Deep Learning

This paper presents a novel method for fast and exact conformalization, leveraging inherent piecewise smoothness to dramatically accelerate uncertainty quantification in machine learning models.

Novel imputation method, scCR, leverages complete gene-gene relationships (associating & dissociating) for superior single-cell RNA sequencing data recovery, significantly outperforming current state-…

GDeR: A novel dynamic graph pruning method boosts GNN training efficiency and robustness by intelligently selecting a representative subset of training data, mitigating issues caused by imbalanced or …

Constrained sampling solved! New functional gradient flow method (CFG) efficiently samples from constrained probability distributions via a novel boundary condition for gradient flows, achieving prov…

PepGLAD, a novel generative model, revolutionizes full-atom peptide design by leveraging geometric latent diffusion to significantly enhance peptide diversity and binding affinity.

FSP-LAPLACE efficiently integrates interpretable function-space priors into Bayesian deep learning via a novel Laplace approximation, significantly improving uncertainty estimates and model performanc…

Channel Clustering Module (CCM) boosts time series forecasting accuracy by intelligently grouping similar channels, improving model performance and generalization.

Learn unbiased molecular dynamics from limited biased data using a novel infinitesimal generator approach; accurately estimating eigenfunctions and eigenvalues even with suboptimal biasing.

FGTI: a novel frequency-aware model significantly improves multivariate time series imputation by focusing on the often-overlooked residual term, leveraging high-frequency information to enhance accur…

Frequency Adaptive Normalization (FAN) significantly boosts non-stationary time series forecasting accuracy by using Fourier transforms to identify and model dynamic trends and seasonal patterns, achi…

Zero-shot learning achieves accurate Markov jump process inference across diverse datasets, eliminating the need for extensive model retraining.

FlexSBDD, a novel deep generative model, accurately predicts flexible protein-ligand complex structures, generating high-affinity drug molecules while overcoming the limitations of rigid protein model…

A new fine-grained dynamic framework jointly optimizes bias and variance for accurate predictions from missing-not-at-random data, surpassing existing methods.

FilterNet: A novel deep learning architecture using learnable frequency filters for superior time series forecasting accuracy and efficiency.

Revolutionizing graph analysis, this paper introduces a novel framework for efficiently solving graph diffusion equations, achieving up to a hundred-fold speed improvement and enabling faster graph ne…

Risk control boosts early-exit neural networks’ speed and safety by ensuring accurate predictions before exiting early, achieving substantial computational savings across diverse tasks.

Quantum computing drastically reduces communication needs for distributed machine learning, enabling faster and more private AI.

XFADS: a novel low-rank structured VAE framework for large-scale nonlinear Gaussian state-space modeling, achieving high predictive accuracy and scalability.

BeNeDiff uses generative diffusion models to disentangle and interpret neural dynamics linked to specific behaviors, providing interpretable quantifications of behavior in multi-brain region datasets.

Low Precision Ensembling (LPE) boosts large model accuracy using training-free ensemble creation via stochastic rounding in low-precision number systems.