Liang Wan

The paper analyzes protracted vulnerabilities (PCVEs) in open-source projects and proposes DeeptraVul, an enhanced detection approach that significantly improves vulnerability coverage by integrating multiple development artifacts and an LLM.

LoRA-Key introduces a user-centric watermarking framework that attaches a recoverable ownership key to LoRA modules via a standalone Watermark LoRA, providing lightweight, plug-and-play copyright protection without requiring per-LoRA retraining.

GaMi is a multimodal material identification system that uses mmWave and acoustic sensing with a cross-modal subtractive disentanglement framework to achieve high accuracy (95.2%) for material identification regardless of geometric variations.

The paper proposes EAPO, a framework that enables agentic models to learn when to forgo using external tools, thereby mitigating tool abuse while maintaining high reasoning accuracy.

The paper proposes a hierarchical framework, PHF (Practice-Habitus-Field), inspired by Bourdieu's Theory of Practice, to improve LLM personalization by modeling user behaviors at three distinct levels.

This paper proposes GLAN, a sequence modeling framework for Personalized Landing Page Modeling on online platforms, addressing the limitations of previous reinforcement learning approaches.

This paper proposes CoLT, a framework that enables multi-modal models to reason through a chain of latent thought representations instead of text tokens, improving performance and reducing inference time.

This paper presents a comprehensive measurement study on the performance and energy consumption of large language models on mobile devices, using five frameworks and three hardware backends, and introduces PowerBench, a tool for fine-grained profiling.