← 返回名录条目信息来自其公开主页与公开发布内容。按本站规范，页面不展示任何联系方式。 需要更正或删除？通过收录与更正通道提交，24 小时内处理。
W
Wenzhe Wang
AI systems, multimodal training, and computational imaging. Contributor to VeOmni, verl, and verl-omni.
- 公司
- Zhejiang University
- 位置
- Hangzhou
- Stars
- 1,173
- 粉丝 / 仓库
- 5
代表作品 / 项目
- verl-omni⭐ 1168Multimodal RL training framework for diffusion & omni models
- MMVideoTextRetrieval⭐ 5MMVideoTextRetrieval is an open source video-text retrieval toolbox based on PyTorch.
- software-agent-sdk⭐ 0A clean, modular SDK for building AI agents with OpenHands V1.
- UniRL⭐ 0UniRL is a Framework for Unified Multimodal Model Reinforcement Learning
- tilelang⭐ 0 Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels