Related papers: HoLa: B-Rep Generation using a Holistic Latent Rep…

Generating realistic images is difficult, and many formulations for this task have been proposed recently. If we restrict the task to that of generating a particular class of images, however, the task becomes more tractable. That is to say,…

We present LARP, a novel video tokenizer designed to overcome limitations in current video tokenization methods for autoregressive (AR) generative models. Unlike traditional patchwise tokenizers that directly encode local visual patches…

Vision benefits from grouping pixels into objects and understanding their spatial relationships, both laterally and in depth. We capture this with a scene representation comprising an occlusion-ordered stack of "object layers," each…

Scene rearrangement, like table tidying, is a challenging task in robotic manipulation due to the complexity of predicting diverse object arrangements. Web-scale trained generative models such as Stable Diffusion can aid by generating…

Learning latent representations that capture both semantic and spatial information is central to efficient spatio-semantic reasoning. However, many existing approaches rely on implicit latent structures combined with dense feature maps or…

The transparency of deep learning models is essential for clinical diagnostics. Concept Bottleneck Model provides clear decision-making processes for diagnosis by transforming the latent space of black-box models into human-understandable…

With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly important. In this paper, we propose a new continual learning…

Causal representation learning (CRL) seeks to uncover meaningful latent variables and their corresponding causal structure from high-dimensional observational data. Although its significance, CRL identifiability remains a crucial property,…

Reconstructing 3D human body shapes from 3D partial textured scans remains a fundamental task for many computer vision and graphics applications -- e.g., body animation, and virtual dressing. We propose a new neural network architecture for…

Causal representation learning (CRL) has emerged as a powerful unsupervised framework that (i) disentangles the latent generative factors underlying high-dimensional data, and (ii) learns the cause-and-effect interactions among the…

Generating realistic hand-object interactions (HOI) videos is a significant challenge due to the difficulty of modeling physical constraints (e.g., contact and occlusion between hands and manipulated objects). Current methods utilize HOI…

Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation. Recently, an…

High-dimensional biological data often exhibit a severe mismatch between feature dimensionality and sample size, making reliable classification difficult in extremely small-data regimes. In these settings, kernel methods can lose…

Recovering intrinsic low dimensional subspaces from data distributed on them is a key preprocessing step to many applications. In recent years, there has been a lot of work that models subspace recovery as low rank minimization problems. We…

We introduce Being-H0.5, a foundational Vision-Language-Action (VLA) model designed for robust cross-embodiment generalization across diverse robotic platforms. While existing VLAs often struggle with morphological heterogeneity and data…

Animating virtual characters with holistic co-speech gestures is a challenging but critical task. Previous systems have primarily focused on the weak correlation between audio and gestures, leading to physically unnatural outcomes that…

Sampling from generative models has become a crucial tool for applications like data synthesis and augmentation. Diffusion, Flow Matching and Continuous Normalising Flows have shown effectiveness across various modalities, and rely on…

We propose a new hologram representation based on structured complex-valued 2D Gaussian primitives, which replaces per-pixel information storage and reduces the parameter search space by up to 10:1. To enable end-to-end training, we develop…

LiDAR-based place recognition serves as a crucial enabler for long-term autonomy in robotics and autonomous driving systems. Yet, prevailing methodologies relying on handcrafted feature extraction face dual challenges: (1) Inconsistent…

Computer-aided design (CAD) tools empower designers to design and modify 3D models through a series of CAD operations, commonly referred to as a CAD sequence. In scenarios where digital CAD files are not accessible, reverse engineering (RE)…