Yen-Chang Hsu

63 papers A* 12A 2B 2Journal 33Unranked 13
YearRankTypeTitle / Venue / Authors
2026 J jnl
ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning.
Trans. Mach. Learn. Res.
Shangqian Gao, Ting Hua, Reza Shirkavand, Chi-Heng Lin, Zheng Tang, Zhengao Li, Longge Yuan, Fangyi Li, Zeyu Zhang, Alireza Ganjdanesh, Qian Lou, Jie Xu, Yen-Chang Hsu
2025 — conf
FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing.
NAACL (Long Papers)
James Seale Smith, Chi-Heng Lin, Shikhar Tuli, Haris Jeelani, Shangqian Gao, Yilin Shen, Hongxia Jin, Yen-Chang Hsu
2025 J jnl
FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing.
CoRR
James Seale Smith, Chi-Heng Lin, Shikhar Tuli, Haris Jeelani, Shangqian Gao, Yilin Shen, Hongxia Jin, Yen-Chang Hsu
2025 A* conf
MoDeGPT: Modular Decomposition for Large Language Model Compression.
ICLR
Chi-Heng Lin, Shangqian Gao, James Seale Smith, Abhishek Patel, Shikhar Tuli, Yilin Shen, Hongxia Jin, Yen-Chang Hsu
2025 — conf
MossNet: Mixture of State-Space Experts is a Multi-Head Attention.
IJCNLP-AACL (long papers)
Shikhar Tuli, James Seale Smith, Haris Jeelani, Chi-Heng Lin, Abhishek Patel, Vasili Ramanishka, Yen-Chang Hsu, Hongxia Jin
2025 J jnl
MossNet: Mixture of State-Space Experts is a Multi-Head Attention.
CoRR
Shikhar Tuli, James Seale Smith, Haris Jeelani, Chi-Heng Lin, Abhishek Patel, Vasili Ramanishka, Yen-Chang Hsu, Hongxia Jin
2025 A* conf
Retraining-free Merging of Sparse MoE via Hierarchical Clustering.
ICML
I-Chun Chen, Hsu-Shen Liu, Wei-Fang Sun, Chen-Hao Chao, Yen-Chang Hsu, Chun-Yi Lee
2025 J jnl
ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning.
CoRR
Shangqian Gao, Ting Hua, Reza Shirkavand, Chi-Heng Lin, Zhen Tang, Zhengao Li, Longge Yuan, Fangyi Li, Zeyu Zhang, Alireza Ganjdanesh, Qian Lou, Xu Jie, Yen-Chang Hsu
2024 — conf
Adaptive Rank Selections for Low-Rank Approximation of Language Models.
NAACL-HLT
Shangqian Gao, Ting Hua, Yen-Chang Hsu, Yilin Shen, Hongxia Jin
2024 — conf
Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters.
CVPR Workshops
James Seale Smith, Yen-Chang Hsu, Zsolt Kira, Yilin Shen, Hongxia Jin
2024 J jnl
Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA.
Trans. Mach. Learn. Res.
James Seale Smith, Yen-Chang Hsu, Lingyu Zhang, Ting Hua, Zsolt Kira, Yilin Shen, Hongxia Jin
2024 A* conf
DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models.
NeurIPS
Shangqian Gao, Chi-Heng Lin, Ting Hua, Zheng Tang, Yilin Shen, Hongxia Jin, Yen-Chang Hsu
2024 J jnl
DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models.
CoRR
Shangqian Gao, Chi-Heng Lin, Ting Hua, Tang Zheng, Yilin Shen, Hongxia Jin, Yen-Chang Hsu
2024 — conf
DynaMo: Accelerating Language Model Inference with Dynamic Multi-Token Sampling.
NAACL-HLT
Shikhar Tuli, Chi-Heng Lin, Yen-Chang Hsu, Niraj K. Jha, Yilin Shen, Hongxia Jin
2024 J jnl
DynaMo: Accelerating Language Model Inference with Dynamic Multi-Token Sampling.
CoRR
Shikhar Tuli, Chi-Heng Lin, Yen-Chang Hsu, Niraj K. Jha, Yilin Shen, Hongxia Jin
2024 J jnl
MoDeGPT: Modular Decomposition for Large Language Model Compression.
CoRR
Chi-Heng Lin, Shangqian Gao, James Seale Smith, Abhishek Patel, Shikhar Tuli, Yilin Shen, Hongxia Jin, Yen-Chang Hsu
2024 J jnl
Retraining-Free Merging of Sparse Mixture-of-Experts via Hierarchical Clustering.
CoRR
I-Chun Chen, Hsu-Shen Liu, Wei-Fang Sun, Chen-Hao Chao, Yen-Chang Hsu, Chun-Yi Lee
2024 — conf
SLiM: Speculative Decoding with Hypothesis Reduction.
NAACL-HLT (Findings)
Chi-Heng Lin, Shikhar Tuli, James Seale Smith, Yen-Chang Hsu, Yilin Shen, Hongxia Jin
2024 A conf
Token Fusion: Bridging the Gap between Token Pruning and Token Merging.
WACV
Minchul Kim, Shangqian Gao, Yen-Chang Hsu, Yilin Shen, Hongxia Jin
2023 — conf
A Closer Look at Rehearsal-Free Continual Learning.
CVPR Workshops
James Seale Smith, Junjiao Tian, Shaunak Halbe, Yen-Chang Hsu, Zsolt Kira
2023 J jnl
Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters.
CoRR
James Seale Smith, Yen-Chang Hsu, Zsolt Kira, Yilin Shen, Hongxia Jin
2023 J jnl
Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA.
CoRR
James Seale Smith, Yen-Chang Hsu, Lingyu Zhang, Ting Hua, Zsolt Kira, Yilin Shen, Hongxia Jin
2023 — conf
Dynamic Low-rank Estimation for Transformer-based Language Models.
EMNLP (Findings)
Ting Hua, Xiao Li, Shangqian Gao, Yen-Chang Hsu, Yilin Shen, Hongxia Jin
2023 J jnl
Token Fusion: Bridging the Gap between Token Pruning and Token Merging.
CoRR
Minchul Kim, Shangqian Gao, Yen-Chang Hsu, Yilin Shen, Hongxia Jin
2023 A* conf
Training Energy-Based Normalizing Flow with Score-Matching Objectives.
NeurIPS
Chen-Hao Chao, Wei-Fang Sun, Yen-Chang Hsu, Zsolt Kira, Chun-Yi Lee
2023 J jnl
Training Energy-Based Normalizing Flow with Score-Matching Objectives.
CoRR
Chen-Hao Chao, Wei-Fang Sun, Yen-Chang Hsu, Zsolt Kira, Chun-Yi Lee
2022 J jnl
A Closer Look at Knowledge Distillation with Features, Logits, and Gradients.
CoRR
Yen-Chang Hsu, James Seale Smith, Yilin Shen, Zsolt Kira, Hongxia Jin
2022 J jnl
A Closer Look at Rehearsal-Free Continual Learning.
CoRR
James Seale Smith, Junjiao Tian, Yen-Chang Hsu, Zsolt Kira
2022 A* conf
DictFormer: Tiny Transformer with Shared Dictionary.
ICLR
Qian Lou, Ting Hua, Yen-Chang Hsu, Yilin Shen, Hongxia Jin
2022 J jnl
Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding.
CoRR
Ting Hua, Yilin Shen, Changsheng Zhao, Yen-Chang Hsu, Hongxia Jin
2022 A* conf
Language model compression with weighted low-rank factorization.
ICLR
Yen-Chang Hsu, Ting Hua, Sungen Chang, Qian Lou, Yilin Shen, Hongxia Jin
2022 J jnl
Language model compression with weighted low-rank factorization.
CoRR
Yen-Chang Hsu, Ting Hua, Sungen Chang, Qian Lou, Yilin Shen, Hongxia Jin
2022 A* conf
Lite-MDETR: A Lightweight Multi-Modal Detector.
CVPR
Qian Lou, Yen-Chang Hsu, Burak Uzkent, Ting Hua, Yilin Shen, Hongxia Jin
2022 J jnl
Numerical Optimizations for Weighted Low-rank Estimation on Language Model.
CoRR
Ting Hua, Yen-Chang Hsu, Felicity Wang, Qian Lou, Yilin Shen, Hongxia Jin
2022 A* conf
Numerical Optimizations for Weighted Low-rank Estimation on Language Models.
EMNLP
Ting Hua, Yen-Chang Hsu, Felicity Wang, Qian Lou, Yilin Shen, Hongxia Jin
2021 A* conf
A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition.
NeurIPS
Junjiao Tian, Dylan Yung, Yen-Chang Hsu, Zsolt Kira
2021 J jnl
A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition.
CoRR
Junjiao Tian, Dylan Yung, Yen-Chang Hsu, Zsolt Kira
2021 A* conf
Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning.
ICCV
James Seale Smith, Yen-Chang Hsu, Jonathan C. Balloch, Yilin Shen, Hongxia Jin, Zsolt Kira
2021 J jnl
Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning.
CoRR
James Seale Smith, Yen-Chang Hsu, Jonathan C. Balloch, Yilin Shen, Hongxia Jin, Zsolt Kira
2021 J jnl
Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU.
CoRR
Yilin Shen, Yen-Chang Hsu, Avik Ray, Hongxia Jin
2021 — conf
Enhancing the generalization for Intent Classification and Out-of-Domain Detection in SLU.
ACL/IJCNLP (1)
Yilin Shen, Yen-Chang Hsu, Avik Ray, Hongxia Jin
2021 J jnl
Exploring Covariate and Concept Shift for Detection and Calibration of Out-of-Distribution Data.
CoRR
Junjiao Tian, Yen-Chang Hsu, Yilin Shen, Hongxia Jin, Zsolt Kira
2021 — conf
Hyperparameter-free Continuous Learning for Domain Classification in Natural Language Understanding.
NAACL-HLT
Ting Hua, Yilin Shen, Changsheng Zhao, Yen-Chang Hsu, Hongxia Jin
2021 B conf
Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer.
IJCNN
James Seale Smith, Jonathan C. Balloch, Yen-Chang Hsu, Zsolt Kira
2021 J jnl
Memory-Efficient Semi-Supervised Continual Learning: The World is its Own Replay Buffer.
CoRR
James Seale Smith, Jonathan C. Balloch, Yen-Chang Hsu, Zsolt Kira
2020 A* conf
Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data.
CVPR
Yen-Chang Hsu, Yilin Shen, Hongxia Jin, Zsolt Kira
2020 J jnl
Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data.
CoRR
Yen-Chang Hsu, Yilin Shen, Hongxia Jin, Zsolt Kira
2020 — —
Learning from pairwise similarity for visual categorization.
Yen-Chang Hsu
2020 A* conf
Posterior Re-calibration for Imbalanced Datasets.
NeurIPS
Junjiao Tian, Yen-Cheng Liu, Nathaniel Glaser, Yen-Chang Hsu, Zsolt Kira
2020 J jnl
Posterior Re-calibration for Imbalanced Datasets.
CoRR
Junjiao Tian, Yen-Cheng Liu, Nathan Glaser, Yen-Chang Hsu, Zsolt Kira
2019 J jnl
Multi-class Classification without Multi-class Labels.
CoRR
Yen-Chang Hsu, Zhaoyang Lv, Joel Schlosser, Phillip Odom, Zsolt Kira
2019 — conf
Multi-class classification without multi-class labels.
ICLR (Poster)
Yen-Chang Hsu, Zhaoyang Lv, Joel Schlosser, Phillip Odom, Zsolt Kira
2018 J jnl
A probabilistic constrained clustering for transfer learning and image category discovery.
CoRR
Yen-Chang Hsu, Zhaoyang Lv, Joel Schlosser, Phillip Odom, Zsolt Kira
2018 B conf
Learning to Cluster for Proposal-Free Instance Segmentation.
IJCNN
Yen-Chang Hsu, Zheng Xu, Zsolt Kira, Jiawei Huang
2018 J jnl
Learning to Cluster for Proposal-Free Instance Segmentation.
CoRR
Yen-Chang Hsu, Zheng Xu, Zsolt Kira, Jiawei Huang
2018 — conf
Learning to cluster in order to transfer across domains and tasks.
ICLR (Poster)
Yen-Chang Hsu, Zhaoyang Lv, Zsolt Kira
2018 J jnl
Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines.
CoRR
Yen-Chang Hsu, Yen-Cheng Liu, Zsolt Kira
2018 — conf
Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks.
ICLR (Workshop)
Zheng Xu, Yen-Chang Hsu, Jiawei Huang
2018 A conf
Training Student Networks for Acceleration with Conditional Adversarial Networks.
BMVC
Zheng Xu, Yen-Chang Hsu, Jiawei Huang
2017 J jnl
Learning Loss for Knowledge Distillation with Conditional Adversarial Networks.
CoRR
Zheng Xu, Yen-Chang Hsu, Jiawei Huang
2017 J jnl
Learning to cluster in order to Transfer across domains and tasks.
CoRR
Yen-Chang Hsu, Zhaoyang Lv, Zsolt Kira
2016 J jnl
Deep Image Category Discovery using a Transferred Similarity Function.
CoRR
Yen-Chang Hsu, Zhaoyang Lv, Zsolt Kira
2015 J jnl
Neural network-based clustering using pairwise constraints.
CoRR
Yen-Chang Hsu, Zsolt Kira