Zhaozhuo Xu

[Scholar][Github]

I am an AI Researcher at Workato. I received my Ph.D. in Computer Science from Rice University under the supervision of professor Anshumali Shrivastava. My research focuses on scaling up machine learning on commodity hardware using randomized algorithms.

Selected Publication

† indicates corresponding authors

• Yuheng Wu, Wentao Guo, Zirui Liu, Heng Ji, Zhaozhuo Xu^† and Denghui Zhang^†, "How large language models encode theory-of-mind: a study on sparse parameter patterns", npj Artificial Intelligence 2025. PDF Code Psychology Today Neuroscience News

* indicates equal contribution

• Duc Duong*, Hoang Anh Duy Le*, Jianwen Xie, Anshumali Shrivastava and Zhaozhuo Xu, "Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets", EMNLP 2026 Oral.

• Hoang Anh Duy Le, Sahil Joshi, Zeyu Yang, Zhaozhuo Xu and Anshumali Shrivastava, "Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM Inference", ICML 2026. PDF

• Yide Ran, Wentao Guo, Jingwei Sun, Yanzhou Pan, Xiaodong Yu, Hao Wang, Jianwen Xie, Yiran Chen, Denghui Zhang and Zhaozhuo Xu, "Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity", ICLR 2026. PDF

• Ziwen Liu, Huawei Lin, Yide Ran, Denghui Zhang, Jianwen Xie, Chuan Li, Weijie Zhao and Zhaozhuo Xu, "Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning", ICLR 2026. PDF

• Zeyu Yang, Tianyi Zhang, Jianwen Xie, Chuan Li, Zhaozhuo Xu and Anshumali Shrivastava, "To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration", ICLR 2026. PDF Code

• Yuheng Wu, Jianwen Xie, Denghui Zhang and Zhaozhuo Xu, "DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic", EMNLP 2025. PDF Code

• Wenya Xie, Shaochen Zhong, Hoang Anh Duy Le, Zhaozhuo Xu, Jianwen Xie and Zirui Liu, "Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly", EMNLP 2025 Oral. PDF Code

• Tianyi Zhang, Junda Su, Aditya Desai, Oscar Wu, Zhaozhuo Xu and Anshumali Shrivastava, "Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation", ICML 2025. PDF

• Wentao Guo, Jikai Long, Yimeng Zeng, Zirui Liu, Xinyu Yang, Yide Ran, Jacob R. Gardner, Osbert Bastani, Christopher De Sa, Xiaodong Yu, Beidi Chen and Zhaozhuo Xu, "Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity", ICLR 2025. PDF

• Yanzhou Pan, Huawei Lin, Yide Ran, Jiamin Chen, Xiaodong Yu, Weijie Zhao, Denghui Zhang and Zhaozhuo Xu, "ALinFiK: Learning to Approximate Linearized Future Influence Kernel for Scalable Third-Party LLM Data Valuation", NAACL 2025 Oral. PDF

• Zhuang Wang*, Zhaozhuo Xu*, Jingyi Xi*, Yuke Wang, Anshumali Shrivastava and T. S. Eugene Ng, "ZEN: Empowering Distributed Training with Sparsity-driven Data Synchronization", OSDI 2025. PDF Code

• Huawei Lin, Jikai Long, Zhaozhuo Xu and Weijie Zhao, "Token-wise Influential Training Data Retrieval for Large Language Models", ACL 2024. PDF Code

• Jialiang Xu, Shenglan Li, Zhaozhuo Xu and Denghui Zhang, "Do LLMs Know to Respect Copyright Notice?", EMNLP 2024. PDF Code

• Junda Su, Zirui Liu, Zeju Qiu, Weiyang Liu and Zhaozhuo Xu, "In Defense of Structural Sparse Adapters for Concurrent LLM Serving", Findings of EMNLP 2024. PDF

• Jiayi Yuan, Hongyi Liu, Shaochen Zhong, Yu-Neng Chuang, Songchen Li, Guanchu Wang, Duy Le, Hongye Jin, Vipin Chaudhary, Zhaozhuo Xu, Zirui Liu and Xia Hu, "KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches", Findings of EMNLP 2024. PDF Code

• Shaochen Zhong, Duy Le, Zirui Liu, Zhimeng Jiang, Andrew Ye, Jiamu Zhang, Jiayi Yuan, Kaixiong Zhou, Zhaozhuo Xu, Jing Ma, Shuai Xu, Vipin Chaudhary and Xia Hu, "GNNs Also Deserve Editing, and They Need It More Than Once", ICML 2024. PDF Code

• Zirui Liu, Jiayi Yuan, Hongye Jin, Shaochen (Henry) Zhong, Zhaozhuo Xu, Vladimir Braverman, Beidi Chen, and Xia Hu, "KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache", ICML 2024. PDF Code

• Duy Le, Shaochen Zhong, Zirui Liu, Shuai Xu, Vipin Chaudhary, Kaixiong Zhou and Zhaozhuo Xu, "Knowledge Graphs Can be Learned with Just Intersection Features", ICML 2024. PDF

• Zhaozhuo Xu*, Zirui Liu*, Beidi Chen, Shaochen (Henry) Zhong, Yuxin Tang, Jue Wang, Kaixiong Zhou, Xia Hu and Anshumali Shrivastava, "Soft Prompt Recovers Compressed LLMs, Transferably", ICML 2024. PDF Code

• Guanchu Wang, Yu-Neng Chuang, Fan Yang, Mengnan Du, Chia-Yuan Chang, Shaochen Zhong, Zirui Liu, Zhaozhuo Xu, Kaixiong Zhou, Xuanting Cai and Xia Hu, "TVE: Learning Meta-attribution for Transferable Vision Explainer", ICML 2024. PDF Code

