Best AI papers explained

437 Afleveringen

1. Adventures in Demand Analysis Using AI

   Gepubliceerd: 4-9-2025
2. Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

   Gepubliceerd: 1-9-2025
3. On the Theoretical Limitations of Embedding-Based Retrieval

   Gepubliceerd: 31-8-2025
4. Performance Prediction for Large Systems via Text-to-Text Regression

   Gepubliceerd: 30-8-2025
5. Demystifying the Visual Quality Paradox in Multimodal Large Language Models

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

   Gepubliceerd: 30-8-2025
7. Compute-Optimal Scaling for Value-Based Deep RL

   Gepubliceerd: 25-8-2025
8. LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experience

   Gepubliceerd: 23-8-2025
9. Signal and Noise: Evaluating Language Model Benchmarks

   Gepubliceerd: 23-8-2025
10. Breaking Feedback Loops in Recommender Systems with Causal Inference

    Gepubliceerd: 21-8-2025
11. RAG is Dead, Context Engineering is King: Building Reliable AI Systems

    Gepubliceerd: 20-8-2025
12. A Survey of Personalization: From RAG to Agent

    Gepubliceerd: 20-8-2025
13. Facilitating the Adoption of Causal Infer-ence Methods Through LLM-Empowered Co-Pilot

    Gepubliceerd: 19-8-2025
14. Performance Prediction for Large Systems via Text-to-Text Regression

    Gepubliceerd: 16-8-2025
15. Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning

    Gepubliceerd: 15-8-2025
16. DINOv3: Vision Models for Self-Supervised Learning

    Gepubliceerd: 15-8-2025
17. Agent Lightning: Training Any AI Agents with Reinforcement Learning

    Gepubliceerd: 14-8-2025
18. Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier

    Gepubliceerd: 14-8-2025
19. From Model Weights to Agent Workflows: Charting the New Frontier of Optimization in Large Language Models

    Gepubliceerd: 12-8-2025
20. Is Chain-of-Thought Reasoning a Mirage?

    Gepubliceerd: 12-8-2025