Yu Huang
7 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Acoustic Interference Attack (AIA), a novel jailbreak method that bypasses Large Audio Language Model (LALM) safety alignments by manipulating the underlying acoustic latent semantics rather than injecting malicious content.
This study analyzes over 20,000 real-world coding sessions to show that AI coding agents frequently fail users through subtle misalignment, requiring constant manual correction even when major system damage is avoided.
This study analyzes over 20,000 real-world coding sessions to show that AI coding agents frequently fail users through subtle misalignment, requiring constant manual correction even when major system damage is avoided.
This paper demonstrates that transformer-based policies can provably learn complex tree search mechanisms, such as depth-first search, purely through reinforcement learning in a stochastic environment.
This paper demonstrates that transformer-based policies can provably learn complex tree search mechanisms, such as depth-first search, purely through reinforcement learning in a stochastic environment.
VERITAS is a zero-shot framework that improves the performance of LLM-based formal provers by routing verifier signals back into proof search.
Specula is an autonomous system that generates high-quality formal specifications for large, complex code using LLMs, improving understanding and finding bugs.
Papers
Specula: Scaling formal specifications for autonomous model checking of system code
Qian Cheng, Saad Mohammad Rafid Pial, Ruize Tang, Yiming Su +5 more
Specula is an autonomous system that generates high-quality formal specifications for large, complex code using LLMs, improving understanding and finding bugs.