Related papers: SITS-DECO: A Generative Decoder Is All You Need Fo…
Visual grouping -- operationalized through tasks such as instance segmentation, visual grounding, and object detection -- enables applications ranging from robotic perception to photo editing. These fundamental problems in computer vision…
Recent development in vision-language approaches has instigated a paradigm shift in learning visual recognition models from language supervision. These approaches align objects with language queries (e.g. "a photo of a cat") and improve the…
We present a decoder-only Transformer architecture that robustly generalizes to sequence lengths substantially longer than those seen during training. Our model, SWAN-GPT, interleaves layers without positional encodings (NoPE) and…
Multi-modal large language models have demonstrated impressive performance across various tasks in different modalities. However, existing multi-modal models primarily emphasize capturing global information within each modality while…
Diffusion Transformers have established a new state-of-the-art in image synthesis, but the high computational cost of iterative sampling severely hampers their practical deployment. While existing acceleration methods often focus on the…
Multivariate Time-Series (MTS) data is crucial in various application fields. With its sequential and multi-source (multiple sensors) properties, MTS data inherently exhibits Spatial-Temporal (ST) dependencies, involving temporal…
How to improve generative modeling by better exploiting spatial regularities and coherence in images? We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs). In our…
Seismic interpretation is vital for understanding subsurface structures but remains labor-intensive, subjective, and computationally demanding. While deep learning (DL) offers promise, its success hinges on large, high-quality datasets,…
Many real-world problems require reasoning across multiple scales, demanding models which operate not on single data points, but on entire distributions. We introduce generative distribution embeddings (GDE), a framework that lifts…
The detection of hazardous terrain during the planetary landing of spacecraft plays a critical role in assuring vehicle safety and mission success. A cheap and effective way of detecting hazardous terrain is through the use of visual…
Optical satellite image time series are extensively used in many Earth observation applications, including agriculture, climate monitoring, and land surface analysis. However, clouds and swath edges result in irregular sampling along the…
Existing Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on static dense computation that applies uniform processing to…
Moir\'e patterns, resulting from aliasing between object light signals and camera sampling frequencies, often degrade image quality during capture. Traditional demoir\'eing methods have generally treated images as a whole for processing and…
As large-scale heterogeneous data sets become increasingly available, adapting foundation models at low cost has become a key issue. Seminal works in natural language processing, e.g. Low-Rank Adaptation (LoRA), leverage the low "intrinsic…
The performance of unified multimodal models for image generation and editing is fundamentally constrained by the quality and comprehensiveness of their training data. While existing datasets have covered basic tasks like style transfer and…
State-of-the-art generative image and video models rely heavily on tokenizers that compress high-dimensional inputs into more efficient latent representations. While this paradigm has revolutionized RGB generation, Earth observation (EO)…
This paper addresses the problem of category-level pose estimation for articulated objects in robotic manipulation tasks. Recent works have shown promising results in estimating part pose and size at the category level. However, these…
A unified structural framework is presented for model-based fault diagnosis that explicitly incorporates both fault locations and constraints imposed by the residual generation methodology. Building on the concepts of proper and minimal…
This paper presents a unified mathematical paradigm, based on stochastic geometry, for downlink cellular networks with multiple-input-multiple-output (MIMO) base stations (BSs). The developed paradigm accounts for signal retransmission upon…
Conventional object detection models are usually limited by the data on which they were trained and by the category logic they define. With the recent rise of Language-Visual Models, new methods have emerged that are not restricted to these…