• Tianyi Zhang, Jonah Yi, Zhaozhuo Xu and Anshumali Shrivastava, "KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization", NeurIPS 2024. PDF

• Tianyi Zhang, Jonah Wonkyu Yi, Bowen Yao, Zhaozhuo Xu and Anshumali Shrivastava, "NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention", NeurIPS 2024. PDF Code

• Yang Zhou, Zhuoming Chen, Zhaozhuo Xu, Victoria Lin and Beidi Chen, "Sirius: Contextual Sparsity with Correction for Efficient LLMs", NeurIPS 2024. PDF Code

• Zhaozhuo Xu, Zhao Song and Anshumali Shrivastava, "A Tale of Two Efficient Value Iteration Algorithms for Solving Linear MDPs with Large Action Space", AISTATS 2023. PDF

• Zhuang Wang, Xinyu Wu, Zhaozhuo Xu and T. S. Eugene Ng, "Cupcake: A Compression Scheduler for Scalable Communication-Efficient Distributed Training", MLSys 2023. PDF

• Zichang Liu*, Zhaozhuo Xu*, Benjamin Coleman and Anshumali Shrivastava, "One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning", NeurIPS 2023. PDF

• Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis and Anshumali Shrivastava, "Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time", NeurIPS 2023. PDF

• Zirui Liu*, Guanchu Wang*, Shaochen Zhong, Zhaozhuo Xu, Daochen Zha, Ruixiang Tang, Zhimeng Jiang, Kaixiong Zhou, Vipin Chaudhary, Shuai Xu and Xia Hu, "Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model", NeurIPS 2023. PDF

• Tianyi Zhang, Zhenwei Dai, Zhaozhuo Xu and Anshumali Shrivastava, "Graph Self-supervised Learning via Proximity Divergence Minimization", UAI 2023. PDF Code

• Tianyi Zhang*, Zhaozhuo Xu*, Tharun Medini and Anshumali Shrivastava, "Structural Contrastive Representation Learning for Zero-shot Multi-label Text Classification", EMNLP Findings 2022. PDF Code

• Zhuang Wang*, Zhaozhuo Xu*, Xinyu Crystal Wu, Anshumali Shrivastava and T. S. Eugene Ng, "DRAGONN: Distributed Randomized Approximate Gradients of Neural Networks", ICML 2022. PDF

• Zichang Liu*, Zhaozhuo Xu*, Alan Ji, Junyan Zhang, Jonathan Li, Beidi Chen and Anshumali Shrivastava, "HALOS: Hashing Large Output Space for Cheap Inference", MLSys 2022. PDF

• Beidi Chen, Zichang Liu, Binghui Peng, Zhaozhuo Xu, Jonathan Lingjie Li, Tri Dao, Zhao Song, Anshumali Shrivastava and Christopher Re, "MONGOOSE: A Learnable LSH Framework for Efficient Neural Network Training", ICLR 2021 Oral. PDF Code

• Shulong Tan, Zhaozhuo Xu, Weijie Zhao, Hongliang Fei, Zhixin Zhou and Ping Li, "Norm Adjusted Proximity Graph for Fast Inner Product Retrieval", KDD 2021. PDF

• Zhaozhuo Xu, Zhao Song and Anshumali Shrivastava, "Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures", NeurIPS 2021. PDF

• Zhaozhuo Xu, Beidi Chen, Chaojian Li, Weiyang Liu, Le Song, Yingyan Lin and Anshumali Shrivastava, "Locality Sensitive Teaching", NeurIPS 2021. PDF Code

• Aditya Desai*, Zhaozhuo Xu*, Menal Gupta, Anu Chandran, Antoine Vial-Aussavy and Anshumali Shrivastava, "Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler", NeurIPS 2021. PDF

• Zhaozhuo Xu, Alan Baonan Ji, Andrew Woods, Beidi Chen and Anshumali Shrivastava, "Satellite Images and Deep Learning to Identify Discrepancy in Mailing Addresses with Applications to Census 2020 in Houston", JSM 2020. PDF

• Shulong Tan, Zhixin Zhou, Zhaozhuo Xu and Ping Li, "Fast Item Ranking under Neural Network based Measures", WSDM 2020. PDF

• Shulong Tan, Zhixin Zhou, Zhaozhuo Xu and Ping Li, "On Efficient Retrieval of Top Similarity Vectors", EMNLP 2019. PDF

• Zhixin Zhou, Shulong Tan, Zhaozhuo Xu and Ping Li, "Möbius Transformation for Fast Inner Product Search on Graph", NeurIPS 2019. PDF Code

Tutorial

• ICDM 2025: Behavior-Aware Data Valuation for LLMs at Scale. Link

• AAAI 2025: KV Cache Compression for Efficient Long Context LLM Inference: Challenges, Trade-Offs, and Opportunities. Link

• AAAI & NAACL 2025: LLMs and Copyright Risks: Benchmarks and Mitigation Approaches. Link

Honor

• AAAI-25 New Faculty Highlights. Link

• Ken Kennedy Institute BP Fellowship, 2021 - 2022. Link

Service

• Associate Editor: Neurocomputing

• Area Chair: NeurIPS, ICLR, ICML, ARR, EMNLP Main/Demo Track, NAACL, COLING

• Organizer: Research On Algorithms & Data Structures (ROADS) to Mega-AI Models Workshop, MLSys 2023. Link

• Organizer: VISTA: Visionary Innovation in Standards and Technology of GenAI workshop at ICDM 2025. Link

• Student Volunteer Co-Chairs: IEEE Big Data 2026. Link