跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 17 天前AI 評分48

Video-Coder:以強化學習提升影片生成的智能體編碼

Video-Coder: Reinforcing Agentic Coding for Video Generation

AI 導讀

Video-Coder 是一個以程式碼驅動的影片生成智能體,會自行編寫及執行程式碼,構建動態 3D 場景,並經監督式微調和強化學習訓練。實驗中,Video-Coder 在 PhyGenBench 的表現較 Minimax-H3 高約 7 分,在 VBench-2.0 高 24 分。研究團隊公開了數據、模型及程式碼。

正文

Abstract

Video-Coder is a code-driven video generation agent that writes and executes code to construct dynamic 3D scenes, trained with supervised fine-tuning and reinforcement learning using execution and video rewards to improve controllable video generation.

Recent years have witnessed remarkable progress in video generation in terms of visual quality and temporal consistency. However, generating videos with precise spatial structure, coherent motion dynamics, and controllable scene composition remains challenging. In this paper, we introduce Video-Coder, the first attempt to train a code-driven video generation agent, which autonomously writes and executes code to construct a dynamic 3D scene (Draft Video) that provides structure and motion signals to downstream video generators. To support this paradigm, we design a dedicated data pipeline and curate two high-quality datasets, Video-Coder-SFT-6k and Video-Coder-RL-2k, which contain diverse prompts and ground-truth reference videos. We further develop the Video- Coder Harness, a unified interactive environment integrating code execution, 3D scene rendering, and execution feedback for agent training and inference. We then train Video-Coder with SFT fol- lowed by harness-native agentic reinforcement learning with dual reward feedback, which combines execution-based and video-based rewards. Additionally, we design an annealing training strategy that gradually reduces the execution reward over time, allowing the model to rely more on the video reward in the later training stages. Experiments show that Video-Coder achieves significant gains, improving Minimax-H3 by approximately 7 points on PhyGenBench and 24 points on VBench-2.0. We hope this work can serve as an open foundation for coding agents in video generation, and we fully open-source our data, models, and code

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2611.09894

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 2

Video-Coder/Video-Coder-9B

9B •

Updated 23 minutes ago

•

220

Video-Coder/Video-Coder-SFT-9B

1.47M •

Updated 22 minutes ago

•

219

Datasets citing this paper 1

Video-Coder/Train-Data

Updated 20 minutes ago

•

119

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.09894 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co