Cite
Notes
Only stored in your browser.
Attribution
Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction
arXiv 2026
Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data
arXiv 2025
from 2 papers
Hongke Zhao
Likang Wu
Haoran Sun
Jianpin Fan
Ming He
Shuai Di
Wen Huang
Xiong Jun Wu
Yongjian Guo