550 Epizód

  1. LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experience

    Közzétéve: 2025. 08. 23.
  2. Signal and Noise: Evaluating Language Model Benchmarks

    Közzétéve: 2025. 08. 23.
  3. Breaking Feedback Loops in Recommender Systems with Causal Inference

    Közzétéve: 2025. 08. 21.
  4. RAG is Dead, Context Engineering is King: Building Reliable AI Systems

    Közzétéve: 2025. 08. 20.
  5. A Survey of Personalization: From RAG to Agent

    Közzétéve: 2025. 08. 20.
  6. Facilitating the Adoption of Causal Infer-ence Methods Through LLM-Empowered Co-Pilot

    Közzétéve: 2025. 08. 19.
  7. Performance Prediction for Large Systems via Text-to-Text Regression

    Közzétéve: 2025. 08. 16.
  8. Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning

    Közzétéve: 2025. 08. 15.
  9. DINOv3: Vision Models for Self-Supervised Learning

    Közzétéve: 2025. 08. 15.
  10. Agent Lightning: Training Any AI Agents with Reinforcement Learning

    Közzétéve: 2025. 08. 14.
  11. Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier

    Közzétéve: 2025. 08. 14.
  12. From Model Weights to Agent Workflows: Charting the New Frontier of Optimization in Large Language Models

    Közzétéve: 2025. 08. 12.
  13. Is Chain-of-Thought Reasoning a Mirage?

    Közzétéve: 2025. 08. 12.
  14. Agentic Web: Weaving the Next Web with AI Agents

    Közzétéve: 2025. 08. 11.
  15. The Assimilation-Accommodation Gap in LLM Intelligence

    Közzétéve: 2025. 08. 10.
  16. The Minimalist AI Kernel: A New Frontier in Reasoning

    Közzétéve: 2025. 08. 06.
  17. Statistical Rigor for Interpretable AI

    Közzétéve: 2025. 08. 06.
  18. Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value

    Közzétéve: 2025. 08. 04.
  19. A foundation model to predict and capture human cognition

    Közzétéve: 2025. 08. 04.
  20. Generative Recommendation with Semantic IDs: A Practitioner’s Handbook

    Közzétéve: 2025. 08. 04.

7 / 28

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

Visit the podcast's native language site