Related papers: FastDINOv2: Frequency Based Curriculum Learning Im…

The advent of large-scale vision foundation models, pre-trained on diverse natural images, has marked a paradigm shift in computer vision. However, how the frontier vision foundation models' efficacies transfer to specialised domains such…

We introduce InternVideo2, a new family of video foundation models (ViFM) that achieve the state-of-the-art results in video recognition, video-text tasks, and video-centric dialogue. Our core design is a progressive training approach that…

The rapid advancement of generative models has introduced serious risks, including deepfake techniques for facial synthesis and editing. Traditional approaches rely on training classifiers and enhancing generalizability through various…

Birds Eye View perception models require extensive data to perform and generalize effectively. While traditional datasets often provide abundant driving scenes from diverse locations, this is not always the case. It is crucial to maximize…

Demand for 2K video synthesis is rising with increasing consumer expectations for ultra-clear visuals. While diffusion transformers (DiTs) have demonstrated remarkable capabilities in high-quality video generation, scaling them to 2K…

Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for…

Reliable plant species and damage segmentation for herbicide field research trials requires models that can withstand substantial real-world variation across seasons, geographies, devices, and sensing modalities. Most deep learning…

Object detection in civil engineering applications is constrained by limited annotated data in specialized domains. We introduce DINO-YOLO, a hybrid architecture combining YOLOv12 with DINOv3 self-supervised vision transformers for…

We introduce Motif-2-12.7B, a new open-weight foundation model that pushes the efficiency frontier of large language models by combining architectural innovation with system-level optimization. Designed for scalable language understanding…

There are increasing interests of studying the video-to-depth (V2D) problem with machine learning techniques. While earlier methods directly learn a mapping from images to depth maps and camera poses, more recent works enforce multi-view…

Text-based web agents offer computational efficiency for autonomous web navigation, yet developing robust agents remains challenging due to the noisy and heterogeneous nature of real-world HTML. Standard Supervised Fine-Tuning (SFT)…

Vision-language models, such as CLIP, have achieved significant success in aligning visual and textual representations, becoming essential components of many multi-modal large language models (MLLMs) like LLaVA and OpenFlamingo. However,…

This paper introduces a new architectural framework, known as input fast-forwarding, that can enhance the performance of deep networks. The main idea is to incorporate a parallel path that sends representations of input values forward to…

Multi-task image restoration has gained significant interest due to its inherent versatility and efficiency compared to its single-task counterpart. However, performance decline is observed with an increase in the number of tasks, primarily…

Face recognition systems are increasingly used in biometric security for convenience and effectiveness. However, they remain vulnerable to spoofing attacks, where attackers use photos, videos, or masks to impersonate legitimate users. This…

With Vision Transformers (ViTs) making great advances in a variety of computer vision tasks, recent literature have proposed various variants of vanilla ViTs to achieve better efficiency and efficacy. However, it remains unclear how their…

Denoising is a fundamental imaging problem. Versatile but fast filtering has been demanded for mobile camera systems. We present an approach to multiscale filtering which allows real-time applications on low-powered devices. The key idea is…

We present DINO-Tracker -- a new framework for long-term dense tracking in video. The pillar of our approach is combining test-time training on a single video, with the powerful localized semantic features learned by a pre-trained DINO-ViT…

The foundation models have recently shown excellent performance on a variety of downstream tasks in computer vision. However, most existing vision foundation models simply focus on image-level pretraining and adpation, which are limited for…

Deploying multiple machine learning models on resource-constrained robotic platforms for different perception tasks often results in redundant computations, large memory footprints, and complex integration challenges. In response, this work…