Best AI papers explained

481 Episodes

1. Prompt Curriculum Learning for Efficient LLM Post-Training

   Published: 10/5/2025
2. Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning

   Published: 10/4/2025
3. Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward

   Published: 10/4/2025
4. Learning to summarize user information for personalized reinforcement learning from human feedback

   Published: 10/4/2025
5. Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF

   Published: 10/3/2025
6. LIMI: Less is More for Agency

   Published: 10/1/2025
7. LoRA Without Regret

   Published: 10/1/2025
8. Actor-Critic without Actor: Critic-Guided Denoising for RL

   Published: 9/29/2025
9. DELTA-Code: How Does RL Unlock and Transfer New Programming Algorithms in LLMs?

   Published: 9/29/2025
10. Linear Transformers Implicitly Discover Unified Numerical Algorithms

    Published: 9/29/2025
11. Regularizing Extrapolation in Causal Inference

    Published: 9/27/2025
12. DoubleGen - Debiased Generative Modeling of Counterfactuals

    Published: 9/27/2025
13. What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

    Published: 9/27/2025
14. Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision

    Published: 9/27/2025
15. Learning without training: The implicit dynamics of in-context learning

    Published: 9/24/2025
16. Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model

    Published: 9/24/2025
17. Open Problems in Mechanistic Interpretability

    Published: 9/21/2025
18. Maestro: Joint Graph & Config Optimization for Reliable AI Agents

    Published: 9/21/2025
19. Thought Anchors: Which LLM Reasoning Steps Matter?

    Published: 9/21/2025
20. Sample Complexity and Representation Ability of Test-time Scaling Paradigms

    Published: 9/9/2025