Best AI papers explained

430 Episoder

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

   Publisert: 23.8.2025
2. Signal and Noise: Evaluating Language Model Benchmarks

   Publisert: 23.8.2025
3. Breaking Feedback Loops in Recommender Systems with Causal Inference

   Publisert: 21.8.2025
4. RAG is Dead, Context Engineering is King: Building Reliable AI Systems

   Publisert: 20.8.2025
5. A Survey of Personalization: From RAG to Agent

   Publisert: 20.8.2025
6. Facilitating the Adoption of Causal Infer-ence Methods Through LLM-Empowered Co-Pilot

   Publisert: 19.8.2025
7. Performance Prediction for Large Systems via Text-to-Text Regression

   Publisert: 16.8.2025
8. Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning

   Publisert: 15.8.2025
9. DINOv3: Vision Models for Self-Supervised Learning

   Publisert: 15.8.2025
10. Agent Lightning: Training Any AI Agents with Reinforcement Learning

    Publisert: 14.8.2025
11. Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier

    Publisert: 14.8.2025
12. From Model Weights to Agent Workflows: Charting the New Frontier of Optimization in Large Language Models

    Publisert: 12.8.2025
13. Is Chain-of-Thought Reasoning a Mirage?

    Publisert: 12.8.2025
14. Agentic Web: Weaving the Next Web with AI Agents

    Publisert: 11.8.2025
15. The Assimilation-Accommodation Gap in LLM Intelligence

    Publisert: 10.8.2025
16. The Minimalist AI Kernel: A New Frontier in Reasoning

    Publisert: 6.8.2025
17. Statistical Rigor for Interpretable AI

    Publisert: 6.8.2025
18. Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value

    Publisert: 4.8.2025
19. A foundation model to predict and capture human cognition

    Publisert: 4.8.2025
20. Generative Recommendation with Semantic IDs: A Practitioner’s Handbook

    Publisert: 4.8.2025