Best AI papers explained

534 Episodes

1. MLPs Learn In-Context on Regression and Classification tasks

   Published: 10/11/2025
2. Is Pre-Training Truly Better than Meta-Learning?

   Published: 10/11/2025
3. Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

   Published: 10/11/2025
4. Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

   Published: 10/9/2025
5. Learning dynamics of LLM finetuning

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 10/1/2025