Best AI papers explained

515 Episodes

1. Understanding Prompt Tuning and In-Context Learning via Meta-Learning

   Published: 11/10/2025
2. MLPs Learn In-Context on Regression and Classification tasks

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Published: 1/10/2025