Computer Vision

Researchers propose TeleMorpher, a one-shot framework for simultaneous motion-location editing in videos, addressing a gap in diffusion model-based editing. The method disentangles protagonist and background, uses motion…

Researchers propose LEAP, a training curriculum for Vision Transformer feature-based knowledge distillation that uses the teacher's intermediate feature maps as progressively difficult targets. LEAP achieves 90.1% accura…

Researchers propose REVEAL++, a differentiable phenotypic grouping method for vision-language retinal modeling that improves Alzheimer's disease risk prediction by treating phenotypic similarity as a continuous, learnabl…

Researchers propose HypOProto, a hyperbolic prototype-based framework for interpretable left ventricular filling pressure classification from B-mode echocardiography, achieving state-of-the-art performance while maintain…

Researchers propose VFACamou, an end-to-end framework for generating adversarial camouflage that remains effective under UAV reconnaissance with changing viewpoints, poses, and lighting. The method integrates UV-volume r…

Researchers propose QueryGaussian, a training-free framework for open-vocabulary 3D instance retrieval that decouples semantic understanding from geometric representation, enabling efficient retrieval in city-scale scene…

Researchers introduced Language-Instructed Vision Embeddings (LIVE), a method that uses language to dynamically guide vision encoders, eliminating the need for task-specific retraining. LIVE reduced visual hallucinations…

FocusOnFun team's Vortex system achieved 90.5% in the Preliminary Round and 'Excellent' overall performance with 'Outstanding' QA results at the Ho Chi Minh City AI Challenge 2025. The multimodal video retrieval system i…

Researchers propose a one-shot novel view and pose human image synthesis method using a conditional denoising diffusion model guided by 3D human priors. The approach outperforms existing techniques on public datasets and…

Researchers introduced GLARE, an LLM-based natural language interface that translates user questions into SQL queries over local explanation data to provide global explanations for black-box image classifiers. The system…

Researchers propose Conditional-Composition Domain Match (CCDM), a training-free metric family that predicts the utility of synthetic data for object detection, achieving a Spearman correlation of 1.0 with YOLOv8 perform…

Researchers introduced BrainG3N, a dual-purpose tokenizer for 3D brain MRI generation that decouples encoder and decoder using a masked-autoencoder, enabling both clinically informative embeddings and anatomically faithf…

Researchers introduced LaViSA, a benchmark to evaluate vision-language models' ability to resolve structural ambiguity using visual scenes. Tests on proprietary and open-source models showed they can partially leverage v…

Researchers at arXiv analyzed the performance of Med-DDPM, a 3D generative diffusion model for MRI synthesis, across three generations of NVIDIA GPUs. They identified inefficiencies in memory access and Tensor Core utili…

Researchers propose ImageWAM, a world action model that replaces video generation with image editing for robot control, achieving superior performance while reducing computational cost to 1/6 FLOPs and 1/4 latency of vid…

Researchers introduced LooseControlVideo, a framework that uses sparse, oriented 3D boxes as a proxy for spatial blocking in text-to-video generation, enabling intuitive control over layout and trajectory. Fine-tuned on …

Researchers propose ProMUSE, a progressive multi-modal uncertainty-guided network for Alzheimer's disease classification that adaptively determines when additional imaging modalities are needed, reducing MRI/PET usage by…

Researchers propose a method to learn asynchronous denoising schedules for multi-representation diffusion models, improving visual synthesis. On ImageNet 256x256, their approach achieves FID 1.05 with 4x less training th…

A developer built IA Code Studio, a real-time multiplayer 3D IDE with WebRTC voice chat and AI prompt-to-3D generation. The platform integrates a Monaco editor with an AI co-pilot for Three.js scenes, Firebase-powered mu…

Luma Ray 3.2 Image to Video defeated Bernini-R Edit Video 16.2 to 12.3 in a head-to-head comparison of two AI video generation models, based on two fresh video tasks scored by GPT-5.4. Luma delivered superior mood, conti…