🏢 UC Berkeley

LLM-based text embeddings are powerful but lack interpretability. This paper introduces QA-Emb, a novel method that uses an LLM to answer yes/no questions about a text, thereby producing an interpreta…

LLMs surprisingly infer censored knowledge from implicit training data hints, posing safety challenges.

This paper presents efficient algorithms for Bayesian persuasion under approximate best response, offering polynomial-time solutions for specific cases and a quasi-polynomial-time approximation scheme…

Goal-conditioned RL gets a temporal upgrade with compositional DFAs (cDFAs), enabling zero-shot generalization and faster policy specialization via novel graph neural network embeddings and reach-avoi…

A novel model reveals how hippocampal-entorhinal circuits use compositional coding and modular attractor networks to enable robust and flexible spatial representation, advancing our understanding of c…

Language models (LMs) can now forecast future events as accurately as expert human forecasters! This groundbreaking research unveils a retrieval-augmented LM system surpassing human forecasters in spe…

Researchers developed an active learning method using two-photon holographic optogenetics to efficiently identify neural population dynamics, achieving up to a two-fold reduction in data needed for ac…