arxiv:2607.14614
Hou Pong (Ken) Chan
kenchan0226
AI & ML interests
None yet
Recent Activity
authored a paper about 23 hours ago
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization upvoted a paper 22 days ago
DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment