Hongyu Zhang

Large Language Models (LLMs) for code generation can replicate insecure patterns from their training data. To mitigate this, a common strategy for security hardening is to fine-tune models using supervision derived from the final transformer layer. However, this design may suffer from a final-lay...

Code Large Language Models face critical Time-To-First-Token (TTFT) latency challenges when handling long code completion due to the quadratic complexity ( O(n^2) ) of attention mechanisms. While existing sparse attention methods attempt to address this issue, they suffer from three key limitatio...

Large Language Models (LLMs) encode substantial knowledge in their parameters, which can be located, traced, and analyzed. Despite recent progress in neural interpretability, it is still unclear how to transfer such knowledge in a fine-grained manner, namely parametric knowledge transfer (PKT). A...

The Development Knowledge Question Answering (Dev Knowledge QA) task aims to provide accurate natural language answers to knowledge-seeking questions during software development. To investigate the importance of Dev Knowledge QA in AI-assisted software development and the extent to which it has b...

Frequency-domain sequential recommendation models enhance sequence representation capacity through spectral transformations. However, existing methods typically adopt coarse-grained spectrum reweighting strategies that strengthen high-frequency components while amplifying random noise within freq...