Best AI papers explained

523 Odcinki

1. No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference

   Opublikowany: 31.05.2025
2. Accelerating RL for LLM Reasoning with Optimal Advantage Regression

   Opublikowany: 31.05.2025
3. Statistical Inference for Online Algorithms

   Opublikowany: 31.05.2025
4. Prismatic Synthesis for Diverse LLM Reasoning Data

   Opublikowany: 31.05.2025
5. Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents

   Opublikowany: 31.05.2025
6. The Agentic Economy

   Opublikowany: 30.05.2025
7. Statistics for Large Language Models

   Opublikowany: 29.05.2025
8. Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search

   Opublikowany: 29.05.2025
9. Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning

   Opublikowany: 29.05.2025
10. Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL

    Opublikowany: 29.05.2025
11. Value-Guided Search for Efficient Chain-of-Thought Reasoning

    Opublikowany: 29.05.2025
12. Shallow Preference Signals: Large Language model aligns even better without truncated data?

    Opublikowany: 29.05.2025
13. Gaming Tool Preferences in Agentic LLMs

    Opublikowany: 29.05.2025
14. Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)

    Opublikowany: 29.05.2025
15. LLM Populations Form Social Conventions and Collective Bias

    Opublikowany: 29.05.2025
16. LLM Generated Persona is a Promise with a Catch

    Opublikowany: 29.05.2025
17. Large Language Models for Digital Twin Simulation

    Opublikowany: 29.05.2025
18. From RL Distillation to Autonomous LLM Agents

    Opublikowany: 29.05.2025
19. Prompting, Auto-Prompting, and Human-AI Communication

    Opublikowany: 29.05.2025
20. Textual Gradients for LLM Optimization

    Opublikowany: 29.05.2025