Best AI papers explained

506 Episodes

1. Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model

   Published: 24/09/2025
2. Open Problems in Mechanistic Interpretability

   Published: 21/09/2025
3. Maestro: Joint Graph & Config Optimization for Reliable AI Agents

   Published: 21/09/2025
4. Thought Anchors: Which LLM Reasoning Steps Matter?

   Published: 21/09/2025
5. Sample Complexity and Representation Ability of Test-time Scaling Paradigms

   Published: 09/09/2025
6. RL's Razor: Why Online RL Forgets Less

   Published: 07/09/2025
7. Why Language Models Hallucinate

   Published: 06/09/2025
8. ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning

   Published: 06/09/2025
9. Sample Efficient Preference Alignment in LLMs via Active Exploration

   Published: 06/09/2025
10. Adventures in Demand Analysis Using AI

    Published: 04/09/2025
11. Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

    Published: 01/09/2025
12. On the Theoretical Limitations of Embedding-Based Retrieval

    Published: 31/08/2025
13. Performance Prediction for Large Systems via Text-to-Text Regression

    Published: 30/08/2025
14. Demystifying the Visual Quality Paradox in Multimodal Large Language Models

    Published: 30/08/2025
15. Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

    Published: 30/08/2025
16. Compute-Optimal Scaling for Value-Based Deep RL

    Published: 25/08/2025
17. LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experience

    Published: 23/08/2025
18. Signal and Noise: Evaluating Language Model Benchmarks

    Published: 23/08/2025
19. Breaking Feedback Loops in Recommender Systems with Causal Inference

    Published: 21/08/2025
20. RAG is Dead, Context Engineering is King: Building Reliable AI Systems

    Published: 20/08/2025