🏢 University of Texas at Austin

Zero-shot Neural ODEs enable autonomous systems to rapidly adapt to unseen scenarios by learning a space of dynamical systems spanned by neural ODE basis functions, achieving efficient online adaptati…

YOUDREAM generates anatomically consistent, high-quality 3D animal models from text and 2D pose priors, pushing creative boundaries in text-to-3D generation.

Warped Diffusion cleverly adapts image diffusion models for video inverse problems, solving flickering and temporal inconsistency issues by viewing video frames as continuous warping transformations a…

This paper presents efficient algorithms for transfer learning in latent variable network models, achieving vanishing error under specific conditions, and attaining minimax optimal rates for stochasti…

The Synthesize-Partition-Adapt (SPA) framework leverages synthetic data to generate diverse, high-quality responses from foundation models, enriching user experience.

LASR, a novel symbolic regression method, uses zero-shot LLM queries to discover and evolve abstract concepts, substantially outperforming state-of-the-art approaches and discovering a new LLM scaling…

SVFT: a novel parameter-efficient fine-tuning method achieves near full fine-tuning accuracy using only 0.006% to 0.25% of parameters, significantly outperforming existing techniques.

Stochastic Newton Proximal Extragradient (SNPE) achieves faster global and local convergence rates for strongly convex functions, improving upon existing stochastic Newton methods by requiring signifi…

SkiLD, a novel unsupervised skill discovery method, uses state factorization and a new objective function to learn skills inducing diverse interactions between state factors, outperforming existing me…

Sigmoid gating significantly boosts sample efficiency in Mixture of Experts models compared to softmax gating, offering faster convergence rates for various expert functions.

Q2VMC, a novel quantum chemistry algorithm, drastically boosts the efficiency and accuracy of solving the Schrödinger equation using a quadratic update mechanism and neural network ansatzes.

Pseudo-Private Data Guided Model Inversion (PPDG-MI) significantly improves model inversion attacks by dynamically tuning the generative model to increase the sampling probability of actual private da…

Parametric Piecewise Linear Networks (PPLNs) achieve state-of-the-art results in event-based and frame-based computer vision tasks by mimicking biological neural principles.

PACE, a novel neural operator, achieves unprecedented accuracy and speed in optical field simulation for complex photonic devices, surpassing existing methods by significantly reducing errors and boos…

Optimization can learn optimal Johnson-Lindenstrauss embeddings, avoiding the limitations of randomized methods and achieving comparable theoretical guarantees.

Oja’s algorithm achieves minimax optimal error rates for streaming sparse PCA using a simple single-pass thresholding method, requiring only O(d) space and O(nd) time.

BFGS algorithm achieves global linear and superlinear convergence rates with inexact Armijo-Wolfe line search, even without precise Hessian knowledge.

This study introduces a neural cover selection framework for image steganography, optimizing latent spaces in generative models to improve message recovery and image quality.

New algorithm, POAM, excels at multi-agent cooperation by adapting to diverse and changing teammates in dynamic scenarios.

Online Subspace Descent: a novel memory-efficient LLM training algorithm guaranteed to converge, closing the performance gap with full-rank methods.