6 papers
Standalone LLM and a Pre-specified Agentic Pipeline for Explaining ICU Mortality Predictions: a Feasibility Study on the eICU Demo Dataset
Di Zhu, Chen Xie, Haoyun Zhang +5
Machine-learning models can predict ICU mortality accurately, but feature-attribution methods alone rarely provide the clinical narrative needed for bedside use. Large language mod…
Tool-Augmented Hybrid Ensemble Reasoning with Distillation for Bilingual Mathematical Problem Solving
Peiqing Lu, Yuan Zhang, Haoyun Zhang +3
Bilingual mathematical problem solving needs a clear link between language reasoning and symbolic calculation. Large language models often handle language well but are weak in accu…
Evolutionary Physics-Informed Temporal Fusion for Lane-Change Intention Prediction
Jiazhao Shi, Qiyang Xie, Ziyu Wang +7
Early lane-change intention prediction is essential for autonomous driving and ADAS, but it remains challenging because lane-changing behavior depends on evolving traffic risk, sur…
RaX-Crash: A Resource Efficient and Explainable Small Model Pipeline with an Application to City Scale Injury Severity Prediction
Di Zhu, Chen Xie, Ziwei Wang +1
New York City reports over one hundred thousand motor vehicle collisions each year, creating substantial injury and public health burden. We present RaX-Crash, a resource efficient…
ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients"
Zhongyi Zhou, Kohei Uehara, Haoyu Zhang +5
Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like depth-first search (DFS). This leads to inevitable anno…
Med-REFL: Medical Reasoning Enhancement via Self-Corrected Fine-grained Reflection
Zongxian Yang, Jiayu Qian, Zegao Peng +4
Large reasoning models excel in domains like mathematics where intermediate reasoning is straightforward to verify, but struggle to self-correct in medicine fields where evaluating…