Shaohang Wei

SylvainWei

·

https://sylvain-wei.github.io

AI & ML interests

NLP, LLM

Recent Activity

upvoted a paper 1 day ago

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

upvoted a paper 5 days ago

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

upvoted a paper 7 days ago

Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs

View all activity

Organizations

commented a paper 10 months ago

Mitigating Overthinking through Reasoning Shaping

Paper • 2510.09535 • Published Oct 10, 2025 • 5 •

New activity in SylvainWei/TIME-Lite about 1 year ago

Add specific tags for discoverability

#2 opened about 1 year ago by

commented a paper over 1 year ago

FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation

Paper • 2503.06680 • Published Mar 9, 2025 • 20 •