MZ
Matei Zaharia
cs.AIcs.LGcs.CLcs.DBcs.DCcs.IRstat.MLcs.SEcs.CVcs.CR
On Valency
published · living versionsW_u7fa5rax·v1 · currentpublished
MLSys: The New Frontier of Machine Learning Systems
with Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen +64
1 version
Preprints & journals
140 papers in the corpus · 2009–2026Token Latency Fairness: Performance Isolation for Multi-Tenant LLM Serving2609.18112v1 · Dev Bali, Soujanya Ponnapalli, Yichuan Wang et al.2026 · 0 citationsarXiv
Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering2609.12039v1 · Alexander Krentsel, Shubham Agarwal, Mert Cemri et al.2026 · 0 citationsarXiv
RAG over Thinking Traces Can Improve Reasoning Tasks2605.03344v3 · Negar Arabzadeh, Wenjie Ma, Sewon Min et al.2026 · 0 citationsarXiv
What Happens When the Model Eats the Stack? Rethinking the Research Agenda for Data Agents to Withstand the Bitter Lesson2609.03141v1 · Liana Patel, Siddharth Jha, Negar Arabzadeh et al.2026 · 0 citationsarXiv
Novel Domain Knowledge-Encoding Algorithm Enables Label-Efficient Deep Learning for Cardiac CT Segmentation to Guide Atrial Fibrillation Treatment in a Pilot Dataset.39061675 · Ganesan, Prasanth, Feng, Ruibin, Deb, Brototo et al.2026 · 3 citationsDiagnostics (Basel, Switzerland). 2024;14(14)
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution2608.16157v1 · Shuo Yang, Xiaoze Fan, Melissa Pan et al.2026 · 0 citationsarXiv
Fantastic Adaptive Taxonomies and How to Use Them2607.16387v2 · Mert Cemri, Andrei Cojocaru, Melissa Pan et al.2026 · 0 citationsarXiv
Recursive Harness Self-Improvement2607.15524v1 · Hyunin Lee, Jinglue Xu, Jeffrey Seely et al.2026 · 0 citationsarXiv
PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation2606.28344v1 · Yichuan Wang, Zhifei Li, Zirui Wang et al.2026 · 0 citationsarXiv
RHO: Your Coding Agent is Secretly a Roboticist2606.16458v1 · Karim Elmaaroufi, Justin Svegliato, Sarunas Kalade et al.2026 · 0 citationsarXiv
Measuring Agents in Production2512.04123v4 · Melissa Z. Pan, Negar Arabzadeh, Riccardo Cogo et al.2025 · 3 citationsarXiv
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments2606.05661v1 · Parth Asawa, Christopher M. Glaze, Gabriel Orlanski et al.2026 · 0 citationsarXiv
The Price Reversal Phenomenon: When Cheaper Reasoning Models Cost More2603.23971v2 · Lingjiao Chen, Chi Zhang, Yeye He et al.2026 · 0 citationsarXiv
Natural Language Query to Configuration for Retrieval Agents2605.27361v1 · Melissa Z. Pan, Negar Arabzadeh, Mathew Jacob et al.2026 · 0 citationsarXiv
vAttention: Verified Sparse Attention2510.05688v2 · Aditya Desai, Kumar Krishna Agrawal, Shuo Yang et al.2025 · 0 citationsProceedings of the International Conference on Learning Representations (ICLR), 2026
The Time is Here for Just-in-Time Systems: Challenges and Opportunities2605.24096v1 · Shu Liu, Alexander Krentsel, Shubham Agarwal et al.2026 · 0 citationsarXiv
Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems2605.23109v1 · Shubham Agarwal, Alexander Krentsel, Shu Liu et al.2026 · 0 citationsarXiv
optimize_anything: A Universal API for Optimizing any Text Parameter2605.19633v1 · Lakshya A Agrawal, Donghyun Lee, Shangyin Tan et al.2026 · 1 citationProceedings of the ACM Conference on AI and Agentic Systems (CAIS 26), May 26-29, 2026, San Jose, CA, USA
How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models2510.02453v3 · Parth Asawa, Alan Zhu, Abigail O'Neill et al.2025 · 1 citationarXiv
Learning, Fast and Slow: Towards LLMs That Adapt Continually2605.12484v2 · Rishabh Tiwari, Kusha Sareen, Lakshya A Agrawal et al.2026 · 0 citationsarXiv
Composing Policy Gradients and Prompt Optimization for Language Model Programs2508.04660v2 · Noah Ziems, Dilara Soylu, Lakshya A Agrawal et al.2025 · 0 citationsarXiv
Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines2604.22661v1 · Negar Arabzadeh, Andrew Drozdov, Michael Bendersky et al.2026 · 0 citationsarXiv
Train Separately, Merge Together: Modular Post-Training with Mixture-of-Experts2604.18473v1 · Jacob Morrison, Sanjay Adhikesaven, Akshita Bhagia et al.2026 · 0 citationsarXiv
