Jia Li
7 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
VulKey introduces a novel LLM-based framework that uses a hierarchical abstraction of expert security knowledge to guide automatic vulnerability repair, achieving state-of-the-art performance on real-world benchmarks.
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.
The paper proposes a disentangled representation framework to significantly improve few-shot layout-to-image generation by separating semantic identity from local visual details, thereby mitigating representation fragmentation.
The paper proposes a disentangled representation framework to significantly improve few-shot layout-to-image generation by separating semantic identity from local visual details, thereby mitigating representation fragmentation.
This paper reveals a vulnerability in Grammar-Constrained Decoding (GCD) that can be exploited to generate malicious code and proposes a safety alignment approach called CodeShield to address this issue.
The paper presents Numina Fuse, an agent-native application for formalizing mathematics in Lean 4, and its development and use in formalizing the three-dimensional Kakeya conjecture.
This paper develops a framework to study bargaining between autonomous and human-driven vehicles using large language models.