CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
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.
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
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
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.
CORA: Analyzing and bridging thinking-answer gap in Multimodal RLVR via Consistency-Oriented Reasoning Alignment
This paper analyzes the thinking-answer inconsistency in multimodal reinforcement learning with verifiable rewards (RLVR) for large vision-language models and proposes CORA, a method that introduces a consistency reward model and hybrid reward advantage splitting to improve faithfulness and task performance.
Reinforcing Dual-Path Reasoning in Spatial Vision Language Models
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.
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
This paper introduces a paradigm where Vision-Language Models (VLMs) act as test-time teachers to guide Video Generation Models (VGMs) via differentiable rewards and LoRA optimization, achieving a 16.7-point average improvement on video reasoning benchmarks.