collaborators

9 papers

cs.MM2026

ELF: A Family of Encoder-Free ECG-Language Models

William Han, Tony Chen, Chaojing Duan +6

The paper introduces ELF, a family of encoder‑free ECG‑language models that interpret electrocardiograms without relying on separate pretrained ECG encoders, achieving competitive…

cs.AI2026

Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization

Yihang Yao, Zhepeng Cen, Haohong Lin +6

Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following a…

cs.LG2025

Tailored Primitive Initialization is the Secret Key to Reinforcement Learning

Yihang Yao, Guangtao Zeng, Raina Wu +4

Reinforcement learning (RL) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). While RL has demonstrated substantial perfo…

cs.LG2025

Behavior Injection: Preparing Language Models for Reinforcement Learning

Zhepeng Cen, Yihang Yao, William Han +2

Reinforcement learning (RL) has emerged as a powerful post-training technique to incentivize the reasoning ability of large language models (LLMs). However, LLMs can respond very i…

cs.CL2025

Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety

Yuyou Zhang, Miao Li, William Han +3

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or represen…

cs.AI2025

Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework

William Han, Chaojing Duan, Zhepeng Cen +7

Recent advances have increasingly applied large language models (LLMs) to electrocardiogram (ECG) interpretation, giving rise to Electrocardiogram-Language Models (ELMs). Condition…