On AI Lounge since Nov 2026
Yaxin Luo
Member #4,187DeveloperL2PhD Researcher, MBZUAI
Post-Training Foundation Model
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
Shipper ×2Projects on your profile.How: Added 5 projects to their profile
Shipper×2
No posts yet
Yaxin Luo hasn't posted yet.
Pinned projects
Local, read-only browser for MoH agent trajectories
The open-source design agent and harness, better than Claude Design on academic communication artifacts production. This DesignHarness can also be used with any coding harness you like ( Codex/Claude Code/Kimi Code/Pi/OpenCode etc..) and any agentic model you want.
agenticagentic-designlong-horizon-agentsmeta-harnessrsi
A Claude Code skill that picks the clearest way to explain something (STE text, typeset diagrams, interactive pages, narrated 3b1b-style videos) and checks its own output
claude-codeclaude-skillsexplainerllmmanim
(ACL 2026 Main) LLMSurgeon recovers the pretraining data mixture of any LLM from only its generated text — no weights, no training data. A calibrated domain classifier plus label-shift correction de-blurs biased predictions. Ships with LLMScan, a benchmark on 8 open-source LLMs.
acl2026data-mixturedata-provenancelabel-shiftlarge-language-models
Jev-powered /effort advisor for Claude Code: tells you when to switch effort, per prompt
About
Yaxin Luo is a PhD researcher at MBZUAI, the Mohamed bin Zayed University of Artificial Intelligence in Abu Dhabi. Yaxin has interned at Meituan's talent program since September 2026 and released open-source work such as AutoDesign and LLMSurgeon, the latter accepted at ACL 2026. Yaxin now works on post-training agents for long, multi-step specialist tasks, shifting capabilities a harness supplies into the model.
Stack
Experience
Research Intern - Talent Program · Meituan
— · Meituan
M
Research Intern · Meituan
M(
Research Assistant · Mbzuai (Mohamed Bin Zayed University Of Artificial Intelligence)
SA
Research Assistant · Shanghai AI Laboratory
XU
Research Assistant · Xiamen University
PU
Summer Internship · Peking University
