Best AI papers explained

546 Episodes

1. Small Language Models are the Future of Agentic AI

   Published: 10/7/2025
2. Activation Steering in Generative Settings via Contrastive Causal Mediation Analysis

   Published: 10/6/2025
3. Eliciting Secret Knowledge from Language Models

   Published: 10/6/2025
4. Temporal difference flow

   Published: 10/6/2025
5. Personalized reasoning: just-in-time personalization and why LLMs fail at it

   Published: 10/5/2025
6. Prompt Curriculum Learning for Efficient LLM Post-Training

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 9/24/2025