Best AI papers explained

471 Avsnitt

1. Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

   Publicerades: 2025-10-09
2. Learning dynamics of LLM finetuning

   Publicerades: 2025-10-09
3. Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF

   Publicerades: 2025-10-09
4. OpenAI Agent Builder and n8n: Orchestrating Reasoning Versus Automating Process

   Publicerades: 2025-10-08
5. Training Agents Inside of Scalable World Models

   Publicerades: 2025-10-08
6. Small Language Models are the Future of Agentic AI

   Publicerades: 2025-10-07
7. Activation Steering in Generative Settings via Contrastive Causal Mediation Analysis

   Publicerades: 2025-10-06
8. Eliciting Secret Knowledge from Language Models

   Publicerades: 2025-10-06
9. Temporal difference flow

   Publicerades: 2025-10-06
10. Personalized reasoning: just-in-time personalization and why LLMs fail at it

    Publicerades: 2025-10-05
11. Prompt Curriculum Learning for Efficient LLM Post-Training

    Publicerades: 2025-10-05
12. Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning

    Publicerades: 2025-10-04
13. Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward

    Publicerades: 2025-10-04
14. Learning to summarize user information for personalized reinforcement learning from human feedback

    Publicerades: 2025-10-04
15. Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF

    Publicerades: 2025-10-03
16. LIMI: Less is More for Agency

    Publicerades: 2025-10-01
17. LoRA Without Regret

    Publicerades: 2025-10-01
18. Actor-Critic without Actor: Critic-Guided Denoising for RL

    Publicerades: 2025-09-29
19. DELTA-Code: How Does RL Unlock and Transfer New Programming Algorithms in LLMs?

    Publicerades: 2025-09-29
20. Linear Transformers Implicitly Discover Unified Numerical Algorithms

    Publicerades: 2025-09-29