Best AI papers explained

550 Afleveringen

1. PREFDISCO: Evaluating Proactive Personalization through Interactive Preference Discovery

   Gepubliceerd: 12-11-2025
2. Reusing pre-training data at test time is a compute multiplier

   Gepubliceerd: 10-11-2025
3. Scaling Agent Learning via Experience Synthesis

   Gepubliceerd: 9-11-2025
4. Continuous Autoregressive Language Models

   Gepubliceerd: 8-11-2025
5. Toward a Theory of Agents as Tool-Use Decision-Makers

   Gepubliceerd: 7-11-2025
6. Nested Learning: The Illusion of Deep Learning Architectures

   Gepubliceerd: 5-11-2025
7. GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

   Gepubliceerd: 5-11-2025
8. Beyond a million tokens: benchmarking and enhancing long-term memory in llms

   Gepubliceerd: 4-11-2025
9. Agentic Economic Modeling

   Gepubliceerd: 3-11-2025
10. Emergent Introspective Awareness in Large Language Models

    Gepubliceerd: 3-11-2025
11. Can Large reasoning models self-train?

    Gepubliceerd: 1-11-2025
12. ALITA-G: Self-Evolving Generative Agent for Agent Generation

    Gepubliceerd: 1-11-2025
13. Self-improving LLM agents at test-time

    Gepubliceerd: 30-10-2025
14. Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

    Gepubliceerd: 30-10-2025
15. Language models are injective and hence invertible

    Gepubliceerd: 30-10-2025
16. ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

    Gepubliceerd: 29-10-2025
17. RLAD: Training LLMs to Discover Abstractions

    Gepubliceerd: 29-10-2025
18. How to Train Your Advisor: Steering Black-Box LLMs with ADVISOR MODELS

    Gepubliceerd: 29-10-2025
19. Self-improving LLM agents at Test-Time

    Gepubliceerd: 27-10-2025
20. KL-Regularized Reinforcement Learning is designed to Mode Collapse

    Gepubliceerd: 27-10-2025