OpenCoF: Learning to Reason Through Video Generation

Hugging Face Daily Papers Papers

Summary

OpenCoF introduces a reasoning video dataset and a fine-tuned video generation model that improves temporal reasoning through diverse supervision and explicit reasoning tokens, showing significant gains on four video reasoning benchmarks.

Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recent video generation models offer a reasoning path distinct from previous Chain-of-Thought (CoT): reasoning can unfold through temporally connected frames, known as Chain-of-Frame (CoF) reasoning. However, existing video generators are primarily trained on general video corpora, still lacking diverse supervision and dedicated designs for CoF reasoning. To address this gap, we introduce OpenCoF, a framework comprising the OpenCoF-17K dataset, a reasoning video dataset spanning 11 task families, and Wan-CoF, a fine-tuned video model for studying whether diverse temporal supervision improves CoF behavior. Across four video reasoning benchmarks, Wan-CoF achieves considerable gains over the Wan2.2-I2V-A14B baseline. Building on this, we empirically explore more advanced designs for CoF capabilities, i.e., equipping the model with visual and textual reasoning tokens. This mechanism respectively captures low-level visual cues and high-level semantic priors for spatial and temporal reasoning. Through performance comparisons and attention analysis, we examine how these tokens contribute across model depth, denoising steps, space, and time. Our results suggest that stronger video reasoning requires both broad temporal supervision and explicit mechanisms for organizing intermediate reasoning state. We open-source the dataset, model, and code to facilitate future research on reasoning-oriented video generation.
Original Article
View Cached Full Text

Cached at: 07/10/26, 06:17 AM

Paper page - OpenCoF: Learning to Reason Through Video Generation

Source: https://huggingface.co/papers/2607.08763

Abstract

OpenCoF framework introduces a reasoning video dataset and model that improve temporal reasoning through diverse supervision and explicit reasoning tokens for visual and textual cues.

Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recentvideo generation modelsoffer a reasoning path distinct from previous Chain-of-Thought (CoT): reasoning can unfold through temporally connected frames, known asChain-of-Frame(CoF) reasoning. However, existing video generators are primarily trained on general video corpora, still lacking diverse supervision and dedicated designs for CoF reasoning. To address this gap, we introduce OpenCoF, a framework comprising theOpenCoF-17K dataset, a reasoning video dataset spanning 11 task families, and Wan-CoF, a fine-tuned video model for studying whether diversetemporal supervisionimproves CoF behavior. Across fourvideo reasoning benchmarks, Wan-CoF achieves considerable gains over the Wan2.2-I2V-A14B baseline. Building on this, we empirically explore more advanced designs for CoF capabilities, i.e., equipping the model with visual andtextual reasoning tokens. This mechanism respectively captures low-level visual cues and high-level semantic priors for spatial and temporal reasoning. Through performance comparisons andattention analysis, we examine how these tokens contribute across model depth,denoising steps, space, and time. Our results suggest that stronger video reasoning requires both broadtemporal supervisionand explicit mechanisms for organizing intermediate reasoning state. We open-source the dataset, model, and code to facilitate future research on reasoning-oriented video generation.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2607\.08763

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.08763 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.08763 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.08763 in a Space README.md to link it from this page.

Collections including this paper1

Similar Articles

VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding

Hugging Face Daily Papers

VideoKR introduces a large-scale video reasoning dataset and benchmark designed to enhance knowledge-intensive video understanding through expert-domain content and human-in-the-loop example generation. The dataset contains 315K video reasoning examples over 145K expert-domain videos.

A Very Big Video Reasoning Suite

Papers with Code Trending

This paper introduces the Very Big Video Reasoning (VBVR) dataset and benchmark, a large-scale resource with over one million video clips across 200 reasoning tasks, enabling systematic study of spatiotemporal reasoning and showing early signs of emergent generalization.

CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition

Hugging Face Daily Papers

CogOmniControl is a reasoning-driven framework for controllable video generation that uses a specialized vision-language model (CogVLM) trained on anime production data to infer creative intent from sparse conditions, then guides a diffusion-based generator via reinforcement learning, achieving state-of-the-art results on new benchmarks.

MotiMotion: Motion-Controlled Video Generation with Visual Reasoning

Hugging Face Daily Papers

MotiMotion introduces a reasoning-then-generation framework for motion-controlled video generation that uses vision-language reasoning to refine trajectories and a confidence-aware control scheme to improve plausibility, outperforming existing approaches on a new benchmark.