arxiv:2510.02190
Tom Lu
eigentom
AI & ML interests
MLLM, Generative AI, Agentic RL
Recent Activity
upvoted a paper 32 minutes ago
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding upvoted a paper about 4 hours ago
Watch Before You Answer: Learning from Visually Grounded Post-Training upvoted a paper about 4 hours ago
ClawBench: Can AI Agents Complete Everyday Online Tasks?