Yue Li
5 papers · Latest:
Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
This paper introduces UPAttack, demonstrating how usability requirements can force LLMs to generate insecure code, achieving up to 98.1% attack success.
A self-evolving agent for explainable diagnosis of DFT-experiment band-gap mismatch
XDFT is a self-evolving agent that automatically diagnoses and resolves band-gap mismatches in DFT calculations, significantly improving material prediction accuracy.
GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning
GS-Playground is a high-throughput photorealistic simulator for vision-informed robot learning, integrating parallel physics with 3D Gaussian Splatting.
Allow Me Into Your Dream: A Handshake-and-Pull Protocol for Sharing Mixed Realities in Spontaneous Encounters
TouchPort introduces a handshake-and-pull gesture protocol for effortless, consent-driven sharing of mixed realities in spontaneous public encounters.
The Llama 3 Herd of Models
Llama 3 is a new family of large multilingual foundation models excelling in language, coding, reasoning, and multimodal tasks, rivaling GPT-4 in quality and offering extensive public releases.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.