · outbound

This paper cites Mmgr: Multi-modal generative reasoning.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Mmgr: Multi-modal generative reasoning

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.830231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d156c6ed-f222-411d-a930-ae4b607b426a · outbound

This paper cites V-reasonbench: Toward unified reasoning benchmark suite for video generation models.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization V-reasonbench: Toward unified reasoning benchmark suite for video generation models

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.782394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 651f20ac-579d-421a-8af1-827746dee51d · outbound

This paper cites Ui2v-bench: An understanding- based image-to-video generation benchmark,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Ui2v-bench: An understanding- based image-to-video generation benchmark,

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.799948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 856341ca-efa8-4bab-a6bb-7b1eeec1c6ec · outbound

This paper cites How Far Are Video Models from True Multimodal Reasoning?.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization How Far Are Video Models from True Multimodal Reasoning?

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.838077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e26b1b27-2671-47b7-bf4d-68e37e734898 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.843471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bdc52e84-8923-4458-8fcb-e942866f9e42 · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.845977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation deecfa7b-19c2-41d5-a114-d0b8a95fafbe · outbound

This paper cites Inference-time scaling for diffusion models beyond scaling denoising steps,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Inference-time scaling for diffusion models beyond scaling denoising steps,

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.279857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 90a80798-1126-4b9a-9c8c-834e6acb913e · outbound

This paper cites Video-t1: Test-time scaling for video generation,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Video-t1: Test-time scaling for video generation,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.260233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7fe8fd98-52e1-4ba1-a3ac-e79dde3036f7 · outbound

This paper cites Scaling Image and Video Generation via Test-Time Evolutionary Search.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Scaling Image and Video Generation via Test-Time Evolutionary Search

Reference 55

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T10:44:36.861793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7cdb1d7b-0caa-4497-b63e-a74babd6ed57 · outbound

This paper cites Can test-time scaling improve world foundation model?.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Can test-time scaling improve world foundation model?

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.262068Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0643ccb8-94a9-4f53-a37a-6ef5a5d8c70b · outbound

This paper cites Thinking in frames: How visual context and test-time scaling empower video reasoning.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Thinking in frames: How visual context and test-time scaling empower video reasoning

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.819799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 196cbccb-f30f-4709-8d8d-2a87670a68ed · outbound

This paper cites Self-Refining Video Sampling.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Self-Refining Video Sampling

Reference 58

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.822055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9f5c8cc6-dfcf-4bdd-bb50-fddf0d2cbdec · outbound

This paper cites Vision-language models for vision tasks: A survey,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Vision-language models for vision tasks: A survey,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.263797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 38db3d05-259b-4c26-98fe-997325f2bdfd · outbound

This paper cites Otter: A multi-modal model with in-context instruction tuning,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Otter: A multi-modal model with in-context instruction tuning,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.265647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ac11893b-d790-474a-b3e8-987d86eb8331 · outbound

This paper cites Cross-modal causal relational reasoning for event-level visual question answering,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Cross-modal causal relational reasoning for event-level visual question answering,

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.274358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 34b7b977-7bcd-4530-b598-0117550aa64b · outbound

This paper cites Language-aware spatial-temporal collaboration for referring video segmentation,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Language-aware spatial-temporal collaboration for referring video segmentation,

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.272597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d28f9118-c0c5-448e-b494-3e5058a60521 · outbound

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

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.827322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1ef5e2ec-7c53-4b66-8092-847994b7ba01 · outbound

This paper cites GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.816892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0e3f530e-357d-408c-a5af-8338b51da26b · outbound

This paper cites Self-correcting llm-controlled diffusion models,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Self-correcting llm-controlled diffusion models,

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.238240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 42427bc5-8a99-4958-b17b-6688a6999ec3 · outbound

This paper cites Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal llms,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal llms,

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.233012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5f3f4aee-245d-48dd-8234-7243b769e53f · outbound

