Best AI papers explained

441 Episodes

1. Statistical Inference for Online Algorithms

   Published: 5/31/2025
2. Prismatic Synthesis for Diverse LLM Reasoning Data

   Published: 5/31/2025
3. Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents

   Published: 5/31/2025
4. The Agentic Economy

   Published: 5/30/2025
5. Statistics for Large Language Models

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

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

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

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

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

    Published: 5/29/2025
11. Gaming Tool Preferences in Agentic LLMs

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

    Published: 5/29/2025
13. LLM Populations Form Social Conventions and Collective Bias

    Published: 5/29/2025
14. LLM Generated Persona is a Promise with a Catch

    Published: 5/29/2025
15. Large Language Models for Digital Twin Simulation

    Published: 5/29/2025
16. From RL Distillation to Autonomous LLM Agents

    Published: 5/29/2025
17. Prompting, Auto-Prompting, and Human-AI Communication

    Published: 5/29/2025
18. Textual Gradients for LLM Optimization

    Published: 5/29/2025
19. Large Language Models as Markov Chains

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

    Published: 5/28/2025