Best AI papers explained

523 Odcinki

1. Reinforcement Learning for Reasoning in Large Language Models with One Training Example

   Opublikowany: 27.05.2025
2. Test-Time Reinforcement Learning (TTRL)

   Opublikowany: 27.05.2025
3. Interpreting Emergent Planning in Model-Free Reinforcement Learning

   Opublikowany: 26.05.2025
4. Agentic Reward Modeling_Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems

   Opublikowany: 26.05.2025
5. Beyond Reward Hacking: Causal Rewards for Large LanguageModel Alignment

   Opublikowany: 26.05.2025
6. Learning How Hard to Think: Input-Adaptive Allocation of LM Computation

   Opublikowany: 26.05.2025
7. Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval

   Opublikowany: 26.05.2025
8. UFT: Unifying Supervised and Reinforcement Fine-Tuning

   Opublikowany: 26.05.2025
9. Understanding High-Dimensional Bayesian Optimization

   Opublikowany: 26.05.2025
10. Inference time alignment in continuous space

    Opublikowany: 25.05.2025
11. Efficient Test-Time Scaling via Self-Calibration

    Opublikowany: 25.05.2025
12. Conformal Prediction via Bayesian Quadrature

    Opublikowany: 25.05.2025
13. Predicting from Strings: Language Model Embeddings for Bayesian Optimization

    Opublikowany: 25.05.2025
14. Self-Evolving Curriculum for LLM Reasoning

    Opublikowany: 25.05.2025
15. Online Decision-Focused Learning in Dynamic Environments

    Opublikowany: 25.05.2025
16. FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain

    Opublikowany: 25.05.2025
17. Reward Shaping from Confounded Offline Data

    Opublikowany: 25.05.2025
18. Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning

    Opublikowany: 25.05.2025
19. Understanding Best-of-N Language Model Alignment

    Opublikowany: 25.05.2025
20. Maximizing Acquisition Functions for Bayesian Optimization - and its relation to Gradient Descent

    Opublikowany: 24.05.2025