Best AI papers explained

A podcast by Enoch H. Kang

527 Episoade

Predictability Shapes Adaptation: An Evolutionary Perspective on Modes of Learning in Transformers
Publicat: 20.05.2025
Efficient Exploration for LLMs
Publicat: 19.05.2025
Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation
Publicat: 18.05.2025
Bayesian Concept Bottlenecks with LLM Priors
Publicat: 17.05.2025
Transformers for In-Context Reinforcement Learning
Publicat: 17.05.2025
Evaluating Large Language Models Across the Lifecycle
Publicat: 17.05.2025
Active Ranking from Human Feedback with DopeWolfe
Publicat: 16.05.2025
Optimal Designs for Preference Elicitation
Publicat: 16.05.2025
Dual Active Learning for Reinforcement Learning from Human Feedback
Publicat: 16.05.2025
Active Learning for Direct Preference Optimization
Publicat: 16.05.2025
Active Preference Optimization for RLHF
Publicat: 16.05.2025
Test-Time Alignment of Diffusion Models without reward over-optimization
Publicat: 16.05.2025
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback
Publicat: 16.05.2025
GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment
Publicat: 16.05.2025
Advantage-Weighted Regression: Simple and Scalable Off-Policy RL
Publicat: 16.05.2025
Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective
Publicat: 16.05.2025
Transformers can be used for in-context linear regression in the presence of endogeneity
Publicat: 15.05.2025
Bayesian Concept Bottlenecks with LLM Priors
Publicat: 15.05.2025
In-Context Parametric Inference: Point or Distribution Estimators?
Publicat: 15.05.2025
Enough Coin Flips Can Make LLMs Act Bayesian
Publicat: 15.05.2025

17 / 27

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

Visit the podcast's native language site

527 Episoade

Predictability Shapes Adaptation: An Evolutionary Perspective on Modes of Learning in Transformers

Efficient Exploration for LLMs

Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation

Bayesian Concept Bottlenecks with LLM Priors

Transformers for In-Context Reinforcement Learning

Evaluating Large Language Models Across the Lifecycle

Active Ranking from Human Feedback with DopeWolfe

Optimal Designs for Preference Elicitation

Dual Active Learning for Reinforcement Learning from Human Feedback

Active Learning for Direct Preference Optimization

Active Preference Optimization for RLHF

Test-Time Alignment of Diffusion Models without reward over-optimization

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment

Advantage-Weighted Regression: Simple and Scalable Off-Policy RL

Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective

Transformers can be used for in-context linear regression in the presence of endogeneity

Bayesian Concept Bottlenecks with LLM Priors

In-Context Parametric Inference: Point or Distribution Estimators?

Enough Coin Flips Can Make LLMs Act Bayesian