Best AI papers explained
Ein Podcast von Enoch H. Kang
518 Folgen
-
Learning How Hard to Think: Input-Adaptive Allocation of LM Computation
Vom: 26.5.2025 -
Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval
Vom: 26.5.2025 -
UFT: Unifying Supervised and Reinforcement Fine-Tuning
Vom: 26.5.2025 -
Understanding High-Dimensional Bayesian Optimization
Vom: 26.5.2025 -
Inference time alignment in continuous space
Vom: 25.5.2025 -
Efficient Test-Time Scaling via Self-Calibration
Vom: 25.5.2025 -
Conformal Prediction via Bayesian Quadrature
Vom: 25.5.2025 -
Predicting from Strings: Language Model Embeddings for Bayesian Optimization
Vom: 25.5.2025 -
Self-Evolving Curriculum for LLM Reasoning
Vom: 25.5.2025 -
Online Decision-Focused Learning in Dynamic Environments
Vom: 25.5.2025 -
FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain
Vom: 25.5.2025 -
Reward Shaping from Confounded Offline Data
Vom: 25.5.2025 -
Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning
Vom: 25.5.2025 -
Understanding Best-of-N Language Model Alignment
Vom: 25.5.2025 -
Maximizing Acquisition Functions for Bayesian Optimization - and its relation to Gradient Descent
Vom: 24.5.2025 -
Bayesian Prompt Ensembles: Model Uncertainty Estimation for Black-Box Large Language Models
Vom: 24.5.2025 -
Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation
Vom: 24.5.2025 -
The Parallel Knowledge Gradient Method for Batch Bayesian Optimization
Vom: 24.5.2025 -
FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
Vom: 24.5.2025 -
Automated Social Science: A Structural Causal Model-Based Approach
Vom: 24.5.2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
