Best AI papers explained

550 Episodes

1. Learning dynamics of LLM finetuning

   Published: 10/9/2025
2. Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF

   Published: 10/9/2025
3. OpenAI Agent Builder and n8n: Orchestrating Reasoning Versus Automating Process

   Published: 10/8/2025
4. Training Agents Inside of Scalable World Models

   Published: 10/8/2025
5. Small Language Models are the Future of Agentic AI

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 9/27/2025