Related papers: MUSE: Resolving Manifold Misalignment in Visual To…

This paper studies the problem of image-goal navigation which involves navigating to the location indicated by a goal image in a novel previously unseen environment. To tackle this problem, we design topological representations for space…

Recently, maximizing mutual information has emerged as a powerful method for unsupervised graph representation learning. The existing methods are typically effective to capture information from the topology view but ignore the feature view.…

This paper identifies a structural limitation in current multimodal AI architectures that is topological rather than parametric. Contrastive alignment (CLIP), cross-attention fusion (GPT-4V/Gemini), and diffusion-based generation share a…

In vision-and-language grounding problems, fine-grained representations of the image are considered to be of paramount importance. Most of the current systems incorporate visual features and textual concepts as a sketch of an image.…

Current multi-modal models exhibit a notable misalignment with the human visual system when identifying objects that are visually assimilated into the background. Our observations reveal that these multi-modal models cannot distinguish…

Audio-visual learning suffers from modality misalignment caused by off-screen sources and background clutter, and current methods usually amplify irrelevant regions or moments, leading to unstable training and degraded representation…

Multimodal representation learning aims to construct a shared embedding space in which heterogeneous modalities are semantically aligned. Despite strong empirical results, InfoNCE-based objectives introduce inherent conflicts that yield…

We introduce a manifold-based framework for addressing optimization problems with equality and inequality constraints found in robotics. Our approach transforms the original problem into an unconstrained optimization problem directly on the…

While Multi-view Graph Neural Networks (MVGNNs) excel at leveraging diverse modalities for learning object representation, existing methods assume identical local topology structures across modalities that overlook real-world discrepancies.…

In sequence to sequence learning, the self-attention mechanism proves to be highly effective, and achieves significant improvements in many tasks. However, the self-attention mechanism is not without its own flaws. Although self-attention…

We present a topology-informed inverse rendering approach for reconstructing high-genus surface meshes from multi-view images. Compared to 3D representations like voxels and point clouds, mesh-based representations are preferred as they…

We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation…

An appropriate visualization of multiobjective non-dominated solutions is a valuable asset for decision making. Although there are methods for visualizing the solutions in the design space, they do not provide any information about their…

Multimodal Sentiment Analysis (MSA) seeks to understand human emotions by integrating textual, acoustic, and visual signals. Although multimodal fusion is designed to leverage cross-modal complementarity, real-world scenarios often exhibit…

To create heterogeneous, multiscale structures with unprecedented functionalities, recent topology optimization approaches design either fully aperiodic systems or functionally graded structures, which compete in terms of design freedom and…

Modality alignment is critical for vision-language models (VLMs) to effectively integrate information across modalities. However, existing methods extract hierarchical features from text while representing each image with a single feature,…

Tokenizer is a crucial component for both visual understanding and generation. To advance toward the ultimate goal of universal modeling, recent research has focused on developing a unified tokenizer. However, existing tokenizers face a…

We propose TopDis (Topological Disentanglement), a method for learning disentangled representations via adding a multi-scale topological loss term. Disentanglement is a crucial property of data representations substantial for the…

In this work, we present an efficiently computational approach for designing material micro-structures by means of topology optimization. The central idea relies on using the isogeometric analysis integrated with the parameterized level set…

Multi-objective optimization (MOO) problems require balancing competing objectives, often under constraints. The Pareto optimal solution set defines all possible optimal trade-offs over such objectives. In this work, we present a novel…