Related papers: Approximate UMAP allows for high-rate online visua…

Discovering atom-level phenomena requires molecular dynamics (MD) simulations with ab initio accuracy. Machine learning interatomic potentials (MLIPs) enable stable, high-accuracy MD simulations, and their models exhibit scaling-law trends…

Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models…

We present UbiSLAM, an innovative solution for real-time mapping and localization in dynamic indoor environments. By deploying a network of fixed RGB-D cameras strategically throughout the workspace, UbiSLAM addresses limitations commonly…

Perceiving and reconstructing objects from images are critical for real-to-sim transfer tasks, which are widely used in the robotics community. Existing methods rely on multiple submodules such as detection, segmentation, shape…

Sparse structure learning in high-dimensional Gaussian graphical models is an important problem in multivariate statistical signal processing; since the sparsity pattern naturally encodes the conditional independence relationship among…

We propose LookinGood^{\pi}, a novel neural re-rendering approach that is aimed to (1) improve the rendering quality of the low-quality reconstructed results from human performance capture system in real-time; (2) improve the generalization…

Human reasoning is grounded in an ability to identify highly abstract commonalities governing superficially dissimilar visual inputs. Recent efforts to develop algorithms with this capacity have largely focused on approaches that require…

Real-time crack segmentation is vital for structural health monitoring but is plagued by aleatoric uncertainties arising from varying lighting, blur, and texture ambiguity. Current uncertainty-aware approaches typically treat uncertainty…

We introduce a high resolution spatially adaptive light source, or a projector, into a neural reflectance field that allows to both calibrate the projector and photo realistic light editing. The projected texture is fully differentiable…

Dimensionality reduction is crucial both for visualization and preprocessing high dimensional data for machine learning. We introduce a novel method based on a hierarchy built on 1-nearest neighbor graphs in the original space which is used…

Path representations are critical in a variety of transportation applications, such as estimating path ranking in path recommendation systems and estimating path travel time in navigation systems. Existing studies often learn task-specific…

In supervised learning, understanding an input's proximity to the training data can help a model decide whether it has sufficient evidence for reaching a reliable prediction. While powerful probabilistic models such as Gaussian Processes…

Supervised dimensionality reduction strategies have been of great interest. However, current supervised dimensionality reduction approaches are difficult to scale for situations characterized by large datasets given the high computational…

Majority of the current dimensionality reduction or retrieval techniques rely on embedding the learned feature representations onto a computable metric space. Once the learned features are mapped, a distance metric aids the bridging of gaps…

Sequence parallelism (SP), which divides the sequence dimension of input tensors across multiple computational devices, is becoming key to unlocking the long-context capabilities of generative AI models. This paper investigates the…

We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network training. Our algorithm is motivated by the step size…

Contrastive vision-language models like CLIP have shown great progress in transfer learning. In the inference stage, the proper text description, also known as prompt, needs to be carefully designed to correctly classify the given images.…

Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a…

We present a novel algorithm for real-time planar semantic mapping tailored for humanoid robots navigating complex terrains such as staircases. Our method is adaptable to any odometry input and leverages GPU-accelerated processes for planar…

We develop the first approximate inference algorithm for 1-Best (and M-Best) decoding in bidirectional neural sequence models by extending Beam Search (BS) to reason about both forward and backward time dependencies. Beam Search (BS) is a…