5 citations · 5 across the 8 of their papers we have counts for
6 papers · 1 filter
DynamicDx: Evaluating Evidence Acquisition in Video-Based Diagnosis
Jiahui Li, Yutong Guo, Nan Yang +3
Diagnosing a patient from video requires more than recognizing the sign: a vision-language model must turn what it sees into hypotheses, questions and tests. DynamicDx evaluates ea…
EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported ED-Encounter Diagnoses
Jiahui Li, Ruili Fang, Zishuai Liu +5
Clinical diagnosis at hospital admission must be made rapidly from limited, incomplete evidence. Existing diagnosis-prediction benchmarks are poorly suited to this setting: they re…
Peak-Detector: Explainable Peak Detection via Instruction-Tuned Large Language Models in Physiological Sign
Jiahui Li, Yida Zhang, Zixuan Zeng +10
Accurate peak detection across diverse cardiac physiological signals, including the Electrocardiogram (ECG), Photoplethysmogram (PPG), Ballistocardiogram (BCG), and Bodyseismograph…
DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisition
Jiahui Li, Ruili Fang, Zishuai Liu +3
Beat-level Electrocardiography (ECG) arrhythmia detection aims to assign an arrhythmia class to each beat in a recording, yet many existing systems treat beats as isolated local in…
Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group Normalization
Jinghan Li, Junfeng Fang, Jinda Lu +5
Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO) have significantly advanced the reasoning capabilities of large language models.…
LARV: Data-Free Layer-wise Adaptive Rescaling Veneer for Model Merging
Xinyu Wang, Ke Deng, Fei Dou +2
Model merging aims to combine multiple fine-tuned models into a single multi-task model without access to training data. Existing task-vector merging methods such as TIES, TSV-M, a…