Best AI papers explained

441 Episodes

1. RL's Razor: Why Online RL Forgets Less

   Published: 9/7/2025
2. Why Language Models Hallucinate

   Published: 9/6/2025
3. ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning

   Published: 9/6/2025
4. Sample Efficient Preference Alignment in LLMs via Active Exploration

   Published: 9/6/2025
5. Adventures in Demand Analysis Using AI

   Published: 9/4/2025
6. Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

   Published: 9/1/2025
7. On the Theoretical Limitations of Embedding-Based Retrieval

   Published: 8/31/2025
8. Performance Prediction for Large Systems via Text-to-Text Regression

   Published: 8/30/2025
9. Demystifying the Visual Quality Paradox in Multimodal Large Language Models

   Published: 8/30/2025
10. Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

    Published: 8/30/2025
11. Compute-Optimal Scaling for Value-Based Deep RL

    Published: 8/25/2025
12. LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experience

    Published: 8/23/2025
13. Signal and Noise: Evaluating Language Model Benchmarks

    Published: 8/23/2025
14. Breaking Feedback Loops in Recommender Systems with Causal Inference

    Published: 8/21/2025
15. RAG is Dead, Context Engineering is King: Building Reliable AI Systems

    Published: 8/20/2025
16. A Survey of Personalization: From RAG to Agent

    Published: 8/20/2025
17. Facilitating the Adoption of Causal Infer-ence Methods Through LLM-Empowered Co-Pilot

    Published: 8/19/2025
18. Performance Prediction for Large Systems via Text-to-Text Regression

    Published: 8/16/2025
19. Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning

    Published: 8/15/2025
20. DINOv3: Vision Models for Self-Supervised Learning

    Published: 8/15/2025