Matei Zaharia

DS SERVE: A Framework for Efficient and Scalable Neural Retrieval AAAI 2026 WriteGuards: Distributed Storage Support for Strongly Consistent Caches OSDI 2026 Compass: Encrypted Semantic Search with High Accuracy OSDI 2025 ElasticTok: Adaptive Tokenization for Image and Video ICLR 2025 HashAttention: Semantic Sparsity for Faster Inference ICML 2025 LangProBe: a Language Program Benchmark EMNLP 2025 Language Models Can Easily Learn to Reason from Demonstrations EMNLP 2025 World Model on Million-Length Video And Language With Blockwise RingAttention ICLR 2025 Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems NeurIPS 2024 ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems NAACL 2024 DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines ICLR 2024 Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs EMNLP 2024 RingAttention with Blockwise Transformers for Near-Infinite Context ICLR 2024 HAPI Explorer: Comprehension, Discovery, and Explanation on History of ML APIs AAAI 2023 Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking ACL 2023 ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction NAACL 2022 Data-Parallel Actors: A Programming Model for Scalable Query Serving Systems NSDI 2022 Efficient Online ML API Selection for Multi-Label Classification Tasks ICML 2022 Estimating and Explaining Model Performance When Both Covariates and Labels Shift NeurIPS 2022 HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions NeurIPS 2022 Hindsight: Posterior-guided training of retrievers for improved open-ended generation ICLR 2022 How Did the Model Change? Efficiently Assessing Machine Learning API Shifts ICLR 2022 Similarity Search for Efficient Active Learning and Search of Rare Concepts AAAI 2022 Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval NeurIPS 2021 Contracting Wide-area Network Topologies to Solve Flow Problems Quickly NSDI 2021 Memory-Efficient Pipeline-Parallel DNN Training ICML 2021 FrugalML: How to use ML Prediction APIs more accurately and cheaply NeurIPS 2020 Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads OSDI 2020 Selection via Proxy: Efficient Data Selection for Deep Learning ICLR 2020 LIT: Learned Intermediate Representation Training for Model Compression ICML 2019 Splinter: Practical Private Queries on Public Data NSDI 2017 FairRide: Near-Optimal, Fair Cache Sharing NSDI 2016 MLlib: Machine Learning in Apache Spark JMLR 2016 Yggdrasil: An Optimized System for Training Deep Decision Trees at Scale NeurIPS 2016 Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing NSDI 2012