This paper cites Mindomni: Unleashing reasoning generation in vision language models with rgpo,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Mindomni: Unleashing reasoning generation in vision language models with rgpo,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.231221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation eaabb265-9f36-4c6d-88a4-591cfff12d08 · outbound

This paper cites Videodirectorgpt: Consistent multi-scene video generation via llm-guided planning,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Videodirectorgpt: Consistent multi-scene video generation via llm-guided planning,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.276116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e73844c5-41c0-4276-b2d0-3dc720c37b49 · outbound

This paper cites Vlipp: Towards physically plausible video generation with vision and language informed physical prior,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Vlipp: Towards physically plausible video generation with vision and language informed physical prior,

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.240165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation afdb13c4-28d4-498f-8501-dd10298baabc · outbound

This paper cites Videoagent: Long-form video understanding with large language model as agent,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Videoagent: Long-form video understanding with large language model as agent,

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.234804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e254e73d-49b7-466b-a8cb-34739b3e5b7a · outbound

This paper cites VChain: Chain-of-Visual-Thought for Reasoning in Video Generation.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization VChain: Chain-of-Visual-Thought for Reasoning in Video Generation

Reference 71

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.804558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1e8a46db-da97-47f2-9914-08673b937a3f · outbound

This paper cites Video Models Can Reason with Verifiable Rewards.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Video Models Can Reason with Verifiable Rewards

Reference 72

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.806976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e082c361-59df-4769-bf90-26132d396e0a · outbound

This paper cites Dual-process image generation,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Dual-process image generation,

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.227430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bb2bc99e-989d-4b3b-a177-a2b1872e68de · outbound

This paper cites Learning an Image Editing Model without Image Editing Pairs.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Learning an Image Editing Model without Image Editing Pairs

Reference 74

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.824660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bf8d4835-ffa5-48fc-ae36-dda67cc92aaa · outbound

This paper cites Diffusion-drf: Differentiable reward flow for video diffusion fine-tuning.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Diffusion-drf: Differentiable reward flow for video diffusion fine-tuning

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:44:36.866479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8f5f9792-af90-411c-aefd-a0e2b0850cb8 · outbound

This paper cites Lightx2v: Light video generation inference framework,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Lightx2v: Light video generation inference framework,

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.222858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation dee8e5c6-7b07-487e-b0a7-a4e0c5107593 · outbound

This paper cites Improved distribution matching distillation for fast image synthesis,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Improved distribution matching distillation for fast image synthesis,

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.220741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9f548417-de46-4454-af42-6d05cc4f8232 · outbound

This paper cites Openai o3 and o4-mini system card,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Openai o3 and o4-mini system card,

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.225265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9c49f700-a81b-4b1a-9613-ddb57c845636 · outbound

This paper cites Kling AI launches video 2.6 model with “simultaneous audio-visual generation.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Kling AI launches video 2.6 model with “simultaneous audio-visual generation

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.229350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9c5024d0-3aa6-4518-94e2-e7020981ba2d · outbound

This paper cites Qwen3-VL Technical Report.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Qwen3-VL Technical Report

Reference 80

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.856094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ef39d6ca-aca9-48b0-bd48-b3a8cf1c58da · outbound

This paper cites Flow-grpo: Training flow matching models via online rl,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Flow-grpo: Training flow matching models via online rl,

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.214655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d65837a3-37b2-4f7d-9a49-abca4427436b · outbound

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

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis,

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.218780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2bdb73d8-9f60-4d07-982c-d66250bedf61 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 83

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.853761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f089b9a7-c3f6-4acc-9969-812f1bfda836 · outbound

This paper cites HunyuanVideo 1.5 Technical Report.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization HunyuanVideo 1.5 Technical Report

Reference 84

Resolution: verified exact; local_arxiv, observed 2026-06-30T10:44:36.863984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 277b75f9-589a-4dfa-a3c6-2424af01dd3a · outbound

This paper cites Fvd: A new metric for video generation,.

VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization Fvd: A new metric for video generation,

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T13:16:16.236439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers