publications.json

[
    {
        "title": "d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation",
        "authors": "Yu-Yang Qian, Junda Su, Lanxiang Hu, Peiyuan Zhang, Zhijie Deng, Peng Zhao, Hao Zhang",
        "venue": "Preprint 2026",
        "pdf": "https://arxiv.org/pdf/2601.07568",
        "code": "https://github.com/hao-ai-lab/d3LLM",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Diffusion Models",
        "date": "01/2026"
    },
    {
        "title": "Fast and Accurate Causal Parallel Decoding using Jacobi Forcing",
        "authors": "Lanxiang Hu, Siqi Kou, Yichao Fu, Samyam Rajbhandari, Tajana Rosing, Yuxiong He, Zhijie Deng, Hao Zhang",
        "venue": "Preprint 2025",
        "pdf": "https://arxiv.org/pdf/2512.14681",
        "code": "https://github.com/hao-ai-lab/JacobiForcing",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models, Diffusion Models",
        "date": "12/2025"
    },
    {
        "title": "Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench",
        "authors": "Lanxiang Hu, Abhilash Shankarampeta, Yixin Huang, Zilin Dai, Haoyang Yu, Yujie Zhao, Haoqiang Kang, Daniel Zhao, Tajana Rosing, Hao Zhang",
        "venue": "Preprint 2025",
        "pdf": "https://arxiv.org/pdf/2512.02942",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Diffusion Models, Evals",
        "date": "10/2025"
    },
    {
        "title": "Efficient Long-context Language Model Training by Core Attention Disaggregation",
        "authors": "Yonghao Zhuang*, Junda Chen*, Bo Pang, Yi Gu, Yibo Zhu, Yimin Jiang, Ion Stoica, Eric Xing, Hao Zhang",
        "venue": "MLSYS 2026",
        "pdf": "https://arxiv.org/pdf/2510.18121",
        "code": "https://github.com/hao-ai-lab/DistCA",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, ML Systems, Large Language Models",
        "date": "10/2025"
    },
    {
        "title": "Stronger Together: On-Policy Reinforcement Learning for Collaborative LLMs",
        "authors": "Yujie Zhao, Lanxiang Hu, Yang Wang, Minmin Hou, Hao Zhang, Ke Ding, Jishen Zhao",
        "venue": "ICLR 2026",
        "pdf": "https://arxiv.org/pdf/2510.11062",
        "code": "https://github.com/pettingllms-ai/PettingLLMs",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large Language Models, Agents",
        "date": "12/2025"
    },
    {
        "title": "Deep Think with Confidence",
        "authors": "Yichao Fu, Xuewei Wang, Hao Zhang, Yuandong Tian, Jiawei Zhao",
        "venue": "ICLR 2026",
        "pdf": "https://arxiv.org/pdf/2508.15260",
        "code": "https://github.com/facebookresearch/deepconf",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models",
        "date": "09/2025"
    },
    {
        "title": "TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs",
        "authors": "Lanxiang Hu, Tajana Rosing, Hao Zhang",
        "venue": "ACL 2025",
        "pdf": "https://aclanthology.org/2025.acl-long.33.pdf",
        "code": "https://github.com/snyhlxde1/TrimLLM",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large Language Models",
        "date": "08/2025"
    },
    {
        "title": "Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing",
        "authors": "Xu Wang, Chenkai Xu, Yijie Jin, Jiachun Jin, Hao Zhang, Zhijie Deng",
        "venue": "ICLR 2026",
        "pdf": "https://arxiv.org/pdf/2508.09192",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://github.com/zhijie-group/Discrete-Diffusion-Forcing",
        "tag": "Selected, Large Language Models, Diffusion Models",
        "date": "08/2025"
    },
    {
        "title": "Scaling Speculative Decoding with Lookahead Reasoning",
        "authors": "Yichao Fu, Rui Ge, Zelei Shao, Zhijie Deng, Hao Zhang",
        "venue": "NeurIPS 2025",
        "pdf": "https://arxiv.org/pdf/2506.19830",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://github.com/hao-ai-lab/LookaheadReasoning",
        "tag": "Selected, Large Language Models",
        "date": "06/2025"
    },
    {
        "title": "Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL",
        "authors": "Zhewei Yao, Guoheng Sun, Lukasz Borchmann, Zheyu Shen, Minghang Deng, Bohan Zhai, Hao Zhang, Ang Li, Yuxiong He",
        "venue": "Preprint 2025",
        "pdf": "https://arxiv.org/pdf/2505.20315",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://huggingface.co/Snowflake/Arctic-Text2SQL-R1-7B",
        "tag": "Large Language Models",
        "date": "05/2025"
    },
    {
        "title": "VSA: Faster Video Diffusion with Trainable Sparse Attention",
        "authors": "Peiyuan Zhang*, Yongqi Chen*, Haofeng Huang*, Will Lin, Zhengzhong Liu, Ion Stoica, Eric P Xing, Hao Zhang",
        "venue": "NeurIPS 2025",
        "pdf": "https://arxiv.org/pdf/2505.13389",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://github.com/hao-ai-lab/FastVideo",
        "tag": "Selected, Diffusion Models",
        "date": "05/2025"
    },
    {
        "title": "LMGame-Bench: How Good are LLMs at Playing Games?",
        "authors": "Lanxiang Hu*, Mingjia Huo*, Yuxuan Zhang, Haoyang Yu, Eric P Xing, Ion Stoica, Tajana Rosing, Haojian Jin, Hao Zhang",
        "venue": "ICLR 2026",
        "pdf": "https://arxiv.org/pdf/2505.15146?",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://github.com/lmgame-org/GamingAgent/tree/main/lmgame-bench",
        "tag": "Selected, Large Language Models, Evals",
        "date": "05/2025"
    },
    {
        "title": "Efficiently Scaling LLM Reasoning with Certaindex",
        "authors": "Yichao Fu*, Junda Chen*, Siqi Zhu, Zheyu Fu, Zhongdongming Dai, Yonghao Zhuang, Yian Ma, Aurick Qiao, Tajana Rosing, Ion Stoica, Hao Zhang",
        "venue": "NeurIPS 2025",
        "pdf": "https://arxiv.org/pdf/2412.20993",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://github.com/hao-ai-lab/Dynasor",
        "tag": "Selected, Large Language Models, ML Systems",
        "date": "01/2025"
    },
    {
        "title": "Reasoning without Self-doubt: More Efficient Chain-of-thought through Certainty Probing",
        "authors": "Yichao Fu, Junda Chen, Yonghao Zhuang, Zheyu Fu, Ion Stoica, Hao Zhang",
        "venue": "Foundation Models in the Wild Workshop @ ICML 2025",
        "pdf": "https://openreview.net/pdf?id=wpK4IMJfdX",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://github.com/hao-ai-lab/Dynasor",
        "tag": "Selected, Large Language Models, ML Systems",
        "date": "03/2025"
    },
    {
        "title": "Fast Video Generation with Sliding Tile Attention",
        "authors": "Peiyuan Zhang, Yongqi Chen*, Runlong Su*, Hangliang Ding, Ion Stoica, Zhengzhong Liu, Hao Zhang",
        "venue": "ICML 2025",
        "pdf": "https://arxiv.org/pdf/2502.04507",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://github.com/hao-ai-lab/FastVideo",
        "tag": "Selected, ML Systems, Diffusion Models",
        "date": "01/2025"
    },
   {
        "title": "ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Format Restriction, and Column Exploration",
        "authors": "Minghang Deng, Ashwin Ramachandran, Canwen Xu, Lanxiang Hu, Zhewei Yao, Anupam Datta, Hao Zhang",
        "venue": "Preprint 2025",
        "pdf": "https://arxiv.org/pdf/2502.00675",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models",
        "date": "01/2025"
    },
    {
        "title": "Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile",
        "authors": "Hangliang Ding*, Dacheng Li*, Runlong Su, Peiyuan Zhang, Zhijie Deng, Ion Stoica, Hao Zhang",
        "venue": "ES-FOMO Workshop @ ICML 2025",
        "pdf": "https://arxiv.org/pdf/2502.06155",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://github.com/hao-ai-lab/FastVideo",
        "tag": "Selected, ML Systems, Diffusion Models",
        "date": "01/2025"
    },
    {
        "title": "Scaling Long Context Training Data by Long-Distance Referrals",
        "authors": "Yonghao Zhuang, Lanxiang Hu, Longfei Yun, Souvik Kundu, Zhengzhong Liu, Eric P. Xing, Hao Zhang",
        "venue": "ICLR 2025",
        "pdf": "https://openreview.net/pdf?id=tePFpDgyqg",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models",
        "date": "09/2024"
    },
    {
        "title": "MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection",
        "authors": "Bokai Lin, Zihao Zeng, Zipeng Xiao, Siqi Kou, TianQi Hou, Xiaofeng Gao, Hao Zhang, Zhijie Deng",
        "venue": "ICLR 2025",
        "pdf": "https://arxiv.org/pdf/2410.14731",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large Language Models, ML Systems",
        "date": "09/2024"
    },
    {
        "title": "GameArena: Evaluating LLM Reasoning through Live Computer Games",
        "authors": "Lanxiang Hu*, Qiyu Li*, Anze Xie*, Nan Jiang, Ion Stoica, Haojian Jin, Hao Zhang",
        "venue": "ICLR 2025",
        "pdf": "https://arxiv.org/pdf/2412.06394",
        "code": "https://github.com/lmgame-org",
        "presentation": "",
        "award": "",
        "project": "https://lmgame.org/#/blog/ai_space_escape",
        "tag": "Selected, Large Language Models, Evals",
        "date": "09/2024"
    },
    {
        "title": "Specifications: The Missing Link to Making the Development of LLM Systems an Engineering Discipline",
        "authors": "Ion Stoica, Matei Zaharia, Joseph Gonzalez, Ken Goldberg, Koushik Sen, Hao Zhang, Anastasios N. Angelopoulos, Shishir G. Patil, Lingjiao Chen, Wei-Lin Chiang, Jared Q. Davis",
        "venue": "Preprint 2024",
        "pdf": "https://arxiv.org/pdf/2412.05299",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models, Scalable ML, ML Systems",
        "date": "08/2024"
    },
    {
        "title": "Efficient LLM Scheduling by Learning to Rank",
        "authors": "Yichao Fu, Siqi Zhu, Runlong Su, Aurick Qiao, Ion Stoica, Hao Zhang",
        "venue": "NeurIPS 2024",
        "pdf": "https://arxiv.org/pdf/2408.15792",
        "code": "https://github.com/hao-ai-lab/vllm-ltr",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models, Scalable ML",
        "date": "08/2024"
    },
    {
        "title": "MPC-Minimized Secure LLM Inference",
        "authors": "Deevashwer Rathee*, Dacheng Li*, Ion Stoica, Hao Zhang, Raluca Ada Popa",
        "venue": "Preprint 2024",
        "pdf": "https://arxiv.org/pdf/2408.03561",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large Language Models, ML Security",
        "date": "08/2024"
    },
    {
        "title": "Optimizing Speculative Decoding for Serving Large Language Models Using Goodput",
        "authors": "Xiaoxuan Liu, Cade Daniel, Langxiang Hu, Woosuk Kwon, Zhuohan Li, Xiangxi Mo, Alvin Cheung, Zhijie Deng, Ion Stoica, Hao Zhang",
        "venue": "Preprint 2024",
        "pdf": "https://arxiv.org/pdf/2406.14066",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models, Scalable ML, ML Systems",
        "date": "06/2024"
    },
    {
        "title": "AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models",
        "authors": "Zihao Zeng, Yibo Miao, Hongcheng Gao, Hao Zhang, Zhijie Deng",
        "venue": "EMNLP 2024",
        "pdf": "https://arxiv.org/pdf/2406.13233",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models, Scalable ML",
        "date": "06/2024"
    },
    {
        "title": "Toward Inference-optimal Mixture-of-Expert Large Language Models",
        "authors": "Longfei Yun*, Yonghao Zhuang*, Yao Fu, Eric P Xing, Hao Zhang",
        "venue": "Preprint 2024",
        "pdf": "https://arxiv.org/pdf/2404.02852",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models",
        "date": "04/2024"
    },
    {
        "title": "Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length",
        "authors": "Xuezhe Ma*, Xiaomeng Yang*, Wenhan Xiong, Beidi Chen, Lili Yu, Hao Zhang, Jonathan May, Luke Zettlemoyer, Omer Levy, Chunting Zhou*",
        "venue": "NeurIPS 2024",
        "pdf": "https://arxiv.org/pdf/2404.08801",
        "code": "https://github.com/XuezheMax/megalodon",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models",
        "date": "04/2024"
    },
    {
        "title": "MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving",
        "authors": "Jiangfei Duan, Runyu Lu, Haojie Duanmu, Xiuhong Li, Xingcheng Zhang, Dahua Lin, Ion Stoica, Hao Zhang",
        "venue": "ICML 2024",
        "pdf": "https://arxiv.org/pdf/2404.02015",
        "code": "https://github.com/hao-ai-lab/MuxServe",
        "presentation": "",
        "award": "",
        "project": "https://hao-ai-lab.github.io/blogs/muxserve/",
        "tag": "Selected, Large Language Models, Scalable ML, ML Systems",
        "date": "06/2024"
    },
    {
        "title": "CLLMs: Consistency Large Language Models",
        "authors": "Siqi Kou*, Lanxiang Hu*, Zhezhi He, Zhijie Deng, Hao Zhang",
        "venue": "ICML 2024",
        "pdf": "https://arxiv.org/pdf/2403.00835.pdf",
        "code": "https://github.com/hao-ai-lab/Consistency_LLM",
        "presentation": "",
        "award": "",
        "project": "https://hao-ai-lab.github.io/blogs/cllm/",
        "tag": "Selected, Large Language Models, Scalable ML, ML Systems",
        "date": "03/2024"
    },
    {
        "title": "DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving",
        "authors": "Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu, Yibo Zhu, Xuanzhe Liu, Xin Jin, Hao Zhang",
        "venue": "OSDI 2024",
        "pdf": "https://arxiv.org/pdf/2401.09670v1.pdf",
        "code": "https://github.com/LLMServe/DistServe",
        "presentation": "",
        "award": "",
        "project": "https://hao-ai-lab.github.io/blogs/distserve/",
        "tag": "Selected, Large Language Models, ML Systems",
        "date": "01/2024"
    },
    {
        "title": "Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference",
        "authors": "Wei-Lin Chiang*, Lianmin Zheng*, Ying Sheng, Anastasios Nikolas Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael Jordan, Joseph E. Gonzalez, Ion Stoica",
        "venue": "ICML 2024",
        "pdf": "https://arxiv.org/pdf/2403.04132.pdf",
        "code": "https://github.com/lm-sys/FastChat",
        "presentation": "",
        "award": "",
        "project": "https://chat.lmsys.org/",
        "tag": "Selected, Large Language Models",
        "date": "03/2024"
    },
    {
        "title": "InferCept: Efficient Intercept Support for Augmented Large Language Model Inference",
        "authors": "Reyna Abhyankar*, Zijian He*, Vikranth Srivatsa, Hao Zhang, Yiying Zhang",
        "venue": "ICML 2024",
        "pdf": "https://arxiv.org/pdf/2402.01869.pdf",
        "code": "https://github.com/WukLab/InferCept",
        "presentation": "",
        "award": "",
        "project": "https://mlsys.wuklab.io/posts/infercept/",
        "tag": "Selected, Large Language Models, ML Systems",
        "date": "02/2024"
    },
    {
        "title": "Break the Sequential Dependency of LLM Inference using Lookahead Decoding",
        "authors": "Yichao Fu, Peter Bailis, Ion Stoica, Hao Zhang",
        "venue": "ICML 2024",
        "pdf": "https://arxiv.org/pdf/2402.02057v1.pdf",
        "code": "https://github.com/hao-ai-lab/LookaheadDecoding",
        "presentation": "",
        "award": "",
        "project": "https://lmsys.org/blog/2023-11-21-lookahead-decoding/",
        "tag": "Selected, Large Language Models, ML Systems",
        "date": "02/2024"
    },
    {
        "title": "How Long Can Context Length of Open-Source LLMs truly Promise?",
        "authors": "Dacheng Li*, Rulin Shao*, Anze Xie, Ying Sheng, Lianmin Zheng, Joseph Gonzalez, Ion Stoica, Xuezhe Ma, Hao Zhang",
        "venue": "Instruction Tuning and Instruction Following Workshop @ NeurIPS 2023",
        "pdf": "https://openreview.net/pdf?id=LywifFNXV5",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://github.com/DachengLi1/LongChat",
        "tag": "Selected, Large Language Models",
        "date": "07/2023"
    },
    {
        "title": "Online Speculative Decoding",
        "authors": "Xiaoxuan Liu, Lanxiang Hu, Peter Bailis, Ion Stoica, Zhijie Deng, Alvin Cheung, Hao Zhang",
        "venue": "ICML 2024",
        "pdf": "https://arxiv.org/pdf/2310.07177.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models, ML Systems, Scalable ML",
        "date": "10/2023"
    },
    {
        "title": "DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training",
        "authors": "Dacheng Li*, Rulin Shao*, Anze Xie, Eric P Xing, Joseph E Gonzalez, Ion Stoica, Xuezhe Ma, Hao Zhang",
        "venue": "COLM 2024",
        "pdf": "https://arxiv.org/pdf/2310.03294.pdf",
        "code": "https://github.com/RulinShao/LightSeq",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large Language Models, ML Systems",
        "date": "10/2023"
    },
    {
        "title": "Efficient Detection of LLM-generated Texts with a Bayesian Surrogate Model",
        "authors": "Yibo Miao*, Hongcheng Gao*, Hao Zhang, Zhijie Deng",
        "venue": "ACL 2024",
        "pdf": "https://arxiv.org/pdf/2305.16617.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large Language Models, ML Security",
        "date": "05/2023"
    },
    {
        "title": "LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset",
        "authors": "Lianmin Zheng*, Wei-Lin Chiang*, Ying Sheng, Tianle Li, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zhuohan Li, Zi Lin, Eric Xing, Joseph E Gonzalez, Ion Stoica, Hao Zhang",
        "venue": "ICLR 2024",
        "pdf": "https://arxiv.org/pdf/2309.11998",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://huggingface.co/datasets/lmsys/lmsys-chat-1m",
        "tag": "Selected, Large Language Models",
        "date": "09/2023"
    },
    {
        "title": "Judging LLM-as-a-judge with MT-Bench and Chatbot Arena",
        "authors": "Lianmin Zheng*, Wei-Lin Chiang*, Ying Sheng*, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, Hao Zhang, Joseph E Gonzalez, Ion Stoica",
        "venue": "NeurIPS 2023",
        "pdf": "https://arxiv.org/pdf/2306.05685",
        "code": "https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge",
        "presentation": "",
        "award": "",
        "project": "https://chat.lmsys.org/?arena",
        "tag": "Selected, Large Language Models",
        "date": "06/2023"
    },
    {
        "title": "Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attacks",
        "authors": "Hongcheng Gao, Hao Zhang, Yinpeng Dong, Zhijie Deng",
        "venue": "Preprint 2023",
        "pdf": "https://arxiv.org/pdf/2306.13103.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "ML Security",
        "date": "06/2023"
    },
    {
        "title": "Efficient Memory Management for Large Language Model Serving with PagedAttention",
        "authors": "Woosuk Kwon*, Zhuohan Li*, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Yu, Joey Gonzalez, Hao Zhang, Ion Stoica",
        "venue": "SOSP 2023",
        "pdf": "",
        "code": "https://github.com/vllm-project/vllm",
        "presentation": "",
        "award": "",
        "project": "https://vllm.ai/",
        "tag": "Selected, Large Language Models, ML Systems",
        "date": "06/2023"
    },
    {
        "title": "Vicuna: An Open-source Chatbot Impressing GPT-4 with 90%* Chatgpt Quality",
        "authors": "Wei-Lin Chiang†, Zhuohan Li†, Zi Lin†, Ying Sheng†, Zhanghao Wu†, Hao Zhang†, Lianmin Zheng†, Siyuan Zhuang†, Yonghao Zhuang†, Joseph E Gonzalez†, Ion Stoica†, Eric P Xing†",
        "venue": "Blogpost 2023",
        "pdf": "https://lmsys.org/blog/2023-03-30-vicuna/",
        "code": "https://huggingface.co/lmsys/vicuna-13b-v1.5",
        "presentation": "",
        "award": "",
        "project": "https://github.com/lm-sys/FastChat",
        "tag": "Selected, Large Language Models, Large-scale ML Applications",
        "date": "03/2023"
    },
    {
        "title": "AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving",
        "authors": "Zhuohan Li*, Lianmin Zheng*, Yinmin Zhong*, Vincent Liu, Ying Sheng, Xin Jin, Yanping Huang, Zhifeng Chen, Hao Zhang, Joseph E Gonzalez, Ion Stoica",
        "venue": "OSDI 2023",
        "pdf": "https://arxiv.org/pdf/2302.11665.pdf",
        "code": "https://github.com/alpa-projects/mms",
        "presentation": "",
        "award": "",
        "project": "https://alpa.ai/opt",
        "tag": "Selected, ML Systems, Large Language Models",
        "date": "02/2023"
    },
    {
        "title": "On Optimizing the Communication of Model Parallelism",
        "authors": "Yonghao Zhuang*, Hexu Zhao*, Lianmin Zheng, Zhuohan Li, Eric P. Xing, Qirong Ho, Joseph E. Gonzalez, Ion Stoica, Hao Zhang",
        "venue": "MLSYS 2023",
        "pdf": "https://arxiv.org/pdf/2211.05322.pdf",
        "code": "https://github.com/alpa-projects/alpa/blob/main/alpa/pipeline_parallel/cross_mesh_resharding.py",
        "presentation": "https://github.com/alpa-projects/alpa/blob/main/alpa/pipeline_parallel/cross_mesh_resharding.py",
        "award": "",
        "project": "",
        "tag": "Selected, ML Systems, Large Language Models",
        "date": "10/2022"
    },
    {
        "title": "AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness",
        "authors": "Dacheng Li, Hongyi Wang, Eric Xing, Hao Zhang",
        "venue": "NeurIPS 2022",
        "pdf": "https://proceedings.neurips.cc/paper_files/paper/2022/file/2b4bfa1cebe78d125fefd7ea6ffcfc6d-Paper-Conference.pdf",
        "code": "https://github.com/DachengLi1/AMP",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "ML Systems, Large Language Models, Scalable ML",
        "date": "06/2022"
    },
    {
        "title": "MPCFormer: Fast, Performant and Private Transformer Inference with MPC",
        "authors": "Dacheng Li*, Rulin Shao*, Hongyi Wang*, Han Guo, Eric P. Xing, Hao Zhang",
        "venue": "ICLR 2023",
        "pdf": "https://arxiv.org/pdf/2211.01452.pdf",
        "code": "https://github.com/DachengLi1/MPCFormer",
        "presentation": "",
        "award": "Notable-top-25%",
        "project": "",
        "tag": "Selected, Large Language Models, ML Security",
        "date": "11/2022"
    },
    {
        "title": "Neural Eigenfunctions Are Structured Representation Learners",
        "authors": "Zhijie Deng, Jiaxin Shi, Hao Zhang, Peng Cui, Cewu Lu, Jun Zhu",
        "venue": "PAMI 2025",
        "pdf": "https://arxiv.org/pdf/2210.12637",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Scalable ML",
        "date": "10/2022"
    },
    {
        "title": "Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning",
        "authors": "Lianmin Zheng*, Zhuohan Li*, Hao Zhang*, Yonghao Zhuang, Zhifeng Chen, Yanping Huang, Yida Wang, Yuanzhong Xu, Danyang Zhuo, Eric P. Xing, Joseph E. Gonzalez, Ion Stoica",
        "venue": "OSDI 2022",
        "pdf": "https://arxiv.org/pdf/2201.12023.pdf",
        "code": "",
        "presentation": "https://youtu.be/Jqz34CV-UqU",
        "award": "",
        "project": "https://alpa.ai/",
        "tag": "Selected, Large Language Models, ML Systems",
        "date": "01/2022"
    },
    {
        "title": "Ada-segment: Automated Multi-loss Adaptation for Panoptic Segmentation",
        "authors": "Gengwei Zhang, Yiming Gao, Hang Xu, Hao Zhang, Zhenguo Li, Xiaodan Liang",
        "venue": "AAAI 2021",
        "pdf": "https://ojs.aaai.org/index.php/AAAI/article/download/16445/16252",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "AutoML, Large-scale ML Applications",
        "date": "02/2021"
    },
    {
        "title": "Terapipe: Token-level Pipeline Parallelism for Training Large-scale Language Models",
        "authors": "Zhuohan Li, Siyuan Zhuang, Shiyuan Guo, Danyang Zhuo, Hao Zhang, Dawn Song, Ion Stoica",
        "venue": "ICML 2021",
        "pdf": "https://arxiv.org/pdf/2102.07988.pdf",
        "code": "https://github.com/zhuohan123/terapipe",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large Language Models, ML Systems, Scalable ML",
        "date": "02/2021"
    },
    {
        "title": "Pollux: Co-adaptive Cluster Scheduling for Goodput-optimized Deep Learning",
        "authors": "Aurick Qiao, Sang Keun Choe, Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R Ganger, Eric P Xing",
        "venue": "OSDI 2021",
        "pdf": "https://arxiv.org/pdf/2008.12260.pdf",
        "code": "https://github.com/petuum/adaptdl",
        "presentation": "https://youtu.be/liPzlDAa8Ss",
        "award": "Jay Lepreau Best Paper Award",
        "project": "",
        "tag": "Selected, ML Systems",
        "date": "08/2020"
    },
    {
        "title": "Machine Learning Parallelism Could Be Adaptive, Composable, and Automated",
        "authors": "Hao Zhang",
        "venue": "CMU PhD Dissertation 2020",
        "pdf": "https://kilthub.cmu.edu/ndownloader/files/27533894",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, ML Systems, Scalable ML, AutoML",
        "date": "07/2020"
    },
    {
        "title": "Autosync: Learning to Synchronize for Data-parallel Distributed Deep Learning",
        "authors": "Hao Zhang*, Yuan Li*, Zhijie Deng, Xiaodan Liang, Lawrence Carin, Eric Xing",
        "venue": "NeurIPS 2020",
        "pdf": "https://proceedings.neurips.cc/paper/2020/file/0a2298a72858d90d5c4b4fee954b6896-Paper.pdf",
        "code": "https://github.com/petuum/autodist",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, ML Systems, Scalable ML, AutoML",
        "date": "06/2020"
    },
    {
        "title": "Toward Understanding the Impact of Staleness in Distributed Machine Learning",
        "authors": "Wei Dai, Yi Zhou, Nanqing Dong, Hao Zhang, Eric P Xing",
        "venue": "ICLR 2019",
        "pdf": "https://arxiv.org/pdf/1810.03264.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Scalable ML",
        "date": "10/2018"
    },
    {
        "title": "Autoloss: Learning Discrete Schedules for Alternate Optimization",
        "authors": "Haowen Xu*, Hao Zhang*, Zhiting Hu, Xiaodan Liang, Ruslan Salakhutdinov, Eric Xing",
        "venue": "ICLR 2019",
        "pdf": "https://arxiv.org/pdf/1810.03264.pdf",
        "code": "https://github.com/safpla/AutoLossRelease",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "AutoML",
        "date": "12/2018"
    },
    {
        "title": "Symbolic Graph Reasoning Meets Convolutions",
        "authors": "Xiaodan Liang, Zhiting Hu, Hao Zhang, Liang Lin, Eric P Xing",
        "venue": "NeurIPS 2018",
        "pdf": "https://proceedings.neurips.cc/paper_files/paper/2018/file/cbb6a3b884f4f88b3a8e3d44c636cbd8-Paper.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large-scale ML Applications",
