Matei Zaharia
3 papers · Latest:
Machine Learning
Learning, Fast and Slow: Towards LLMs That Adapt Continually
Fast-Slow Training enables LLMs to adapt continually with improved efficiency and less forgetting by combining fast context and slow parameter updates.
2605.12484
Information RetrievalRAG over Thinking Traces Can Improve Reasoning Tasks
This paper shows that using "thinking traces" as a retrieval corpus significantly enhances RAG performance on complex reasoning tasks like math and code.
2605.03344
Information RetrievalCan QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines
This paper evaluates Query Performance Prediction (QPP) for selecting optimal query variants in RAG pipelines, revealing a "utility gap" between retrieval and generation.
2604.22661
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.