Apple Researchers Release CLaRa: A Continuous Latent Reasoning Framework for Compression‑Native RAG with 16x–128x Semantic Document Compression

Apple Researchers Release CLaRa: A Continuous Latent Reasoning Framework for Compression‑Native RAG with 16x–128x Semantic Document Compression

⋅

How do you keep RAG systems accurate and efficient when every query tries to stuff thousands of tokens into the context window and the retriever and generator are still optimized as 2 separate, disconnected systems? A team of researchers from Apple and University of Edinburgh released CLaRa, Continuous Latent Reasoning, (CLaRa-7B-Base, CLaRa-7B-Instruct and CLaRa-7B-E2E) a retrieval augmented generation framework that compresses documents into continuous memory tokens and then performs both retrieval and generation in that shared latent space. […]

Ver mais

Liked Liked
New algorithms enable efficient machine learning with symmetric data

New algorithms enable efficient machine learning with symmetric data

⋅

If you rotate an image of a molecular structure, a human can tell the rotated image is still the same molecule, but a machine-learning model might think it is a new data point. In computer science parlance, the molecule is “symmetric,” meaning the fundamental structure of that molecule remains the same if it undergoes certain transformations, like rotation. If a drug discovery model doesn’t understand symmetry, it could make inaccurate predictions about molecular properties. But despite some empirical […]

Ver mais

Liked Liked

Load More

↑

Digitado © 2025