        "date": "12/2018"
    },
    {
        "title": "Scan: Structure Correcting Adversarial Network for Organ Segmentation in Chest X-rays",
        "authors": "Wei Dai, Nanqing Dong, Zeya Wang, Xiaodan Liang, Hao Zhang, Eric P Xing",
        "venue": "Workshop on Deep Learning in Medical Image Analysis 2019",
        "pdf": "https://arxiv.org/pdf/1703.08770.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Healthcare",
        "date": "04/2017"
    },
    {
        "title": "Generative Semantic Manipulation with Mask-contrasting GAN",
        "authors": "Xiaodan Liang, Hao Zhang, Liang Lin, Eric Xing",
        "venue": "ECCV 2018",
        "pdf": "https://openaccess.thecvf.com/content_ECCV_2018/papers/Liang_Generative_Semantic_Manipulation_ECCV_2018_paper.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large-scale ML Applications",
        "date": "09/2018"
    },
    {
        "title": "Cavs: An Efficient Runtime System for Dynamic Neural Networks",
        "authors": "Shizhen Xu*, Hao Zhang*, Graham Neubig, Wei Dai, Jin Kyu Kim, Zhijie Deng, Qirong Ho, Guangwen Yang, Eric P Xing",
        "venue": "ATC 2018",
        "pdf": "https://www.usenix.org/system/files/conference/atc18/atc18-xu-shizhen.pdf",
        "code": "https://github.com/zhisbug/Cavs",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, ML Systems",
        "date": "12/2017"
    },
    {
        "title": "Zm-net: Real-time Zero-shot Image Manipulation Network",
        "authors": "Hao Wang, Xiaodan Liang, Hao Zhang, Dit-Yan Yeung, Eric P Xing",
        "venue": "Preprint 2017",
        "pdf": "https://arxiv.org/pdf/1703.07255",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large-scale ML Applications",
        "date": "03/2017"
    },
    {
        "title": "Structured Generative Adversarial Networks",
        "authors": "Zhijie Deng*, Hao Zhang*, Xiaodan Liang, Luona Yang, Shizhen Xu, Jun Zhu, Eric P Xing",
        "venue": "NeurIPS 2017",
        "pdf": "https://proceedings.neurips.cc/paper/2017/file/c3535febaff29fcb7c0d20cbe94391c7-Paper.pdf",
        "code": "https://github.com/thudzj/StructuredGAN",
        "presentation": "",
        "award": "Nvidia Pioneer Research Award",
        "project": "",
        "tag": "Scalable ML, Large-scale ML Applications",
        "date": "12/2017"
    },
    {
        "title": "Poseidon: An Efficient Communication Architecture for Distributed Deep Learning on GPU Clusters",
        "authors": "Hao Zhang, Zeyu Zheng, Shizhen Xu, Wei Dai, Qirong Ho, Xiaodan Liang, Zhiting Hu, Jinliang Wei, Pengtao Xie, Eric P Xing",
        "venue": "ATC 2017",
        "pdf": "https://www.usenix.org/system/files/conference/atc17/atc17-zhang.pdf",
        "code": "https://github.com/sailing-pmls/pmls-caffe",
        "presentation": "",
        "award": "",
        "project": "https://poseidon-release.readthedocs.io/en/v1.0.1/",
        "tag": "Selected, ML Systems",
        "date": "06/2017"
    },
    {
        "title": "Recurrent Topic-transition GAN for Visual Paragraph Generation",
        "authors": "Xiaodan Liang, Zhiting Hu, Hao Zhang, Chuang Gan, Eric P Xing",
        "venue": "ICCV 2017",
        "pdf": "https://openaccess.thecvf.com/content_ICCV_2017/papers/Liang_Recurrent_Topic-Transition_GAN_ICCV_2017_paper.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large-scale ML Applications",
        "date": "10/2017"
    },
    {
        "title": "On the Reducibility of Submodular Functions",
        "authors": "Jincheng Mei, Hao Zhang, Bao-Liang Lu",
        "venue": "AISTATS 2016",
        "pdf": "http://proceedings.mlr.press/v51/mei16.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Scalable ML",
        "date": "05/2016"
    },
    {
        "title": "Geeps: Scalable Deep Learning on Distributed GPUs with a GPU-specialized Parameter Server",
        "authors": "Henggang Cui, Hao Zhang, Gregory R Ganger, Phillip B Gibbons, Eric P Xing",
        "venue": "EUROSYS 2016",
        "pdf": "https://dl.acm.org/doi/pdf/10.1145/2901318.2901323",
        "code": "https://github.com/cuihenggang/geeps",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, ML Systems",
        "date": "04/2016"
    },
    {
        "title": "Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation",
        "authors": "Zhicheng Yan, Hao Zhang, Yangqing Jia, Thomas Breuel, Yizhou Yu",
