Related papers: From Directions to Regions: Decomposing Activation…

We explore the interpretability of 3D geometric deep learning models in the context of Computer-Aided Design (CAD). The field of parametric CAD can be limited by the difficulty of expressing high-level design concepts in terms of a few…

Weakly supervised object localization has recently attracted attention since it aims to identify both class labels and locations of objects by using image-level labels. Most previous methods utilize the activation map corresponding to the…

To fully leverage the capabilities of mobile manipulation robots, it is imperative that they are able to autonomously execute long-horizon tasks in large unexplored environments. While large language models (LLMs) have shown emergent…

The activations of language transformers like GPT-2 have been shown to linearly map onto brain activity during speech comprehension. However, the nature of these activations remains largely unknown and presumably conflate distinct…

We study planning site formation in language models -- where internal representations of structurally-constrained future tokens form during the forward pass, and whether they causally drive generation. Using rhyming-couplet completion as a…

Local geometric descriptors remain an essential component for 3D rigid data matching and fusion. The devise of a rotational invariant local geometric descriptor usually consists of two steps: local reference frame (LRF) construction and…

Trust region-based optimization methods have become foundational reinforcement learning algorithms that offer stability and strong empirical performance in continuous control tasks. Growing interest in scalable and reusable control policies…

Spatial functional organization is a hallmark of biological brains: neurons are arranged topographically according to their response properties, at multiple scales. In contrast, representations within most machine learning models lack…

We propose an end-to-end deep neural encoder-decoder model to encode and decode brain activity in response to naturalistic stimuli using functional magnetic resonance imaging (fMRI) data. Leveraging temporally correlated input from…

In the field of multi-organ medical image segmentation, recent methods frequently employ Transformers to capture long-range dependencies from image features. However, these methods overlook the high computational cost of Transformers and…

Multimodal Large Language Models (MLLMs) are increasingly applied to pixel-level vision tasks, yet their intrinsic capacity for spatial understanding remains poorly understood. We investigate segmentation capacity through a layerwise linear…

Many fMRI analyses examine functional connectivity, or statistical dependencies among remote brain regions. Yet popular methods for studying whole-brain functional connectivity often yield results that are difficult to interpret. Factor…

Flow maps are thematic maps that visualize object movements across space with a tree layout, in which the underlying tree structure is similar to a natural river system. In this paper, we present a novel and automated approach named RFDA-FM…

Monads govern computational side-effects in programming semantics. They can be combined in a ''bottom-up'' way to handle several instances of such effects. Indexed monads and graded monads do this in a modular way. Here, instead, we equip…

Computational food analysis (CFA) naturally requires multi-modal evidence of a particular food, e.g., images, recipe text, etc. A key to making CFA possible is multi-modal shared representation learning, which aims to create a joint…

Functional magnetic resonance imaging produces high dimensional data, with a less then ideal number of labelled samples for brain decoding tasks (predicting brain states). In this study, we propose a new deep temporal convolutional neural…

We introduce a novel data-driven approach aimed at designing high-quality shape deformations based on a coarse localized input signal. Unlike previous data-driven methods that require a global shape encoding, we observe that…

There has been an explosion of interest in designing high-performance Transformers. While Transformers have delivered significant performance improvements, training such networks is extremely memory intensive owing to storing all…

Image segmentation is a fundamental task in computer vision, aimed at partitioning an image into semantically meaningful regions. Referring image segmentation extends this task by using natural language expressions to localize specific…

Video decomposition is very important to extract moving foreground objects from complex backgrounds in computer vision, machine learning, and medical imaging, e.g., extracting moving contrast-filled vessels from the complex and noisy…