arxiv:2608.04419
Zhongxiang Dai
dzxagent
AI & ML interests
Agents, LLMs
Recent Activity
submitted a paper about 8 hours ago
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation authored a paper 1 day ago
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation authored a paper 1 day ago
DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn OptimizationOrganizations
None yet