        "venue": "Preprint 2016",
        "pdf": "https://arxiv.org/pdf/1603.04871.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large-scale ML Applications",
        "date": "03/2016"
    },
    {
        "title": "Learning Concept Taxonomies from Multi-modal Data",
        "authors": "Hao Zhang, Zhiting Hu, Yuntian Deng, Mrinmaya Sachan, Zhicheng Yan, Eric P. Xing",
        "venue": "ACL 2016",
        "pdf": "https://arxiv.org/pdf/1606.09239.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Large-scale ML Applications",
        "date": "06/2016"
    },
    {
        "title": "Automatic Photo Adjustment Using Deep Neural Networks",
        "authors": "Zhicheng Yan, Hao Zhang, Baoyuan Wang, Sylvain Paris, Yizhou Yu",
        "venue": "ACM Transactions on Graphics 2015",
        "pdf": "https://arxiv.org/pdf/1412.7725.pdf",
        "code": "https://github.com/stephenyan1231/dl-image-enhance",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large-scale ML Applications",
        "date": "05/2015"
    },
    {
        "title": "Dynamic Topic Modeling for Monitoring Market Competition from Online Text and Image Data",
        "authors": "Hao Zhang, Gunhee Kim, Eric P Xing",
        "venue": "KDD 2015",
        "pdf": "https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=848442f9ec47f3c310c3edaf2efc1477172db227",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "https://people.eecs.berkeley.edu/~hao/projects/BrandCompetition/brandcompetition.html",
        "tag": "Large-scale ML Applications, Scalable ML",
        "date": "08/2015"
    },
    {
        "title": "A Boosting-Based Spatial-Spectral Model for Stroke Patients' EEG Analysis in Rehabilitation Training",
        "authors": "Ye Liu, Hao Zhang, Min Chen, Liqing Zhang",
        "venue": "Transactions on Neural Systems and Rehabilitation Engineering 2015",
        "pdf": "https://people.eecs.berkeley.edu/~hao/projects/BSSM-TNSRE/07214285.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Healthcare",
        "date": "08/2015"
    },
    {
        "title": "HD-CNN: Hierarchical Deep Convolutional Neural Networks for Large Scale Visual Recognition",
        "authors": "Zhicheng Yan, Hao Zhang, Robinson Piramuthu, Vignesh Jagadeesh, Dennis DeCoste, Wei Di, Yizhou Yu",
        "venue": "ICCV 2015",
        "pdf": "https://openaccess.thecvf.com/content_iccv_2015/papers/Yan_HD-CNN_Hierarchical_Deep_ICCV_2015_paper.pdf",
        "code": "https://paperswithcode.com/paper/hd-cnn-hierarchical-deep-convolutional-neural#code",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Selected, Large-scale ML Applications, Scalable ML",
        "date": "12/2015"
    },
    {
        "title": "A Tensor-based Scheme for Stroke Patients’ Motor Imagery EEG Analysis in BCI-FES Rehabilitation Training",
        "authors": "Ye Liu, Mingfen Li, Hao Zhang, Hang Wang, Junhua Li, Jie Jia, Yi Wu, Liqing Zhang",
        "venue": "Journal of neuroscience methods 2014",
        "pdf": "https://bcmi.sjtu.edu.cn/~zhangliqing/Papers/2014JNM-StrokePatients-Liu.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Healthcare",
        "date": "01/2014"
    },
    {
        "title": "Common Spatial-spectral Boosting Pattern for Brain-computer Interface",
        "authors": "Ye Liu, Hao Zhang, Qibin Zhao, Liqing Zhang",
        "venue": "ECAI 2014",
        "pdf": "https://ebooks.iospress.nl/pdf/doi/10.3233/978-1-61499-419-0-537",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Healthcare",
        "date": "08/2014"
    },
    {
        "title": "Gaussian Mixture Modeling in Stroke Patients' Rehabilitation EEG Data Analysis",
        "authors": "Hao Zhang, Ye Liu, Jianyi Liang, Jianting Cao, Liqing Zhang",
        "venue": "EMBC 2013",
        "pdf": "http://139.91.210.27/CBML/PROCEEDINGS/2013_EMBC/PDFs/Papers/05861329.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "Healthcare",
        "date": "07/2013"
    },
    {
        "title": "Single-trial Discrimination of EEG Signals for Stroke Patients: a General Multi-way Analysis",
        "authors": "Ye Liu, Mingfen Li, Hao Zhang, Junhua Li, Jie Jia, Yi Wu, Jianting Cao, Liqing Zhang",
        "venue": "EMBC 2013",
        "pdf": "https://people.eecs.berkeley.edu/~hao/projects/TensorJNM/06609973.pdf",
        "code": "",
        "presentation": "",
        "award": "",
        "project": "",
        "tag": "",
        "date": "07/2013"
    }
]