Linear Representations of Sentiment in Large Language Models

Quality-Diversity through AI Feedback

PsyArXiv Preprints | A Psychological Model Predicts Fears about Artificial Intelligence across 20 Countries and 6 Domains of Application

AI Adoption in America: Who, What, and Where

Towards Understanding Sycophancy in Language Models

Managing AI Risks in an Era of Rapid Progress

🥇Top ML Papers of the Week

3D-GPT: Procedural 3D Modeling with Large Language Models

A taxonomy and review of generalization research in NLP

DEEP-squared: deep learning powered De-scattering with Excitation Patterning

Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution (Paper Explained)

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models

Llemma: An Open Language Model For Mathematics

Efficient Streaming Language Models with Attention Sinks (Paper Explained)

Millimeter-sized battery-free epidural cortical stimulators

🥇Top ML Papers of the Week

Large Language Models can Learn Rules

A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics

Learning Interactive Real-World Simulators

Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading

Large Language Models Cannot Self-Correct Reasoning Yet

The second law of infodynamics and its implications for the simulated universe hypothesis

Enable Language Models to Implicitly Learn Self-Improvement From Data

PFGM++: Unlocking the Potential of Physics-Inspired Generative Models

AWAreness during REsuscitation - II: A multi-center study of consciousness and awareness in cardiac arrest

Human Feedback is not Gold Standard

Borges and AI

Language Models Represent Space and Time

Efficient automatic design of robots