好网站,从官网开始
企业认领/联系与合作
官网导航 提交官网
V

VideoWorld官网

豆包等推出的开源视频生成模型

官网资料

网站名称
VideoWorld
身份核实
尚未完成企业认领核实
最近更新
链接检测
尚未检测

关于 VideoWorld

--> VideoWorld: Exploring Knowledge Learning from Unlabeled Videos --> 图片居中 More Research HyperNeRF Nerfies LatentFusion PhotoShape --> VideoWorld: Exploring Knowledge Learning from Unlabeled Videos Zhongwei Ren 1,2 , Yunchao Wei 1 † , Xun Guo 2 , Yao Zhao 1 , Bingyi Kang 2 , Jiashi Feng 2 , Xiaojie Jin 2 † ‡ 1 Beijing Jiaotong University, 3 ByteDance Seed ( † Correspondence, ‡ Project Lead) Paper arXiv Video Code Data --> Figure 1: VideoWorld explores learning knowledge from raw videos, ranging from task-specific rules to high-level reasoning and planning capabilities.Compared to other learning methods: reinforcement learning (RL), supervised learning (SL) and text-based learning, it offers three advantages: 1. better generalization with unified visual representation for various tasks and interfaces, 2. lower mannual annotation burden, and 3. richer real-world information than text description. Figure 2: VideoWorld plays Go by generating next board state. Figure 3: VideoWorld controls robotic arms across different environments. Abstract This work explores whether a deep generative model can learn complex knowledge solely from visual input, in contrast to the prevalent focus on text-based models like large language models (LLMs). We develop VideoWorld, an autoregressive video generation model trained on raw video data, and test its knowledge acquisition abilities in video-based Go and robotic control tasks. Our experiments reveal two key findings: (1) video-only training provides sufficient information for learning knowledge, including rules, reasoning and planning capabilities, and (2) increasing the compactness of visual representations significantly enhances learning efficiency. To improve both the efficiency and efficacy of knowledge learning, we introduce the Latent Dynamics Model (LDM) as a key component of VideoWorld. Remarkably, VideoWorld reaches a 5-dan professional level in the Video-GoBench with just a 300-million-parameter model, without relying on search algorithms or reward mechanisms typical in reinforcement learning. In robotic tasks, VideoWorld effectively learns diverse control operations and generalizes across environments, approaching the performance of oracle models in CALVIN and RLBench. This study opens new avenues for knowledge acquisition from visual data, with all code, data, and models to be open-sourced for further research. --> 🔥 Highlights 1. We explore for the first time, whether video generation models can learn sophisticat

访问提示

本站仅提供官网信息与访问导航,不代表对该网站的产品、服务或交易作出担保。访问外部网站时,请核对网址,注意账号和财产安全。

同类型网站 366

查看分类

AutoGPT 是面向自主智能体的开源平台,支持用自然语言或可视化流程创建、运行和管理能够持续执行任务的智能体。

支持多 AI Agent 框架的可视化管理面板,支持 OpenClaw 和 Hermes Agent 双引擎,内置智能助手一键安装诊断

让更多人找到你的官网

提交网站信息,建立清晰、完整的官网资料。

免费提交官网

咨询提交、推广、认领

客服微信二维码,长按识别或保存后使用微信扫一扫

扫一扫添加微信,沟通官网导航提交、认领、推广需求。

可长按识别,或保存图片后在微信扫一扫中识别。

添加时可备注“官网导航”,便于沟通您的企业需求。

保存二维码 打开原图