Deep Learning

Boost multivariate time series forecasting accuracy by efficiently learning the complex correlation structure of prediction errors, enhancing reliability without expanding model size.

Adaptive multi-model ensemble conformal prediction achieves strongly adaptive regret, yielding more efficient prediction sets in dynamic environments.

SLAN: A novel approach for multi-label open-set recognition, enriching sub-labeling info using structural data to identify unknown labels.

MSAGPT: Revolutionizing protein structure prediction by generating accurate virtual MSAs from limited data, boosting prediction accuracy by up to +8.5% TM-Score!

MOTE-NAS: A new multi-objective training-based estimate drastically improves neural architecture search efficiency, achieving state-of-the-art accuracy with significantly reduced costs.

Monomial-NFNs boost neural network efficiency by leveraging scaling/sign-flipping symmetries, resulting in fewer trainable parameters and competitive performance.

f-RAG: A novel fragment-based molecular generation framework boosts drug discovery by combining retrieval augmentation with a generative model, enabling exploration beyond existing fragments and signi…

gpSLDS, a novel model, balances expressiveness and interpretability in modeling complex neural dynamics by combining Gaussian processes with switching linear dynamical systems, improving accuracy and …

Model LEGO (MDA) revolutionizes deep learning by enabling the creation of new models by assembling and disassembling task-aware components from pre-trained models, eliminating the need for retraining.

Link-MoE boosts link prediction accuracy by strategically selecting the best model for each node pair, surpassing single-model approaches.

Non-linear Residual Gates (NoRGa) boosts prompt-based continual learning by theoretically framing prefix tuning as adding new experts to a pre-trained Mixture-of-Experts model, achieving state-of-the-…

Proactive Defensive Backdoor (PDB) thwarts malicious backdoors by injecting a hidden defensive backdoor during training, suppressing attacks while maintaining model utility.

MiSO: a novel closed-loop brain stimulation framework optimizes stimulation parameters to achieve desired neural population activity states, overcoming limitations of current methods by merging data a…

METRIC FLOW MATCHING (MFM) generates smooth interpolations on data manifolds by minimizing kinetic energy, outperforming Euclidean methods and achieving state-of-the-art results in single-cell traject…

Adaptive MCMC with CNFs accelerates probabilistic inference by combining local and flow-informed transition kernels, achieving state-of-the-art results efficiently.

Lorentz Geometric Algebra Transformer (L-GATr): A novel, scalable architecture for high-energy physics, achieving high-precision, data-efficient learning and outperforming existing methods on regressi…

LCSS, a novel score-matching method, enables efficient and high-quality image generation in score-based diffusion models by using Stein’s identity to bypass the computationally expensive Jacobian trac…

LM-HT SNN: A learnable multi-hierarchical threshold model dramatically improves SNN performance, achieving near-ANN accuracy through dynamic current regulation and seamless ANN-SNN conversion.

LLM-AutoDA: Automating data augmentation for long-tailed learning using large language models, significantly boosting model performance.

Drifted VESDE: Faster convergence, efficient sampling for variance-exploding diffusion models!