AutoML Seminars
Virtual reading group on topics about automated machine learning. For more information see: https://automl-seminars.github.io/
Stop Guessing, Start Discovering Trade-offs in Your ML Models
ShinkaEvolve: На пути к открытой и эффективной с точки зрения использования примеров эволюции про...
Машинное обучение без данных: обучение небольших моделей на 10 примерах.
Benchmarking Beyond Statistics: Data-Driven Footprints for Explainable Black-Box Optimization
Do-PFN: In-Context Learning for Causal Effect Estimation
Multi-Objective AutoML: Towards Accurate and Robust models
carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks
Accelerating Bayesian Inference and Data Acquisition via Amortization
A LLM Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms
TabArena: A Living Benchmark for Machine Learning on Tabular Data
Tuning LLM Judge Design Decisions for 1/1000 of the Cost
Hyperband-based Bayesian Optimization for Efficient Black-box Prompt Selection
Understanding High-Dimensional Bayesian Optimization
AutoML in the Age of Structured Foundation Models
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization
Accurate predictions on small data (and time series) with the tabular foundation model TabPFN
Chronos: Time series forecasting in the age of pretrained models
Scaling Exponents Across Parameterizations and Optimizers
Unlocking State-Tracking in Linear RNNs Through Negative Eigenvalues
FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearch
GRAF: Performance Prediction with Neural Graph Features
Large Language Models to Enhance Bayesian Optimization
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
einspace: Searching for Neural Architectures from Fundamental Operations
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed MoE
Vanilla Bayesian Optimization Performs Great in High Dimensions
Multi-objective Differentiable Neural Architecture Search
Neural Fine-Tuning Search for Few-Shot Learning
Is Mamba Capable of In-Context Learning?