Qingfu Zhu

ProxyAttn: Guided Sparse Attention via Representative Heads

How Many Code and Test Cases Are Enough? Evaluating Test Cases Generation from a Binary-Matrix Perspective

Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond

Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding

Learning-to-Context Slope: Evaluating In-Context Learning Effectiveness Beyond Performance Illusions

CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing

Beyond Score: A Multi-Agent System to Discover Capability and Behavioral Weaknesses in LLMs

Scaling Law for Code: A More Data-Hungry Regime

In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks