相关论文: PDE-SSM: A Spectral State Space Approach to Spatia…

Transformer-based object detectors often struggle with occlusions, fine-grained localization, and computational inefficiency caused by fixed queries and dense attention. We propose DAMM, Dual-stream Attention with Multi-Modal queries, a…

Recently, transformers have shown great potential in image classification and established state-of-the-art results on the ImageNet benchmark. However, compared to CNNs, transformers converge slowly and are prone to overfitting in low-data…

Transformers provide a class of expressive architectures that are extremely effective for sequence modeling. However, the key limitation of transformers is their quadratic memory and time complexity $\mathcal{O}(L^2)$ with respect to the…

Given the remarkable achievements in image generation through diffusion models, the research community has shown increasing interest in extending these models to video generation. Recent diffusion models for video generation have…

The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either…

Transformer architectures deliver state-of-the-art accuracy via dense full-attention, but their quadratic time and memory complexity with respect to sequence length limits practical deployment. Linear attention mechanisms offer linear or…

Physics-informed neural networks (PINNs) were recently proposed in [1] as an alternative way to solve partial differential equations (PDEs). A neural network (NN) represents the solution while a PDE-induced NN is coupled to the solution NN,…

The evolution of Vision Transformers has led to their widespread adaptation to different domains. Despite large-scale success, there remain significant challenges including their reliance on extensive computational and memory resources for…

We study the problem of traffic forecasting, aiming to predict the inflow and outflow of a region in the subsequent time slot. The problem is complex due to the intricate spatial and temporal interdependence among regions. Prior works study…

Attention-based models have revolutionized AI, but the quadratic cost of self-attention incurs severe computational and memory overhead. Sparse attention methods alleviate this by skipping low-relevance token pairs. However, current…

Stochastic simulation methods can be applied successfully to model exact spatio-temporally resolved reaction-diffusion systems. However, in many cases, these methods can quickly become extremely computationally intensive with increasing…

Flow matching has recently emerged as a principled framework for learning continuous-time transport maps, enabling efficient ODE-based sampling without relying on stochastic diffusion processes. While generative modeling has shown promise…

Monocular Depth Estimation (MDE) aims to predict pixel-wise depth given a single RGB image. For both, the convolutional as well as the recent attention-based models, encoder-decoder-based architectures have been found to be useful due to…

Learning meaningful and interpretable representations from high-dimensional volumetric magnetic resonance (MR) images is essential for advancing personalized medicine. While Vision Transformers (ViTs) have shown promise in handling image…

Deep learning paradigms, such as PINNs and neural operators, have significantly advanced the solving of PDEs. However, they often struggle to capture the continuous integral nature of physical systems, relying either on pointwise residuals…

Few-Shot Medical Image Segmentation (FSMIS) aims to segment novel object classes in medical images using only minimal annotated examples, addressing the critical challenges of data scarcity and domain shifts prevalent in medical imaging.…

Stereo Imaging technology integration into medical diagnostics and surgeries brings a great revolution in the field of medical sciences. Now, surgeons and physicians have better insight into the anatomy of patients' organs. Like other…

Transformers have recently gained attention in the computer vision domain due to their ability to model long-range dependencies. However, the self-attention mechanism, which is the core part of the Transformer model, usually suffers from…

Stochastic differential equations provide a rich class of flexible generative models, capable of describing a wide range of spatio-temporal processes. A host of recent work looks to learn data-representing SDEs, using neural networks and…

Transformers owe much of their empirical success in natural language processing to the self-attention blocks. Recent perspectives interpret attention blocks as interacting particle systems, whose mean-field limits correspond to gradient…