Identification of cardiac wall motion abnormalities in diverse populations by deep learning of the electrocardiogram.39799179 · Rogers, Albert J, Bhatia, Neal K, Bandyopadhyay, Sabyasachi et al.2026 · 8 citationsNPJ digital medicine. 2025;8(1):21
AI-Driven Research for Databases2604.06566v1 · Audrey Cheng, Harald Ng, Aaron Kabcenell et al.2026 · 0 citationsarXiv
SIEVE: Sample-Efficient Parametric Learning from Natural Language2604.02339v1 · Parth Asawa, Alexandros G. Dimakis, Matei Zaharia2026 · 0 citationsarXiv
EvoX: Meta-Evolution for Automated Discovery2602.23413v2 · Shu Liu, Shubham Agarwal, Monishwaran Maheswaran et al.2026 · 1 citationarXiv
OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning2603.08655v1 · Krista Opsahl-Ong, Arnav Singhvi, Jasmine Collins et al.2026 · 0 citationsarXiv
DS SERVE: A Framework for Efficient and Scalable Neural Retrieval2602.22224v1 · Jinjian Liu, Yichuan Wang, Xinxi Lyu et al.2025 · 0 citationsarXiv
vCache: Verified Semantic Prompt Caching2502.03771v5 · Luis Gaspar Schroeder, Aditya Desai, Alejandro Cuadron et al.2025 · 0 citationsarXiv
AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization2602.20133v1 · Mert Cemri, Shubham Agrawal, Akshat Gupta et al.2026 · 2 citationsarXiv
Delta Fair Sharing: Performance Isolation for Multi-Tenant Storage Systems2601.20030v1 · Tyler Griggs, Soujanya Ponnapalli, Dev Bali et al.2026 · 0 citationsarXiv
Let the Barbarians In: How AI Can Accelerate Systems Performance Research2512.14806v4 · Audrey Cheng, Shu Liu, Melissa Pan et al.2025 · 0 citationsarXiv
Supporting Our AI Overlords: Redesigning Data Systems to be Agent-First2509.00997v2 · Shu Liu, Soujanya Ponnapalli, Shreya Shankar et al.2025 · 2 citationsarXiv
LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess2512.01992v1 · Sai Kolasani, Maxim Saplin, Nicholas Crispino et al.2025 · 0 citationsarXiv
LEANN: A Low-Storage Vector Index2506.08276v2 · Yichuan Wang, Zhifei Li, Shu Liu et al.2025 · 0 citationsarXiv
SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent2511.16108v1 · Shiyi Cao, Dacheng Li, Fangzhou Zhao et al.2025 · 0 citationsarXiv
Why Do Multi-Agent LLM Systems Fail?2503.13657v3 · Mert Cemri, Melissa Z. Pan, Shuyi Yang et al.2025 · 44 citationsarXiv
Barbarians at the Gate: How AI is Upending Systems Research2510.06189v3 · Audrey Cheng, Shu Liu, Melissa Pan et al.2025 · 1 citationarXiv
Image and Data Mining in Reticular Chemistry Using GPT-4V2312.05468v1 · Zhiling Zheng, Zhiguo He, Omar Khattab et al.2023 · 68 citationsDigital Discovery, 2024,3, 491-501
Alto: Orchestrating Distributed Compound AI Systems with Nested Ancestry2403.04311v3 · Deepti Raghavan, Keshav Santhanam, Muhammad Shahir Rahman et al.2024 · 0 citationsarXiv
Drowning in Documents: Consequences of Scaling Reranker Inference2411.11767v2 · Mathew Jacob, Erik Lindgren, Matei Zaharia et al.2024 · 1 citationarXiv
WARP: An Efficient Engine for Multi-Vector Retrieval2501.17788v3 · Jan Luca Scheerer, Matei Zaharia, Christopher Potts et al.2025 · 8 citationsarXiv
HashAttention: Semantic Sparsity for Faster Inference2412.14468v2 · Aditya Desai, Shuo Yang, Alejandro Cuadron et al.2024 · 1 citationarXiv
BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation2502.01697v3 · Alan Zhu, Parth Asawa, Jared Quincy Davis et al.2025 · 0 citationsarXiv
ColBERT-serve: Efficient Multi-Stage Memory-Mapped Scoring2504.14903v1 · Kaili Huang, Thejas Venkatesh, Uma Dingankar et al.2025 · 3 citationsarXiv
The Cambridge Report on Database Research2504.11259v1 · Anastasia Ailamaki, Samuel Madden, Daniel Abadi et al.2025 · 3 citationsarXiv
Reasoning Models Can Be Effective Without Thinking2504.09858v1 · Wenjie Ma, Jingxuan He, Charlie Snell et al.2025 · 0 citationsarXiv
Optimizing LLM Queries in Relational Data Analytics Workloads2403.05821v2 · Shu Liu, Asim Biswal, Amog Kamsetty et al.2024 · 6 citationsarXiv
LangProBe: a Language Programs Benchmark2502.20315v1 · Shangyin Tan, Lakshya A Agrawal, Arnav Singhvi et al.2025 · 0 citationsarXiv
Career total: 359 works. 140 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.