Best AI papers explained

203 Episoder

1. Adaptive Polyhedral Methods for Conjoint Analysis

   Publisert: 11.4.2025
2. MSL: Enhancing LLM Recommenders via Masked Softmax Loss

   Publisert: 11.4.2025
3. Self-Supervised Deep Reinforcement Learning for Optimal Question Ranking

   Publisert: 11.4.2025
4. Adaptive Language Elicitation for Latent Information Discovery

   Publisert: 10.4.2025
5. LLM Persona Bias: Promise and Peril in Simulation

   Publisert: 10.4.2025
6. AutoTools: Automating Tool Use for Large Language Models

   Publisert: 10.4.2025
7. Tool Learning with Large Language Models: A Comprehensive Survey

   Publisert: 10.4.2025
8. All Roads Lead to Likelihood: RL for Fine-Tuning Value

   Publisert: 8.4.2025
9. ATLAS: Tuning Agents via Critical Step Learning

   Publisert: 8.4.2025
10. Thinking Faster by Writing Less: Chain of Draft Reasoning

    Publisert: 8.4.2025
11. Meta Plan Optimization for Boosting LLM Agents

    Publisert: 8.4.2025
12. L1: Length Controlled Reasoning with Reinforcement Learning

    Publisert: 8.4.2025
13. WikiBigEdit: Benchmarking Lifelong Knowledge Editing in LLMs

    Publisert: 8.4.2025
14. PLAN-AND-ACT: LLM Agent Planning with Synthetic Data

    Publisert: 8.4.2025
15. SEARCH-R1: LLMs Learn to Reason and Search via Reinforcement Learning

    Publisert: 8.4.2025
16. The Theory of the Firm: Information, Incentives, and Organization

    Publisert: 8.4.2025
17. Four Formalizable Theories of the Firm

    Publisert: 8.4.2025
18. Efficient Tool Use with Chain-of-Abstraction Reasoning

    Publisert: 6.4.2025
19. CodeTool: Process Supervision for Enhanced LLM Tool Invocation

    Publisert: 6.4.2025
20. Evaluating LLM Agents in Multi-Turn Conversations: A Survey

    Publisert: 6.4.2025