From memories to maps: Mechanisms of in context reinforcement learning in transformers11просмотров10 месяцев назад
What Non-Content Perturbations Reveal About Human and Clinical LLM Decision8просмотров10 месяцев назад
Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework7просмотров10 месяцев назад
LiveCodeBench Pro: How Do Olympiad MedalistsJudge LLMs in Competitive Programming?10просмотровгод назад
The Diffusion Duality: Bridging Continuous and Discrete Diffusion for Faster Text Generation13просмотровгод назад
Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing T10просмотровгод назад
