titleCollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
authorsJoowon Kim, Seungho Shin, Joonhyung Park, Eunho Yang
date2026-05-09
venuearXiv (preprint, not peer reviewed)
idarXiv:2605.08735
affiliationKAIST AI
upvotes71 (Hugging Face Daily Papers, 2026-11-01)
linksabs pdf hf code
abstractRecent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on goal-directed tasks: long-horizon drift on multi-step tasks and mid-clip simulation errors that compound. Both stem from the absence of explicit reasoning built upon the VGM's short-horizon visual prior, a role naturally filled by Vision-Language Models (VLMs), but where to place the VLM is non-trivial: upfront plans commit before any frame is generated and post-hoc critiques over whole videos intervene too late. We propose VLM-VGM Collaborative Video Reasoning (CollabVR), a closed-loop framework that couples the VLM with the VGM at step-level granularity: the VLM plans the immediate next action, inspects the clip the VGM generates, and folds the verifier's diagnosis directly into the next action prompt to repair detected failures. On Gen-ViRe and VBVR-Bench, CollabVR improves both open-source and closed-source VGMs over single-inference, Pass@k, and prior test-time scaling baselines at matched compute, with the largest gains on the hardest tasks. It also yields further improvements on top of a reasoning-fine-tuned VGM, indicating that step-level VLM supervision is orthogonal to and stackable with reasoning-oriented fine-tuning. We provide video samples and additional qualitative results at our project page: https://joow0n-kim.github.io/collabvr-project-page.

cite

@misc{kim2026collabvr,
  title={CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models},
  author={Joowon Kim and Seungho Shin and Joonhyung Park and Eunho Yang},
  year={2026},
  eprint={2605.08735},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2605.08735}
}