Related papers: FlowFormer: A Transformer Architecture for Optical…

The recently proposed Conformer architecture which combines convolution with attention to capture both local and global dependencies has become the \textit{de facto} backbone model for Automatic Speech Recognition~(ASR). Inherited from the…

Event-based cameras can overpass frame-based cameras limitations for important tasks such as high-speed motion detection during self-driving cars navigation in low illumination conditions. The event cameras' high temporal resolution and…

Event cameras generate asynchronous and sparse event streams capturing changes in light intensity. They offer significant advantages over conventional frame-based cameras, such as a higher dynamic range and an extremely faster data rate,…

This paper presents CLUSTERFORMER, a universal vision model that is based on the CLUSTERing paradigm with TransFORMER. It comprises two novel designs: 1. recurrent cross-attention clustering, which reformulates the cross-attention mechanism…

Flow-level simulation is widely used to model large-scale data center networks due to its scalability. Unlike packet-level simulators that model individual packets, flow-level simulators abstract traffic as continuous flows with dynamically…

This paper presents an investigation of vision transformer learning for multi-view geometry tasks, such as optical flow estimation, by fine-tuning video foundation models. Unlike previous methods that involve custom architectural designs…

Recent advances in optical flow estimation have prioritized accuracy at the cost of growing GPU memory consumption, particularly for high-resolution (FullHD) inputs. We introduce MEMFOF, a memory-efficient multi-frame optical flow method…

Knowledge Tracing (KT) models face a critical ``Performance-Complexity Trap'': capturing complex cognitive dynamics like learning sessions and memory decay typically requires deep hierarchical architectures, which incur prohibitive…

The performance of a deep learning model on a specific task and dataset depends heavily on its neural architecture, motivating considerable efforts to rapidly and accurately identify architectures suited to the target task and dataset. To…

Flow Matching (FM) models achieve remarkable results in generative tasks. Building upon diffusion models, FM's simulation-free training paradigm enables simplicity and efficiency but introduces a train-inference gap: model outputs cannot be…

Transformers, the standard implementation for large language models (LLMs), typically consist of tens to hundreds of discrete layers. While more layers can lead to better performance, this approach has been challenged as far from efficient,…

Enhancing the efficiency of high-quality image generation using Diffusion Models (DMs) is a significant challenge due to the iterative nature of the process. Flow Matching (FM) is emerging as a powerful generative modeling paradigm based on…

Accurate segmentation of organs and lesions in medical images is essential for clinical applications including diagnosis, prognosis, and treatment planning. While Vision Transformers (ViTs) have shown impressive segmentation performance,…

Optical flow estimation is a challenging problem remaining unsolved. Recent deep learning based optical flow models have achieved considerable success. However, these models often train networks from the scratch on standard optical flow…

Bridging different modalities lies at the heart of cross-modality generation. While conventional approaches treat the text modality as a conditioning signal that gradually guides the denoising process from Gaussian noise to the target image…

Image Captioning is an important Language and Vision task that finds application in a variety of contexts, ranging from healthcare to autonomous vehicles. As many real-world applications rely on devices with limited resources, much effort…

With the success of language pretraining, it is highly desirable to develop more efficient architectures of good scalability that can exploit the abundant unlabeled data at a lower cost. To improve the efficiency, we examine the…

We present the Fourier-Invertible Neural Encoder (FINE), a compact and interpretable architecture for dimension reduction in translation-equivariant datasets. FINE integrates reversible filters and monotonic activation functions with a…

Simulating fluid flow around arbitrary shapes is key to solving various engineering problems. However, simulating flow physics across complex geometries remains numerically challenging and computationally resource-intensive, particularly…

Optical flow estimation is a crucial subfield of computer vision, serving as a foundation for video tasks. However, the real-world robustness is limited by animated synthetic datasets for training. This introduces domain gaps when applied…