Yuansheng Ni

yuanshengni

·

https://yuanshengni.github.io/

AI & ML interests

NLP

Recent Activity

upvoted a paper 14 days ago

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

upvoted a paper 16 days ago

Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models

authored a paper 20 days ago

SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code Understanding

View all activity

Organizations

yuanshengni 's papers 14

arxiv:2606.06880

arxiv:2603.16124

arxiv:2510.23642

arxiv:2506.03930

arxiv:2505.15929

arxiv:2502.14739

arxiv:2410.10563

arxiv:2409.02813

arxiv:2406.15252

arxiv:2406.05862

arxiv:2406.04485

arxiv:2406.01574

arxiv:2401.01286

arxiv:2311.16502