5 papers
PACT: Learning Diverse Diagnostic Strategies via Privileged Synthesis and Branch Consensus
Gen Li, Yuanze Hu, Zhichao Yang +10
Clinical diagnosis requires flexible use of multiple reasoning paradigms under incomplete patient information. Existing LLM-based medical agents show strong medical reasoning abili…
Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers
Nanxiang Jiang, Zhaoxin Fan, Baisen Wang +8
Concept erasure serves as a vital safety mechanism for removing unwanted concepts from text-to-image (T2I) models. While extensively studied in U-Net and dual-stream architectures…
IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters
Hongwei Zheng, Weiqi Wu, Zhengjia Wang +6
Conversational agents, such as ChatGPT and Doubao, have become essential daily assistants for billions of users. To further enhance engagement, these systems are evolving from pass…
HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
Boshui Chen, Zhaoxin Fan, Ke Wang +5
Large Language Models (LLMs) are powerful and widely adopted, but their practical impact is limited by the well-known hallucination phenomenon. While recent hallucination detection…
Lyapunov Probes for Hallucination Detection in Large Foundation Models
Bozhi Luan, Gen Li, Yalan Qin +6
We address hallucination detection in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) by framing the problem through the lens of dynamical systems stabili…