← 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。
Y
Yuxiang Chen
MS student @ Zhejiang University. Working on multimodal / speech / vision LLMs — half research, half poking things to see how they break.
- 公司
- Zhejiang University
- 位置
- Hangzhou, China
- Stars
- 1
- 粉丝 / 仓库
- 4
代表作品 / 项目
- LightVLM⭐ 1A tiny, hackable vision-language model. CLIP/SigLIP + Qwen2.5 + minimal LoRA, ~1.5k lines.
- frieren-agent-monitor⭐ 0A local open-source Frieren desktop companion for monitoring Claude Code, Codex, and Cursor sessions.
- paper-radar⭐ 0Finds the AI papers 28 tech companies put on arXiv over any date range, and splits lead authorship from bylines. A SKILL.md agent skill — no ML, no state, stdlib only.
- verl-omni⭐ 0Multimodal RL training framework for diffusion & omni models
- SenseNova-U1⭐ 0SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles