Best AI papers explained
En podkast av Enoch H. Kang
490 Episoder
-
Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
Publisert: 22.7.2025 -
The Invisible Leash: Why RLVR May Not Escape Its Origin
Publisert: 20.7.2025 -
Language Model Personalization via Reward Factorization
Publisert: 20.7.2025 -
Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions
Publisert: 18.7.2025 -
Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective
Publisert: 17.7.2025 -
Soft Best-of-n Sampling for Model Alignment
Publisert: 16.7.2025 -
On Temporal Credit Assignment and Data-Efficient Reinforcement Learning
Publisert: 15.7.2025 -
Bradley–Terry and Multi-Objective Reward Modeling Are Complementary
Publisert: 15.7.2025 -
Probing Foundation Models for World Models
Publisert: 15.7.2025 -
GenAI-Powered Statistical Inference (with Unstructured Data)
Publisert: 14.7.2025 -
Interpretable Reward Modeling with Active Concept Bottlenecks
Publisert: 14.7.2025 -
PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications
Publisert: 14.7.2025 -
A Collectivist, Economic Perspective on AI
Publisert: 14.7.2025 -
Textual Bayes: Quantifying Uncertainty in LLM-Based Systems
Publisert: 12.7.2025 -
The Winner's Curse in Data-Driven Decisions
Publisert: 11.7.2025 -
SPIRAL: Self-Play for Reasoning Through Zero-Sum Games
Publisert: 11.7.2025 -
Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
Publisert: 11.7.2025 -
Aligning Learning and Endogenous Decision-Making
Publisert: 11.7.2025 -
Reliable Statistical Inference with Synthetic Data from Large Language Models
Publisert: 11.7.2025 -
Multi-Turn Reinforcement Learning from Human Preference Feedback
Publisert: 10.7.2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
