🏢 Imperial College London

UV3-TeD generates high-quality 3D textures directly on object surfaces using a novel diffusion probabilistic model, eliminating UV-mapping limitations.

Universal Sample Coding revolutionizes data transmission by reducing bits needed to communicate multiple samples from an unknown distribution, achieving significant improvements in federated learning …

This paper presents a novel BayesOpt framework that incorporates Markov Decision Processes to optimize black-box functions with transition constraints, overcoming limitations of traditional methods.

Universal Mesh Movement Network (UM2N) revolutionizes mesh movement for PDE solvers, enabling zero-shot adaptation to diverse problems and significantly accelerating simulations with improved accuracy…

Deep learning’s sequence modeling is revolutionized by selective state-space models (SSMs)! This paper provides theoretical grounding for their superior performance, revealing the crucial role of gati…

OpenDlign uses novel depth-aligned images from a diffusion model to boost open-world 3D understanding, achieving significant performance gains on diverse benchmarks.

Noether’s Razor learns conserved quantities and symmetries directly from data via Bayesian model selection, improving dynamical systems modeling accuracy and generalizability.

New metric, Maximum Entropy Goal-Directedness (MEG), quantifies AI goal-directedness, crucial for assessing AI safety and agency.

Probabilistic Slot Attention achieves identifiable object-centric representations without supervision, advancing systematic generalization in machine learning.

ID-to-3D: Generate expressive, identity-consistent 3D human heads from just a few in-the-wild images using score distillation sampling and 2D diffusion models.

Brain-inspired recurrent neural networks learn efficiently by using feedback control to approximate optimal gradients, enabling rapid movement corrections and efficient adaptation to persistent errors…

This paper provides novel entrywise error bounds for low-rank kernel matrix approximations, showing how many data points are needed to get statistically consistent results for low-rank approximations.

Train discrete EBMs efficiently with Energy Discrepancy, a novel loss function that eliminates the need for Markov Chain Monte Carlo, using diffusion processes on structured spaces.

Absorb & Escape: a novel post-training sampling method that overcomes single model limitations by combining Autoregressive (AR) and Diffusion Models (DMs), generating high-quality heterogeneous genomi…