Best AI papers explained

456 Episodes

1. ShiQ: Bringing back Bellman to LLMs

   Published: 5/22/2025
2. Policy Learning with a Natural Language Action Space: A Causal Approach

   Published: 5/22/2025
3. Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models

   Published: 5/22/2025
4. End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

   Published: 5/21/2025
5. TEXTGRAD: Automatic Differentiation via Text

   Published: 5/21/2025
6. Steering off Course: Reliability Challenges in Steering Language Models

   Published: 5/20/2025
7. Past-Token Prediction for Long-Context Robot Policies

   Published: 5/20/2025
8. Recovering Coherent Event Probabilities from LLM Embeddings

   Published: 5/20/2025
9. Systematic Meta-Abilities Alignment in Large Reasoning Models

   Published: 5/20/2025
10. Predictability Shapes Adaptation: An Evolutionary Perspective on Modes of Learning in Transformers

    Published: 5/20/2025
11. Efficient Exploration for LLMs

    Published: 5/19/2025
12. Rankers, Judges, and Assistants: Towards Understanding the Interplay of LLMs in Information Retrieval Evaluation

    Published: 5/18/2025
13. Bayesian Concept Bottlenecks with LLM Priors

    Published: 5/17/2025
14. Transformers for In-Context Reinforcement Learning

    Published: 5/17/2025
15. Evaluating Large Language Models Across the Lifecycle

    Published: 5/17/2025
16. Active Ranking from Human Feedback with DopeWolfe

    Published: 5/16/2025
17. Optimal Designs for Preference Elicitation

    Published: 5/16/2025
18. Dual Active Learning for Reinforcement Learning from Human Feedback

    Published: 5/16/2025
19. Active Learning for Direct Preference Optimization

    Published: 5/16/2025
20. Active Preference Optimization for RLHF

    Published: 5/16/2025