CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models

Hugging Face Daily Papers Papers

Summary

CollabVR is a research paper proposing a closed-loop framework that collaboratively integrates vision-language models with video generation models to improve visual reasoning and correct failures in real-time.

Recent "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.
Original Article
View Cached Full Text

Cached at: 05/12/26, 07:29 AM

Paper page - CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models

Source: https://huggingface.co/papers/2605.08735

Abstract

A closed-loop framework collaboratively integrates vision-language models with video generation models at step level to improve visual reasoning by enabling real-time failure detection and correction during video generation.

Recent “Thinking with Video” approaches useVideo Generation Models(VGMs) forvisual reasoningby producing temporally coherentChain-of-Framesas reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on goal-directed tasks:long-horizon drifton multi-step tasks andmid-clip simulation errorsthat compound. Both stem from the absence of explicit reasoning built upon the VGM’s short-horizon visual prior, a role naturally filled byVision-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), aclosed-loop frameworkthat couples the VLM with the VGM atstep-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.

View arXiv pageView PDFProject pageAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.08735 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.08735 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.08735 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning

Hugging Face Daily Papers

Introduces CLVR (Closed-Loop Visual Reasoning), a framework that reformulates text-to-image generation from a single-step process into a closed-loop, multi-step visual reasoning approach using a VLM controller and diffusion models, achieving improved performance on compositional prompts.

Video Models Can Reason with Verifiable Rewards

Hugging Face Daily Papers

VideoRLVR optimizes video diffusion models for verifiable reasoning tasks using reinforcement learning with rule-based rewards, achieving better performance than supervised methods in constraint-satisfying video generation.

Reinforcing Dual-Path Reasoning in Spatial Vision Language Models

Hugging Face Daily Papers

This paper introduces SR-REAL, a unified framework for spatial vision-language models that combines linguistic deduction and 3D geometric reasoning via reinforcement learning, enabling robust multi-step spatial reasoning across diverse tasks.