Xiangnan Wu

XiangnanW

·

AI & ML interests

LLM Reasoning VLM

Recent Activity

upvoted a paper 3 days ago

Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds

upvoted a paper 4 days ago

HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs

upvoted a paper 11 days ago

Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability

View all activity

Organizations

XiangnanW 's models

None public yet