Chi-Chih Chang

29 papers A* 4A 3Misc 1Journal 19Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Bit-Serial Acceleration of LLM Inference With Mixture-of-Datatype Quantization. IEEE Trans. Computers Yuzong Chen, Chi-Chih Chang, Xilai Dai, Ahmed F. AbouElhamayed, Marta Andronic, George A. Constantinides, Mohamed S. Abdelfattah
2026	J	`jnl`	SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache. CoRR Chi-Chih Chang, Siqi Zhu, Zhichen Zeng, Haibin Lin, Jiaxuan You, Mohamed S. Abdelfattah, Ziheng Jiang, Xuehai Qian
2025	J	`jnl`	Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding. CoRR Yilong Zhao, Jiaming Tang, Kan Zhu, Zihao Ye, Chi-Chih Chang, Chaofan Lin, Jongseok Park, Guangxuan Xiao, Mohamed S. Abdelfattah, Mingyu Gao, Baris Kasikci, Song Han, Ion Stoica
2025	A*	`conf`	FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference. EMNLP Yu-Chen Lu, Chong-Yan Chen, Chi-Chih Chang, Yu-Fang Hu, Kai-Chiang Wu
2025	J	`jnl`	FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference. CoRR Yu-Chen Lu, Chong-Yan Chen, Chi-Chih Chang, Yu-Fang Hu, Kai-Chiang Wu
2025	A*	`conf`	Palu: KV-Cache Compression with Low-Rank Projection. ICLR Chi-Chih Chang, Wei-Cheng Lin, Chien-Yu Lin, Chong-Yan Chen, Yu-Fang Hu, Pei-Shuo Wang, Ning-Chi Huang, Luis Ceze, Mohamed S. Abdelfattah, Kai-Chiang Wu
2025	A*	`conf`	Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models. ICML Hung-Yueh Chiang, Chi-Chih Chang, Natalia Frumkin, Kai-Chiang Wu, Mohamed S. Abdelfattah, Diana Marculescu
2025	J	`jnl`	Quamba2: A Robust and Scalable Post-training Quantization Framework for Selective State Space Models. CoRR Hung-Yueh Chiang, Chi-Chih Chang, Natalia Frumkin, Kai-Chiang Wu, Mohamed S. Abdelfattah, Diana Marculescu
2025	A*	`conf`	Quamba: A Post-Training Quantization Recipe for Selective State Space Models. ICLR Hung-Yueh Chiang, Chi-Chih Chang, Natalia Frumkin, Kai-Chiang Wu, Diana Marculescu
2025	J	`jnl`	SparAMX: Accelerating Compressed LLMs Token Generation on AMX-powered CPUs. CoRR Ahmed F. AbouElhamayed, Jordan Dotzel, Yash Akhauri, Chi-Chih Chang, Sameh Gobriel, J. Pablo Muñoz, Vui Seng Chua, Nilesh Jain, Mohamed S. Abdelfattah
2025	J	`jnl`	Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding. CoRR Pei-Shuo Wang, Jian-Jia Chen, Chun-Che Yang, Chi-Chih Chang, Ning-Chi Huang, Mohamed S. Abdelfattah, Kai-Chiang Wu
2025	J	`jnl`	SplitReason: Learning To Offload Reasoning. CoRR Yash Akhauri, Anthony Fei, Chi-Chih Chang, Ahmed F. AbouElhamayed, Yueying Li, Mohamed S. Abdelfattah
2025	A	`conf`	Systolic Sparse Tensor Slices: FPGA Building Blocks for Sparse and Dense AI Acceleration. FPGA Endri Taka, Ning-Chi Huang, Chi-Chih Chang, Kai-Chiang Wu, Aman Arora, Diana Marculescu
2025	J	`jnl`	Systolic Sparse Tensor Slices: FPGA Building Blocks for Sparse and Dense AI Acceleration. CoRR Endri Taka, Ning-Chi Huang, Chi-Chih Chang, Kai-Chiang Wu, Aman Arora, Diana Marculescu
