Best AI papers explained

529 Episodes

1. Beyond Conjoint Analysis: The Future of Preference Measurement

   Published: 11/04/2025
2. An Optimization Framework for Adaptive Questionnaire Design

   Published: 11/04/2025
3. Adaptive Self-Explication of Multiattribute Preferences

   Published: 11/04/2025
4. Conjoint Analysis: Methods, Applications, and Recent Developments

   Published: 11/04/2025
5. Current Issues and a “Wish List” for Conjoint Analysis

   Published: 11/04/2025
6. Ellipsoidal Methods for Adaptive Choice-Based Conjoint Analysis

   Published: 11/04/2025
7. Adaptive Polyhedral Methods for Conjoint Analysis

   Published: 11/04/2025
8. MSL: Enhancing LLM Recommenders via Masked Softmax Loss

   Published: 11/04/2025
9. Self-Supervised Deep Reinforcement Learning for Optimal Question Ranking

   Published: 11/04/2025
10. Adaptive Language Elicitation for Latent Information Discovery

    Published: 10/04/2025
11. LLM Persona Bias: Promise and Peril in Simulation

    Published: 10/04/2025
12. AutoTools: Automating Tool Use for Large Language Models

    Published: 10/04/2025
13. Tool Learning with Large Language Models: A Comprehensive Survey

    Published: 10/04/2025
14. All Roads Lead to Likelihood: RL for Fine-Tuning Value

    Published: 8/04/2025
15. ATLAS: Tuning Agents via Critical Step Learning

    Published: 8/04/2025
16. Thinking Faster by Writing Less: Chain of Draft Reasoning

    Published: 8/04/2025
17. Meta Plan Optimization for Boosting LLM Agents

    Published: 8/04/2025
18. L1: Length Controlled Reasoning with Reinforcement Learning

    Published: 8/04/2025
19. WikiBigEdit: Benchmarking Lifelong Knowledge Editing in LLMs

    Published: 8/04/2025
20. PLAN-AND-ACT: LLM Agent Planning with Synthetic Data

    Published: 8/04/2025