Computer Vision

Ukraine launched a "Logistics Lockdown" campaign using AI-guided Hornet kamikaze drones, developed by US company Swift Beat LLC with backing from former Google CEO Eric Schmidt, to strike Russian fuel tankers, convoys, a…

Avataar AI, a startup selected for India's $1.2 billion India AI Mission, launched a new video generation model called Varya that is 10 times faster and 20 times cheaper than competitors like Veo and Runway. The model, b…

Researchers have developed SalArt-VQA, a diagnostic benchmark to evaluate whether vision-language models (VLMs) truly understand salient artifacts in AI-generated images, rather than just correctly flagging their presenc…

Researchers have developed CD-RCM, the first novel-view synthesis approach specifically for reflectance confocal microscopy (RCM), enabling continuous-depth visualization of human skin from sparse, anisotropic z-stacks. …

Researchers introduced Efficient Continual Alignment (ECA), a new exemplar-free incremental learning approach for open-ended image-to-text generation that adapts alignment modules within pre-trained vision-language model…

Researchers introduced GRIP, a feedback-guided retrieval framework for multimodal in-context learning that selects examples based on their actual impact on model predictions rather than visual similarity. The system impr…

Researchers have developed Context-Centric Feature Fusion (CCFF), a framework that uses two attention-based modules to improve detection of co-occurring objects in autonomous driving. The system achieved a Category-level…

Researchers have identified three critical limitations in existing preference optimization methods for medical Large Vision-Language Models (LVLMs), including their inability to distinguish clinically critical tokens fro…

Researchers introduced PERIA, a tool-augmented visual agent designed to improve spatial reasoning in vision-language models by actively acquiring evidence and performing multi-step visual interactions. The agent uses two…

Researchers introduced FreeBridge, a variational Schrödinger Bridge model that infers continuous cellular transition dynamics from high-content imaging assays where only endpoint populations are observable. By constraini…

Researchers have developed L-VARC, a novel framework that enhances visual reasoning on the Abstraction and Reasoning Corpus (ARC) by integrating a language-guided Learning Using Privileged Information (LUPI) branch. The …

Researchers have developed a Density-Equalizing Convolutional Neural Network (DECNN) that uses learned density functions to dynamically redistribute computational attention toward informative regions in images and surfac…

Researchers have identified that vision-language models (VLMs) often locate relevant text in images but fail to utilize it for answering questions, a phenomenon called "localization-without-utilization." To address this,…

Researchers have developed Bayesian Conditional Priors (BCP) Estimation, a gradient-free test-time adaptation method that improves multi-label recognition with frozen Vision-Language Models under distribution shift. The …

Researchers have developed MAMVI, a new test-time adaptation method for 3D point cloud models that replaces sequential multi-view optimization with a single-step adaptation process. The approach uses a hybrid masking str…

Researchers have developed YOLO-AMC, an improved YOLO architecture integrating attention mechanisms for building crack detection, achieving mAP@0.5 of 0.9917 on test datasets. The model outperforms baseline YOLOv11n and …

Researchers have developed PersonaDrive, a pipeline that conditions vision-language-action driving agents on retrieved demonstrations from a style-instructed human driving dataset to produce aggressive, neutral, or conse…

Researchers have identified a failure mode in multimodal AI systems called "Modal Isolation," where generated images and text reasoning fail to inform each other during complex tasks. The team proposes MoTiF, a two-stage…

Researchers have developed Z-Image Turbo++, a two-step image generation model distilled from an eight-step teacher model, achieving high-fidelity results through three targeted design choices. The method uses teacher-gen…

Researchers have introduced MLUBench, a large-scale benchmark for evaluating lifelong unlearning in multimodal large language models (MLLMs), featuring 127 entities across 9 classes. The benchmark reveals that existing u…