Best AI papers explained

436 Avsnitt

1. Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

   Publicerades: 2025-09-01
2. On the Theoretical Limitations of Embedding-Based Retrieval

   Publicerades: 2025-08-31
3. Performance Prediction for Large Systems via Text-to-Text Regression

   Publicerades: 2025-08-30
4. Demystifying the Visual Quality Paradox in Multimodal Large Language Models

   Publicerades: 2025-08-30
5. Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

   Publicerades: 2025-08-30
6. Compute-Optimal Scaling for Value-Based Deep RL

   Publicerades: 2025-08-25
7. LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experience

   Publicerades: 2025-08-23
8. Signal and Noise: Evaluating Language Model Benchmarks

   Publicerades: 2025-08-23
9. Breaking Feedback Loops in Recommender Systems with Causal Inference

   Publicerades: 2025-08-21
10. RAG is Dead, Context Engineering is King: Building Reliable AI Systems

    Publicerades: 2025-08-20
11. A Survey of Personalization: From RAG to Agent

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

    Publicerades: 2025-08-19
13. Performance Prediction for Large Systems via Text-to-Text Regression

    Publicerades: 2025-08-16
14. Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning

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

    Publicerades: 2025-08-15
16. Agent Lightning: Training Any AI Agents with Reinforcement Learning

    Publicerades: 2025-08-14
17. Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier

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

    Publicerades: 2025-08-12
19. Is Chain-of-Thought Reasoning a Mirage?

    Publicerades: 2025-08-12
20. Agentic Web: Weaving the Next Web with AI Agents

    Publicerades: 2025-08-11