Zeng
Michael0420
ยท
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents upvoted a paper 30 days ago
GOAT-Bench: Safety Insights to Large Multimodal Models through
Meme-Based Social Abuse upvoted a paper about 2 months ago
Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism