Best AI papers explained

535 Episodes

1. The Era of Agentic Organization: Learning to Organize with Language Models

   Published: 15/11/2025
2. Understanding neural networks through sparse circuits

   Published: 14/11/2025
3. Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

   Published: 14/11/2025
4. Multi-Agent Evolve: LLM Self-Improvement Through Co-Evolution

   Published: 14/11/2025
5. LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics

   Published: 14/11/2025
6. PREFDISCO: Evaluating Proactive Personalization through Interactive Preference Discovery

   Published: 12/11/2025
7. Reusing pre-training data at test time is a compute multiplier

   Published: 10/11/2025
8. Scaling Agent Learning via Experience Synthesis

   Published: 9/11/2025
9. Continuous Autoregressive Language Models

   Published: 8/11/2025
10. Toward a Theory of Agents as Tool-Use Decision-Makers

    Published: 7/11/2025
11. Nested Learning: The Illusion of Deep Learning Architectures

    Published: 5/11/2025
12. GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

    Published: 5/11/2025
13. Beyond a million tokens: benchmarking and enhancing long-term memory in llms

    Published: 4/11/2025
14. Agentic Economic Modeling

    Published: 3/11/2025
15. Emergent Introspective Awareness in Large Language Models

    Published: 3/11/2025
16. Can Large reasoning models self-train?

    Published: 1/11/2025
17. ALITA-G: Self-Evolving Generative Agent for Agent Generation

    Published: 1/11/2025
18. Self-improving LLM agents at test-time

    Published: 30/10/2025
19. Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

    Published: 30/10/2025
20. Language models are injective and hence invertible

    Published: 30/10/2025