QIN ZHIBIN
tuantuan0321
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Mix-Quant: Quantized Prefilling, Precise Decoding for Agentic LLMs upvoted a paper 4 days ago
ReactiveGWM: Steering NPC in Reactive Game World Models upvoted a paper 9 days ago
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment