Chi-Heng Lin - RankMe

40 papers A* 10A 1B 1Journal 23Unranked 4

Year	Rank	Type	Title / 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
2026	J	`jnl`	Transform-Augmented GRPO Improves Pass@k. CoRR Khiem Le, Youssef Mroueh, Phuc Nguyen, Chi-Heng Lin, Shangqian Gao, Ting Hua, Nitesh V. Chawla
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	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
2025	J	`jnl`	VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs. CoRR Avinash Amballa, Yashas Malur Saidutta, Chi-Heng Lin, Vivek Kulkarni, Srinivas Chappidi
2025	J	`jnl`	Your contrastive learning problem is secretly a distribution alignment problem. CoRR Zihao Chen, Chi-Heng Lin, Ran Liu, Jingyun Xiao, Eva L. Dyer
2024	A*	`conf`	Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance. ICML Chiraag Kaushik, Ran Liu, Chi-Heng Lin, Amrit Khera, Matthew Y. Jin, Wenrui Ma, Vidya Muthukumar, Eva L. Dyer
2024	J	`jnl`	Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance. CoRR Chiraag Kaushik, Ran Liu, Chi-Heng Lin, Amrit Khera, Matthew Y. Jin, Wenrui Ma, Vidya Muthukumar, Eva L. Dyer
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	—	`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	J	`jnl`	The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective. J. Mach. Learn. Res. Chi-Heng Lin, Chiraag Kaushik, Eva L. Dyer, Vidya Muthukumar
2024	A*	`conf`	Your contrastive learning problem is secretly a distribution alignment problem. NeurIPS Zihao Chen, Chi-Heng Lin, Ran Liu, Jingyun Xiao, Eva L. Dyer
2023	A*	`conf`	Half-Hop: A graph upsampling approach for slowing down message passing. ICML Mehdi Azabou, Venkataramana Ganesh, Shantanu Thakoor, Chi-Heng Lin, Lakshmi Sathidevi, Ran Liu, Michal Valko, Petar Velickovic, Eva L. Dyer
2023	J	`jnl`	Half-Hop: A graph upsampling approach for slowing down message passing. CoRR Mehdi Azabou, Venkataramana Ganesh, Shantanu Thakoor, Chi-Heng Lin, Lakshmi Sathidevi, Ran Liu, Michal Valko, Petar Velickovic, Eva L. Dyer
2023	—	`—`	Understanding Data Manipulation and How to Leverage it To Improve Generalization. Chi-Heng Lin
2022	A*	`conf`	Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out. ICML Jun-Kun Wang, Chi-Heng Lin, Andre Wibisono, Bin Hu
2022	J	`jnl`	Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Łojasiewicz Functions when the Non-Convexity is Averaged-Out. CoRR Jun-Kun Wang, Chi-Heng Lin, Andre Wibisono, Bin Hu
2022	J	`jnl`	The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective. CoRR Chi-Heng Lin, Chiraag Kaushik, Eva L. Dyer, Vidya Muthukumar
2021	A*	`conf`	A Modular Analysis of Provable Acceleration via Polyak's Momentum: Training a Wide ReLU Network and a Deep Linear Network. ICML Jun-Kun Wang, Chi-Heng Lin, Jacob D. Abernethy
2021	A	`conf`	Bayesian optimization for modular black-box systems with switching costs. UAI Chi-Heng Lin, Joseph D. Miano, Eva L. Dyer
2021	A*	`conf`	Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity. NeurIPS Ran Liu, Mehdi Azabou, Max Dabagia, Chi-Heng Lin, Mohammad Gheshlaghi Azar, Keith B. Hengen, Michal Valko, Eva L. Dyer
2021	J	`jnl`	Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity. CoRR Ran Liu, Mehdi Azabou, Max Dabagia, Chi-Heng Lin, Mohammad Gheshlaghi Azar, Keith B. Hengen, Michal Valko, Eva L. Dyer
2021	J	`jnl`	Escaping Saddle Points Faster with Stochastic Momentum. CoRR Jun-Kun Wang, Chi-Heng Lin, Jacob D. Abernethy
2021	A*	`conf`	Making transport more robust and interpretable by moving data through a small number of anchor points. ICML Chi-Heng Lin, Mehdi Azabou, Eva L. Dyer
2021	J	`jnl`	Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction. CoRR Mehdi Azabou, Mohammad Gheshlaghi Azar, Ran Liu, Chi-Heng Lin, Erik C. Johnson, Kiran Bhaskaran-Nair, Max Dabagia, Keith B. Hengen, William R. Gray Roncal, Michal Valko, Eva L. Dyer
2020	J	`jnl`	Bayesian optimization for modular black-box systems with switching costs. CoRR Chi-Heng Lin, Joseph D. Miano, Eva L. Dyer
2020	A*	`conf`	Escaping Saddle Points Faster with Stochastic Momentum. ICLR Jun-Kun Wang, Chi-Heng Lin, Jacob D. Abernethy
2020	J	`jnl`	Making transport more robust and interpretable by moving data through a small number of anchor points. CoRR Chi-Heng Lin, Mehdi Azabou, Eva L. Dyer
2017	J	`jnl`	Downlink Linear Precoders Based on Statistical CSI for Multicell MIMO-OFDM. Wirel. Commun. Mob. Comput. Ebrahim Baktash, Chi-Heng Lin, Xiaodong Wang, Mahmood Karimi
2016	B	`conf`	Efficient Error-Resilient Multicasting for Multi-View 3D Videos in Wireless Network. GLOBECOM Chi-Heng Lin, De-Nian Yang, Ji-Tang Lee, Wanjiun Liao
2015	J	`jnl`	Error-Resilient Multicast for Multi-View 3D Videos in IEEE 802.11 Networks. CoRR Chi-Heng Lin, De-Nian Yang, Ji-Tang Lee, Wanjiun Liao
2013	J	`jnl`	In-Network Computations of Machine-to-Machine Communications for Wireless Robotics. Wirel. Pers. Commun. Fan-Min Tseng, Chi-Heng Lin, Kwang-Cheng Chen