-
Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal
Paper • 2508.05988 • Published • 20 -
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
Paper • 2508.07407 • Published • 98 -
Compressing Chain-of-Thought in LLMs via Step Entropy
Paper • 2508.03346 • Published • 8 -
Reinforcement Learning in Vision: A Survey
Paper • 2508.08189 • Published • 30
LiuQuan
liuquan
AI & ML interests
None yet
Organizations
None yet
good paper
-
Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal
Paper • 2508.05988 • Published • 20 -
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
Paper • 2508.07407 • Published • 98 -
Compressing Chain-of-Thought in LLMs via Step Entropy
Paper • 2508.03346 • Published • 8 -
Reinforcement Learning in Vision: A Survey
Paper • 2508.08189 • Published • 30