Best AI papers explained

441 Afleveringen

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

   Gepubliceerd: 7-9-2025
2. Why Language Models Hallucinate

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

   Gepubliceerd: 6-9-2025
4. Sample Efficient Preference Alignment in LLMs via Active Exploration

   Gepubliceerd: 6-9-2025
5. Adventures in Demand Analysis Using AI

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

    Gepubliceerd: 15-8-2025