Xuezhi Cao
3 papers · Latest:
Software Engineering
SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle
SWE-Cycle introduces a new benchmark and SWE-Judge evaluation system to accurately assess autonomous code agents across the complete software issue resolution cycle.
2605.13139
Natural Language ProcessingGeneral365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging Tasks
General365 is a new benchmark assessing LLMs' general reasoning, revealing their domain-dependent abilities and significant room for improvement beyond specialized tasks.
2604.11778
Computer VisionLARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment
LARY introduces a benchmark and dataset for evaluating latent action representations, showing general visual models excel and latent spaces align better with physical actions.
2604.11689
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.