arxiv:2510.24411
Mukai Li
kiaia
AI & ML interests
NLP
Recent Activity
upvoted a paper 1 day ago
PACE: A Proxy for Agentic Capability Evaluation liked a model 25 days ago
zai-org/GLM-5.2 upvoted a paper about 2 months ago
WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation