False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents
Paper • 2609.39102 • Published • 150
Chengwei Cheung
ChengweiCcc
·
AI & ML interests
Chess player, Python enthusiast
Recent Activity
updated a model 23 days ago
ChengweiCcc/blip-retrieval published a model 23 days ago
ChengweiCcc/blip-retrieval updated a model 23 days ago
ChengweiCcc/zero-shot-transfer-betaOrganizations
None yet
upvoted 4
papers about 1 month ago
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
Paper • 2610.07767 • Published • 43
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Paper • 2609.38288 • Published • 89
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 168
upvoted a paper 2 months ago