SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation
Paper • 2608.04419 • Published • 28
Shuang Qiu
shq-ml
AI & ML interests
None yet
Recent Activity
upvoted a paper 17 days ago
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation upvoted a paper about 1 year ago
Rewards-in-Context: Multi-objective Alignment of Foundation Models with
Dynamic Preference AdjustmentOrganizations
None yet
upvoted a paper 17 days ago
upvoted a paper 12 months ago
upvoted a paper about 1 year ago
authored 4
papers about 1 year ago
On the Value of Myopic Behavior in Policy Reuse
Paper • 2305.17623 • Published
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
Paper • 2402.10207 • Published • 3
Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
Paper • 2402.18571 • Published
Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
Paper • 2505.23564 • Published • 3