Best AI papers explained

512 Episoade

1. Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

   Publicat: 11.10.2025
2. Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

   Publicat: 09.10.2025
3. Learning dynamics of LLM finetuning

   Publicat: 09.10.2025
4. Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF

   Publicat: 09.10.2025
5. OpenAI Agent Builder and n8n: Orchestrating Reasoning Versus Automating Process

   Publicat: 08.10.2025
6. Training Agents Inside of Scalable World Models

   Publicat: 08.10.2025
7. Small Language Models are the Future of Agentic AI

   Publicat: 07.10.2025
8. Activation Steering in Generative Settings via Contrastive Causal Mediation Analysis

   Publicat: 06.10.2025
9. Eliciting Secret Knowledge from Language Models

   Publicat: 06.10.2025
10. Temporal difference flow

    Publicat: 06.10.2025
11. Personalized reasoning: just-in-time personalization and why LLMs fail at it

    Publicat: 05.10.2025
12. Prompt Curriculum Learning for Efficient LLM Post-Training

    Publicat: 05.10.2025
13. Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning

    Publicat: 04.10.2025
14. Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward

    Publicat: 04.10.2025
15. Learning to summarize user information for personalized reinforcement learning from human feedback

    Publicat: 04.10.2025
16. Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF

    Publicat: 03.10.2025
17. LIMI: Less is More for Agency

    Publicat: 01.10.2025
18. LoRA Without Regret

    Publicat: 01.10.2025
19. Actor-Critic without Actor: Critic-Guided Denoising for RL

    Publicat: 29.09.2025
20. DELTA-Code: How Does RL Unlock and Transfer New Programming Algorithms in LLMs?

    Publicat: 29.09.2025