Guangxuan Xiao

According to our database, Guangxuan Xiao authored at least 28 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding.

Jiayi Yuan, Cameron Shinn, Kai Xu, Jingze Cui, George Klimiashvili, Guangxuan Xiao, Perkz Zheng, Bo Li, Yuxin Zhou, Zhouhai Ye, Weijie You, Tian Zheng, Dominic Brown, Pengbo Wang, Richard Cai, Julien Demouth, John D. Owens, Xia Hu, Song Han, Timmy Liu, Huizi Mao

CoRR, December, 2025

Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling.

Jack Cook, Junxian Guo, Guangxuan Xiao, Yujun Lin, Song Han

CoRR, December, 2025

Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding.

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

CoRR, December, 2025

Optimizing Mixture of Block Attention.

Guangxuan Xiao, Junxian Guo, Kasra Mazaheri, Song Han

CoRR, November, 2025

StreamingVLM: Real-Time Understanding for Infinite Video Streams.

Ruyi Xu, Guangxuan Xiao, Yukang Chen, Liuning He, Kelly Peng, Yao Lu, Song Han

CoRR, October, 2025

FastComposer: Tuning-Free Multi-subject Image Generation with Localized Attention.

Guangxuan Xiao, Tianwei Yin, William T. Freeman, Frédo Durand, Song Han

Int. J. Comput. Vis., March, 2025

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention.

Shang Yang, Junxian Guo, Haotian Tang, Qinghao Hu, Guangxuan Xiao, Jiaming Tang, Yujun Lin, Zhijian Liu, Yao Lu, Song Han

Proceedings of the Eighth Conference on Machine Learning and Systems, 2025

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving.

Yujun Lin, Haotian Tang, Shang Yang, Zhekai Zhang, Guangxuan Xiao, Chuang Gan, Song Han

Proceedings of the Eighth Conference on Machine Learning and Systems, 2025

XAttention: Block Sparse Attention with Antidiagonal Scoring.

Ruyi Xu, Guangxuan Xiao, Haofeng Huang, Junxian Guo, Song Han

Proceedings of the Forty-second International Conference on Machine Learning, 2025

DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads.

Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, Junxian Guo, Shang Yang, Haotian Tang, Yao Fu, Song Han

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Retrieval Head Mechanistically Explains Long-Context Factuality.

Wenhao Wu, Yizhong Wang, Guangxuan Xiao, Hao Peng, Yao Fu

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration.

Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Guangxuan Xiao, Song Han

GetMobile Mob. Comput. Commun., December, 2024

Correction to: Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-level Backdoor Attacks.

Zhengyan Zhang, Guangxuan Xiao, Yongwei Li, Tian Lv, Fanchao Qi, Zhiyuan Liu, Yasheng Wang, Xin Jiang, Maosong Sun

Mach. Intell. Res., December, 2024

FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training.

Kezhao Huang, Haitian Jiang, Minjie Wang, Guangxuan Xiao, David Wipf, Xiang Song, Quan Gan, Zengfeng Huang, Jidong Zhai, Zheng Zhang

Proc. VLDB Endow., February, 2024

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving.

Yujun Lin, Haotian Tang, Shang Yang, Zhekai Zhang, Guangxuan Xiao, Chuang Gan, Song Han

CoRR, 2024

InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory.

Chaojun Xiao, Pengle Zhang, Xu Han, Guangxuan Xiao, Yankai Lin, Zhengyan Zhang, Zhiyuan Liu, Song Han, Maosong Sun

CoRR, 2024

InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory.

Chaojun Xiao, Pengle Zhang, Xu Han, Guangxuan Xiao, Yankai Lin, Zhengyan Zhang, Zhiyuan Liu, Maosong Sun

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

BitDelta: Your Fine-Tune May Only Be Worth One Bit.

James Liu, Guangxuan Xiao, Kai Li, Jason D. Lee, Song Han, Tri Dao, Tianle Cai

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration.

Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, Song Han

Proceedings of the Seventh Annual Conference on Machine Learning and Systems, 2024

QUEST: Query-Aware Sparsity for Efficient Long-Context LLM Inference.

Jiaming Tang, Yilong Zhao, Kan Zhu, Guangxuan Xiao, Baris Kasikci, Song Han

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Efficient Streaming Language Models with Attention Sinks.

Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, Mike Lewis

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-level Backdoor Attacks.

Zhengyan Zhang, Guangxuan Xiao, Yongwei Li, Tian Lv, Fanchao Qi, Zhiyuan Liu, Yasheng Wang, Xin Jiang, Maosong Sun

Mach. Intell. Res., April, 2023

Offsite-Tuning: Transfer Learning without Full Model.

Guangxuan Xiao, Ji Lin, Song Han

CoRR, 2023

ReFresh: Reducing Memory Access from Exploiting Stable Historical Embeddings for Graph Neural Network Training.

Kezhao Huang, Haitian Jiang, Minjie Wang, Guangxuan Xiao, David Wipf, Xiang Song, Quan Gan, Zengfeng Huang, Jidong Zhai, Zheng Zhang

CoRR, 2023

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models.

Guangxuan Xiao, Ji Lin, Mickaël Seznec, Hao Wu, Julien Demouth, Song Han

Proceedings of the International Conference on Machine Learning, 2023

2022

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models.

Guangxuan Xiao, Ji Lin, Mickaël Seznec, Julien Demouth, Song Han

CoRR, 2022

Sparse and Local Networks for Hypergraph Reasoning.

Guangxuan Xiao, Leslie Pack Kaelbling, Jiajun Wu, Jiayuan Mao

Proceedings of the Learning on Graphs Conference, 2022

2021

Red Alarm for Pre-trained Models: Universal Vulnerabilities by Neuron-Level Backdoor Attacks.

Zhengyan Zhang, Guangxuan Xiao, Yongwei Li, Tian Lv, Fanchao Qi, Zhiyuan Liu, Yasheng Wang, Xin Jiang, Maosong Sun

CoRR, 2021