publications

(*, †, and ‡ denote equal contribution)

2026

  1. EMNLP
    mdmprime-v2.png
    MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Scaling of Diffusion Language Models
    Chen-Hao Chao, Wei-Fang Sun, Junwei Quan, and 2 more authors
    Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026
    Paper GitHub
  2. EMNLP
    pivot.png
    Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models
    Seo Hyun Kim, Sunwoo Hong, Younwoo Choi, and 3 more authors
    Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026
    Paper
  3. ICML Workshop
    logical.png
    Logical Equivariance in Diffusion Language Models
    Sunwoo Hong, Seo Hyun Kim, Chen-Hao Chao, and 3 more authors
    ICML Workshop on Foundations of Deep Generative Models: Understanding Memorization, Generalization, and Reasoning, 2026
    Paper

2025

  1. NeurIPS
    mdmprime.png
    Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking
    Chen-Hao Chao, Wei-Fang Sun, Hanwen Liang, and 2 more authors
    In Proceedings of the Conference on Neural Information Processing Systems (NeurIPS) , 2025
    Paper GitHub Website
  2. ICML
    smoe.png
    Retraining-Free Merging of Sparse Mixture-of-Experts via Hierarchical Clustering
    I-Chun Chen, Hsu-Shen Liu, Wei-Fang Sun, and 3 more authors
    In Proceedings of the International Conference on Machine Learning (ICML) , 2025
    Paper GitHub

2024

  1. NeurIPS
    meow.png
    Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
    Chen-Hao Chao*, Chien Feng*, Wei-Fang Sun, and 3 more authors
    In Proceedings of the Conference on Neural Information Processing Systems (NeurIPS) , 2024
    Paper GitHub Website

2023

  1. NeurIPS
    ebflow.png
    Training Energy-Based Normalizing Flow with Score-Matching Objectives
    Chen-Hao Chao, Wei-Fang Sun, Yen-Chang Hsu, and 2 more authors
    In Proceedings of the Conference on Neural Information Processing Systems (NeurIPS) , 2023
    Paper GitHub Website
  2. ICML
    qcsbm.png
    On Investigating the Conservative Property of Score-Based Generative Models
    Chen-Hao Chao, Wei-Fang Sun, Bo-Wun Cheng, and 1 more author
    In Proceedings of the International Conference on Machine Learning (ICML) , 2023
    Paper GitHub Website
  3. TPAMI
    rainbow.png
    Rainbow UDA: Combining Domain Adaptive Models for Semantic Segmentation Tasks
    Chen-Hao Chao, Bo-Wun Cheng, Tzu-Wen Wang*, and 2 more authors
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
    Paper
  4. ASP-DAC
    colab.png
    COLAB: Collaborative and Efficient Processing of Replicated Cache Requests in GPU
    Bo-Wun Cheng, En-Ming Huang, Chen-Hao Chao, and 3 more authors
    In Proceedings of the Asia and South Pacific Design Automation Conference (ASP-DAC) , 2023
    Paper

2022

  1. ICLR
    dlsm.png
    Denoising Likelihood Score Matching for Conditional Score-based Data Generation
    Chen-Hao Chao, Wei-Fang Sun, Bo-Wun Cheng, and 6 more authors
    In Proceedings of the International Conference on Learning Representations (ICLR) , 2022
    Paper GitHub Website
  2. BMVC
    elda.png
    ELDA: Using Edges to Have an Edge on Semantic Segmentation Based UDA
    Ting-Hsuan Liao*, Huang-Ru Liao*, Shan-Ya Yang†, and 8 more authors
    In Proceedings of the British Machine Vision Conference (BMVC) , 2022
    Paper GitHub
  3. SASIMI
    rata.png
    Remote Access Tag Array for Efficient GPU Intra-Cluster Data Sharing
    Bo-Wun Cheng, En-Ming Huang, Chen-Hao Chao, and 3 more authors
    Workshop on Synthesis And System Integration of Mixed Information Technologies (SASIMI), 2022
    Paper

2021

  1. CVPR Workshop
    re.png
    Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaption
    Chen-Hao Chao, Bo-Wun Cheng, and Chun-Yi Lee
    CVPR Workshop on Learning From Limited or Imperfect Data, 2021
    Paper GitHub Website