Best AI papers explained
A podcast by Enoch H. Kang
526 Episoade
-
Harnessing the Universal Geometry of Embeddings
Publicat: 27.05.2025 -
Goal Inference using Reward-Producing Programs in a Novel Physics Environment
Publicat: 27.05.2025 -
Trial-Error-Explain In-Context Learning for Personalized Text Generation
Publicat: 27.05.2025 -
Reinforcement Learning for Reasoning in Large Language Models with One Training Example
Publicat: 27.05.2025 -
Test-Time Reinforcement Learning (TTRL)
Publicat: 27.05.2025 -
Interpreting Emergent Planning in Model-Free Reinforcement Learning
Publicat: 26.05.2025 -
Agentic Reward Modeling_Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
Publicat: 26.05.2025 -
Beyond Reward Hacking: Causal Rewards for Large LanguageModel Alignment
Publicat: 26.05.2025 -
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
Publicat: 26.05.2025 -
Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval
Publicat: 26.05.2025 -
UFT: Unifying Supervised and Reinforcement Fine-Tuning
Publicat: 26.05.2025 -
Understanding High-Dimensional Bayesian Optimization
Publicat: 26.05.2025 -
Inference time alignment in continuous space
Publicat: 25.05.2025 -
Efficient Test-Time Scaling via Self-Calibration
Publicat: 25.05.2025 -
Conformal Prediction via Bayesian Quadrature
Publicat: 25.05.2025 -
Predicting from Strings: Language Model Embeddings for Bayesian Optimization
Publicat: 25.05.2025 -
Self-Evolving Curriculum for LLM Reasoning
Publicat: 25.05.2025 -
Online Decision-Focused Learning in Dynamic Environments
Publicat: 25.05.2025 -
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
Publicat: 25.05.2025 -
Reward Shaping from Confounded Offline Data
Publicat: 25.05.2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
