Best AI papers explained
A podcast by Enoch H. Kang
550 Episodio
-
Past-Token Prediction for Long-Context Robot Policies
Pubblicato: 20/05/2025 -
Recovering Coherent Event Probabilities from LLM Embeddings
Pubblicato: 20/05/2025 -
Systematic Meta-Abilities Alignment in Large Reasoning Models
Pubblicato: 20/05/2025 -
Predictability Shapes Adaptation: An Evolutionary Perspective on Modes of Learning in Transformers
Pubblicato: 20/05/2025 -
Efficient Exploration for LLMs
Pubblicato: 19/05/2025 -
Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation
Pubblicato: 18/05/2025 -
Bayesian Concept Bottlenecks with LLM Priors
Pubblicato: 17/05/2025 -
Transformers for In-Context Reinforcement Learning
Pubblicato: 17/05/2025 -
Evaluating Large Language Models Across the Lifecycle
Pubblicato: 17/05/2025 -
Active Ranking from Human Feedback with DopeWolfe
Pubblicato: 16/05/2025 -
Optimal Designs for Preference Elicitation
Pubblicato: 16/05/2025 -
Dual Active Learning for Reinforcement Learning from Human Feedback
Pubblicato: 16/05/2025 -
Active Learning for Direct Preference Optimization
Pubblicato: 16/05/2025 -
Active Preference Optimization for RLHF
Pubblicato: 16/05/2025 -
Test-Time Alignment of Diffusion Models without reward over-optimization
Pubblicato: 16/05/2025 -
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
Pubblicato: 16/05/2025 -
GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment
Pubblicato: 16/05/2025 -
Advantage-Weighted Regression: Simple and Scalable Off-Policy RL
Pubblicato: 16/05/2025 -
Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
Pubblicato: 16/05/2025 -
Transformers can be used for in-context linear regression in the presence of endogeneity
Pubblicato: 15/05/2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
