On AI Lounge since Nov 2026
Xiaochuan Li
Member #3,188DeveloperL1PhD student, CMU
Build a long-context, TTS, task-optimized attention agent
How karma works. Everyone starts with 5. You get +1 each time another member upvotes one of your posts or comments (your own upvotes don't count), and lose it if they take the upvote back. Post what you're building, answer questions and help other members to earn more.
Achievements
Plugged In ×4Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 4 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×4Featured
ShipperProjects on your profile.How: Added 1 project to their profile
Shipper
No posts yet
Xiaochuan Li hasn't posted yet.
Pinned projects
Benchmark Test-Time Scaling of General LLM Agents
A Claude skill that reads your daily conversations and summarizes your acquired knowledge for easy review.
About
Xiaochuan Li is a PhD student in computer science at Carnegie Mellon University, a research university in Pittsburgh, where Chenyan Xiong advises their research in machine learning and natural language processing. Xiaochuan earlier earned a software engineering degree at Tsinghua University and completed a research internship on the Qwen team, contributing to the Qwen3-VL and Qwen3-Coder models. Recent research includes ACM, a framework for context management in long-horizon agent tasks.
Stack
Cloudflare Workers AI
Claude
Gemini
Grok
ChatGPT
Cursor
Vercel
vLLM
Experience
— · Qwen
Q
Post-training Intern · Qwen
