Kaixiang Zhao

kzhao5's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 19 days ago

Recovering Reliable Supervision via Critique-Guided On-Policy Distillation

Paper • 2610.20572 • Published 20 days ago • 32

upvoted 3 papers about 1 month ago

An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning

Paper • 2609.35505 • Published Sep 28 • 29

Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It

Paper • 2609.32444 • Published Sep 26 • 29

The Value of Graph-based Encoding in NBA Salary Prediction

Paper • 2603.05671 • Published Mar 5 • 3

upvoted 3 papers about 2 months ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published Sep 17 • 60

Self-Correction Can Amplify Hallucinations: Fact-Level Repair with Graph-Based Evidence Routing in Multimodal Generation

Paper • 2606.00232 • Published Aug 30 • 5

A Survey on Model Extraction Attacks and Defenses for Large Language Models

Paper • 2506.22521 • Published Jun 26, 2025 • 5