Zhongxiang Dai

dzxagent

https://daizhongxiang.github.io

AI & ML interests

Agents, LLMs

Recent Activity

submitted a paper about 4 hours ago

SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation

authored a paper about 21 hours ago

SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation

authored a paper about 21 hours ago

DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization

View all activity

Organizations

None yet

Papers 16

arxiv:2608.04419

arxiv:2605.31455

arxiv:2603.02630

arxiv:2603.01375

models 0

None public yet

datasets 0

None public yet