publications

2026

1. NeurIPS 2026

   Precision-Aware Hopfield Retrieval: Unifying Population Codes and Memory Retrieval with Information Optimization

   Yi-Chun Hung, Dennis Wu, Hong-Yu Chen, Han Liu, and Emma Alexander
2. ICML 2026

   

   In-Context Universal Approximation, Compositional Generalization, and Algorithm Emulation

   Jerry Yao-Chieh Hu^*, Hong-Yu Chen^*, Po-Chiao Lin^*, Maojiang Su, and Han Liu
3. ICML 2026

   Universal Approximation with Softmax Attention

   Jerry Yao-Chieh Hu^*, Hude Liu^*, Hong-Yu Chen^*, Weimin Wu, and Han Liu

   arXiv
4. ICML 2026

   Chain-of-Thought Gradient Descent

   Hong-Yu Chen^*, Venkat Sripad Ganti^*, Jerry Yao-Chieh Hu, Hude Liu, and Han Liu
5. ICML 2026

   

   StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars

   Weijian Li^*, Hong-Yu Chen^*, Nabeel Rehemtulla^*, Ved G. Shah, Dennis Wu, Dongho Kim, Qinjie Lin, Adam A. Miller, and Han Liu

   AI4Physics Workshop Outstanding Paper arXiv Code Website

   Outstanding Paper Award and Oral Presentation at the AI4Physics Workshop, ICML 2026

2025

1. arXiv

   Transformers versus the EM Algorithm in Multi-class Clustering

   Yihan He, Hong-Yu Chen, Yuan Cao, Jianqing Fan, and Han Liu

   arXiv
2. arXiv

   Learning spectral methods by transformers

   Yihan He, Yuan Cao, Hong-Yu Chen, Dennis Wu, Jianqing Fan, and Han Liu

   arXiv
3. arXiv

   Transformers Simulate MLE for Sequence Generation in Bayesian Networks

   Yuan Cao, Yihan He, Dennis Wu, Hong-Yu Chen, Jianqing Fan, and Han Liu

   arXiv

2024

1. ICML 2024

   

   Outlier-Efficient Hopfield Layers for Large Transformer-Based Models

   Jerry Yao-Chieh Hu, Pei-Hsuan Chang, Haozheng Luo, Hong-Yu Chen, Weijian Li, Wei-Po Wang, and Han Liu

   arXiv PDF Code Poster Slides