10 papers
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning
Xinyan Guan, Jiali Zeng, Chunlei Xin +5
Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating risks where plausible-sounding but incorrect derivatio…
Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation
Yanjiang Liu, Jie Lou, Xinyan Guan +7
On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher. However, we identif…
When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
Yingzhi Mao, Chunkang Zhang, Junxiang Wang +6
Large Reasoning Models (LRMs) achieve strong performance on complex multi-step reasoning, yet they still exhibit severe safety failures such as harmful content generation. Existing…
ECGTwin: Personalized ECG Generation Using Controllable Diffusion Model
Yongfan Lai, Bo Liu, Xinyan Guan +3
Personalized electrocardiogram (ECG) generation is to simulate a patient's ECG digital twins tailored to specific conditions. It has the potential to transform traditional healthca…
Dissecting Long-Chain-of-Thought Reasoning Models: An Empirical Study
Yongyu Mu, Jiali Zeng, Bei Li +5
Despite recent progress in training long-chain-of-thought reasoning models via scaling reinforcement learning (RL), its underlying training dynamics remain poorly understood, and s…
Reconstructing 12-Lead ECG from 3-Lead ECG using Variational Autoencoder to Improve Cardiac Disease Detection of Wearable ECG Devices
Xinyan Guan, Yongfan Lai, Jiarui Jin +6
Twelve-lead electrocardiograms (ECGs) are the clinical gold standard for cardiac diagnosis, providing comprehensive spatial coverage of the heart necessary to detect conditions suc…