Best AI papers explained

437 Episodo

1. Statistics for Large Language Models

   Publicado: 29/5/2025
2. Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search

   Publicado: 29/5/2025
3. Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning

   Publicado: 29/5/2025
4. Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL

   Publicado: 29/5/2025
5. Value-Guided Search for Efficient Chain-of-Thought Reasoning

   Publicado: 29/5/2025
6. Shallow Preference Signals: Large Language model aligns even better without truncated data?

   Publicado: 29/5/2025
7. Gaming Tool Preferences in Agentic LLMs

   Publicado: 29/5/2025
8. Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)

   Publicado: 29/5/2025
9. LLM Populations Form Social Conventions and Collective Bias

   Publicado: 29/5/2025
10. LLM Generated Persona is a Promise with a Catch

    Publicado: 29/5/2025
11. Large Language Models for Digital Twin Simulation

    Publicado: 29/5/2025
12. From RL Distillation to Autonomous LLM Agents

    Publicado: 29/5/2025
13. Prompting, Auto-Prompting, and Human-AI Communication

    Publicado: 29/5/2025
14. Textual Gradients for LLM Optimization

    Publicado: 29/5/2025
15. Large Language Models as Markov Chains

    Publicado: 28/5/2025
16. Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation

    Publicado: 28/5/2025
17. Selective induction heads: how transformers select causal structures in context

    Publicado: 28/5/2025
18. The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains

    Publicado: 28/5/2025
19. How Transformers Learn Causal Structure with Gradient Descent

    Publicado: 28/5/2025
20. Planning anything with rigor: general-purpose zero-shot planning with llm-based formalized programming

    Publicado: 28/5/2025