Alexandre Drouin | Alexandre Drouin

Latest

TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
Capture the Flag: Uncovering Data Insights with Large Language Models
The Unsolved Challenges of LLMs as Generalist Web Agents: A Case Study
Lag-llama: Towards foundation models for time series forecasting
Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
Causal Discovery with Language Models as Imperfect Experts
Invariant Causal Set Covering Machines
Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts
GEO-Bench: Toward Foundation Models for Earth Monitoring
TACTiS: Transformer-Attentional Copulas for Time Series
Typing Assumptions Improve Identification in Causal Discovery
Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark
byteSteady: Fast Classification Using Byte-Level n-Gram Embeddings
In search of robust measures of generalization
Synbols: Probing Learning Algorithms with Synthetic Datasets
Differentiable Causal Discovery from Interventional Data
Gradient-based Neural DAG Learning with Interventions
Embedding Propagation: Smoother Manifold for Few-Shot Classification
Deep learning for electromyographic hand gesture signal classification using transfer learning
Inferring phenotypes from genotypes with machine learning: an application to the global problem of antibiotic resistance
Interpretable genotype-to-phenotype classifiers with performance guarantees
Mass spectra alignment using virtual lock-masses
Maximum margin interval trees
Large scale modeling of antimicrobial resistance with interpretable classifiers
Predictive computational phenotyping and biomarker discovery using reference-free genome comparisons
Greedy Biomarker Discovery in the Genome with Applications to Antimicrobial Resistance
Learning interpretable models of phenotypes from whole genome sequences with the Set Covering Machine
Accelerated Robust Point Cloud Registration in Natural Environments through Positive and Unlabeled Learning
Learning a peptide-protein binding affinity predictor with kernel ridge regression
MHC-NP: predicting peptides naturally processed by the MHC