2025	J	`jnl`	The Power of Negative Zero: Datatype Customization for Quantized Large Language Models. CoRR Yuzong Chen, Xilai Dai, Chi-Chih Chang, Yash Akhauri, Mohamed S. Abdelfattah
2025	J	`jnl`	TokenButler: Token Importance is Predictable. CoRR Yash Akhauri, Ahmed F. AbouElhamayed, Yifei Gao, Chi-Chih Chang, Nilesh Jain, Mohamed S. Abdelfattah
2025	J	`jnl`	UniQL: Unified Quantization and Low-rank Compression for Adaptive Edge LLMs. CoRR Hung-Yueh Chiang, Chi-Chih Chang, Yu-Chen Lu, Chien-Yu Lin, Kai-Chiang Wu, Mohamed S. Abdelfattah, Diana Marculescu
2025	J	`jnl`	xKV: Cross-Layer SVD for KV-Cache Compression. CoRR Chi-Chih Chang, Chien-Yu Lin, Yash Akhauri, Wei-Cheng Lin, Kai-Chiang Wu, Luis Ceze, Mohamed S. Abdelfattah
2024	—	`conf`	ELSA: Exploiting Layer-wise N: M Sparsity for Vision Transformer Acceleration. CVPR Workshops Ning-Chi Huang, Chi-Chih Chang, Wei-Cheng Lin, Endri Taka, Diana Marculescu, Kai-Chiang Wu
2024	J	`jnl`	ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration. CoRR Ning-Chi Huang, Chi-Chih Chang, Wei-Cheng Lin, Endri Taka, Diana Marculescu, Kai-Chiang Wu
2024	A	`conf`	FLORA: Fine-grained Low-Rank Architecture Search for Vision Transformer. WACV Chi-Chih Chang, Yuan-Yao Sung, Shixing Yu, Ning-Chi Huang, Diana Marculescu, Kai-Chiang Wu
2024	J	`jnl`	Palu: Compressing KV-Cache with Low-Rank Projection. CoRR Chi-Chih Chang, Wei-Cheng Lin, Chien-Yu Lin, Chong-Yan Chen, Yu-Fang Hu, Pei-Shuo Wang, Ning-Chi Huang, Luis Ceze, Kai-Chiang Wu
2024	J	`jnl`	Quamba: A Post-Training Quantization Recipe for Selective State Space Models. CoRR Hung-Yueh Chiang, Chi-Chih Chang, Natalia Frumkin, Kai-Chiang Wu, Diana Marculescu
2024	Misc	`conf`	Transformer and Its Variants for Identifying Good Dice in Bad Neighborhoods. VTS Cheng-Che Lu, Chi-Chih Chang, Chia-Heng Yen, Shuo-Wen Chang, Ying-Hua Chu, Kai-Chiang Wu, Mango Chia-Tso Chao
2024	J	`jnl`	V"Mean"ba: Visual State Space Models only need 1 hidden dimension. CoRR Tien-Yu Chi, Hung-Yueh Chiang, Chi-Chih Chang, Ning-Chi Huang, Kai-Chiang Wu
2023	J	`jnl`	FLORA: Fine-grained Low-Rank Architecture Search for Vision Transformer. CoRR Chi-Chih Chang, Yuan-Yao Sung, Shixing Yu, Ning-Chi Huang, Diana Marculescu, Kai-Chiang Wu
2023	—	`conf`	Q-YOLOP: Quantization-Aware You Only Look Once for Panoptic Driving Perception. ICME Workshops Chi-Chih Chang, Wei-Cheng Lin, Pei-Shuo Wang, Sheng-Feng Yu, Yu-Chen Lu, Kuan-Cheng Lin, Kai-Chiang Wu
2023	J	`jnl`	Q-YOLOP: Quantization-aware You Only Look Once for Panoptic Driving Perception. CoRR Chi-Chih Chang, Wei-Cheng Lin, Pei-Shuo Wang, Sheng-Feng Yu, Yu-Chen Lu, Kuan-Cheng Lin, Kai-Chiang Wu
2004	A	`conf`	Embedding information within dynamic visual patterns. ICME Wen-Hung Liao, Chi-Chih Chang