Best AI papers explained

442 Episodes

1. Test-Time Reinforcement Learning (TTRL)

   Published: 5/27/2025
2. Interpreting Emergent Planning in Model-Free Reinforcement Learning

   Published: 5/26/2025
3. Agentic Reward Modeling_Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems

   Published: 5/26/2025
4. Beyond Reward Hacking: Causal Rewards for Large LanguageModel Alignment

   Published: 5/26/2025
5. Learning How Hard to Think: Input-Adaptive Allocation of LM Computation

   Published: 5/26/2025
6. Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval

   Published: 5/26/2025
7. UFT: Unifying Supervised and Reinforcement Fine-Tuning

   Published: 5/26/2025
8. Understanding High-Dimensional Bayesian Optimization

   Published: 5/26/2025
9. Inference time alignment in continuous space

   Published: 5/25/2025
10. Efficient Test-Time Scaling via Self-Calibration

    Published: 5/25/2025
11. Conformal Prediction via Bayesian Quadrature

    Published: 5/25/2025
12. Predicting from Strings: Language Model Embeddings for Bayesian Optimization

    Published: 5/25/2025
13. Self-Evolving Curriculum for LLM Reasoning

    Published: 5/25/2025
14. Online Decision-Focused Learning in Dynamic Environments

    Published: 5/25/2025
15. FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain

    Published: 5/25/2025
16. Reward Shaping from Confounded Offline Data

    Published: 5/25/2025
17. Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning

    Published: 5/25/2025
18. Understanding Best-of-N Language Model Alignment

    Published: 5/25/2025
19. Maximizing Acquisition Functions for Bayesian Optimization - and its relation to Gradient Descent

    Published: 5/24/2025
20. Bayesian Prompt Ensembles: Model Uncertainty Estimation for Black-Box Large Language Models

    Published: 5/24/2025