Computer Vision

Researchers propose a training-free IBA framework for Knowledge-Based VQA that decouples entity identification from evidence re-ranking, outperforming fine-tuned baselines on Encyclopedic-VQA and InfoSeek while reducing …

Researchers introduced Sol Video Inference Engine, an agent-native full-stack acceleration framework for video diffusion models that achieves over 2x end-to-end speedup with near-lossless quality across models from 2B to…

Researchers developed a hybrid machine learning approach combining EfficientNetB0 feature extraction with Random Forest classification to achieve 94.58% accuracy and sub-millisecond inference for real-time melt pool moni…

Researchers introduced EPEdit, an efficient photo editor that combines generative AI with a user-friendly interface for tasks like object replacement, background modification, and region-specific editing. The system uses…

Researchers propose Forensic Knowledge Graphs (FKGs) to unify forensic evidence extraction, structured reasoning, and interpretable explanations for image authentication. The framework outperforms existing forensic detec…

Researchers introduced Token-to-Token alignment, a framework that establishes explicit semantic correspondence between tokens across prompts in text-to-image models. The method rephrases prompts into a structured form an…

Researchers propose Progressive Pixel-Neighborhood Deformable Cross-Attention (PNAFusion) for multispectral object detection, achieving state-of-the-art results on FLIR, M3FD, and DroneVehicle datasets while reducing GPU…

Researchers introduced OmniPath, a multi-modal agentic framework that audits wheelchair accessibility by fusing OpenStreetMap data with aerial LiDAR to create high-fidelity 3D models. The system analyzes pedestrian surfa…

Researchers introduced ReMMD, a framework for realistic multilingual multi-image agentic verification to detect multimodal misinformation. The framework includes a benchmark with 500 samples and 2,756 images across five …

Researchers introduced DriveStack-VLA, a framework that enhances Vision-Language-Action driving models with Bird-Eye-View representations and Render-Teacher Alignment to improve spatial intelligence. The model achieved s…

Researchers propose ObsGraph, a hierarchical scene graph that unifies scene representation, retrieval, and exploration for embodied reasoning. The system organizes visual evidence into room-view-object layers and uses co…

Baidu released Unlimited-OCR, a new model that uses Reference Sliding Window Attention to parse up to 40 PDF pages in a single inference pass, eliminating the linear memory growth of traditional LLM-based OCR decoders. T…

A developer built a real-time gesture-controlled invisibility cloak using Python, MediaPipe, and OpenCV. The system uses hand gestures such as a pinch to create a moving portal of invisibility or an open left hand to ful…

Researchers released DiffusionBench, a unified codebase for holistic evaluation of generative diffusion transformers across tasks like ImageNet and text-to-image generation. The benchmark supports training and evaluation…

A developer built Fig0, an AI tool that automates the creation of scientific illustrations from hand-drawn sketches or text descriptions. The tool generates clean, vector schematics that remain editable in formats like S…

Plot.so, an AI-powered video social listening platform, has raised $14 million in seed funding to help enterprise marketing teams monitor user-generated video content across platforms. The platform uses multi-modal analy…

ByteDance released Seedance 2.5, an AI video generation model capable of producing 30-second native clips with up to 50 multimodal references. The model addresses key limitations in AI video workflows, including short cl…

Zhipu AI released GLM 5.2, a 744-billion-parameter mixture-of-experts open-weight model that outperforms Claude Opus on visual design tasks at lower cost. The model features a longer context window, improved vision-langu…

Google Home will update its facial recognition feature on June 23rd to identify people using body size and clothing color when faces aren't visible, and will automatically update Familiar Faces libraries with recent imag…

Mistral released OCR 4, a multilingual document extraction model supporting 170 languages with bounding boxes, block classification, and confidence scores. The model outperforms competitors on rare languages and is avail…