guanzhong's picture

guanzhong

guanzhong2

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 23 hours ago

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

submitted a paper about 23 hours ago

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

updated a dataset 8 days ago

guanzhong2/TU_Pipeline

View all activity

Organizations

None yet

upvoted a paper about 23 hours ago

Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction

Paper • 2605.12070 • Published 2 days ago • 14

upvoted a paper 8 months ago

Recall-Extend Dynamics: Enhancing Small Language Models through Controlled Exploration and Refined Offline Integration

Paper • 2508.16677 • Published Aug 21, 2025 • 2

upvoted a paper about 1 year ago

Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data

Paper • 2505.02130 • Published May 4, 2025 • 3