Computer Vision

Researchers propose DinoLink, a token-centric compression framework that reduces bitrate by 139x for collaborative V2X perception while maintaining 32.8% mAP on nuScenes, achieving 34.5x acceleration in narrow-band envir…

Researchers propose ForeAgent, an agentic forensics framework for AI-generated image detection that uses a Perception-Verdict architecture and a Hindsight-Driven Self-Refining strategy to iteratively improve. The system …

Researchers developed a multimodal deep learning model for methane-plume segmentation from hyperspectral satellite imagery, integrating a feature-guided methane enhancement mechanism into transformer-based RGB representa…

Researchers introduced CRISP, a new evaluation paradigm that diagnoses visual spatial intelligence in vision-language models by measuring consistency between implicit perception and explicit reasoning. The study found th…

Researchers introduced the Frame Forgetting Network (FFN) for test-time training on long videos, using only three frames per sliding window to reduce computational cost. The model defines a surprise metric to adaptively …

Researchers present the first systematic survey of unified vision-language perception in Multimodal Large Language Models (MLLMs), tracing the paradigm evolution through a five-stage taxonomy and identifying open challen…

Researchers developed an attention-based, physics-guided convolutional neural network to predict microstructural evolution in binary mixtures governed by the Cahn-Hilliard equation. The surrogate model accurately forecas…

Researchers developed a hybrid approach combining image processing and deep learning to assess fruit freshness, achieving over 90% accuracy in real-time classification of apples and oranges. The method uses a CNN for bin…

Researchers extended fMRI cognitive taskonomy from single-source to multi-source transfer across 23 Human Connectome Project task states, training 1,127 models. They found that motor states transfer well within their par…

Researchers developed topology-informed neural networks that integrate topological data analysis with deep learning to improve flood detection in satellite imagery, achieving more robust and interpretable results on the …

Researchers introduced PhyEditBench, a benchmark for evaluating physics-aware image editing in generative models, revealing significant limitations in current state-of-the-art methods. The benchmark includes 238 real-wor…

Researchers introduced Neural Voxel Dynamics, a self-supervised framework that learns implicit 3D physics from video by lifting 2D features into a volumetric latent space. The method achieves long-term structural stabili…

Researchers developed a multi-task spatiotemporal deep neural network that predicts penetration depth and weld seam morphology in laser welding with high accuracy, achieving 99.35% accuracy for penetration state and 95.6…

Firefly launched the AIBOX-9075, an industrial Edge AI box powered by the Qualcomm DragonWing IQ-9075 SoC delivering up to 200 TOPS at INT8, with 36GB ECC memory and 8x GMSL2 camera inputs, priced at $1,239. The ruggediz…

A fully autonomous humanoid robot penalty shootout at MWC Shanghai 2026 drew over 10,000 spectators, with eight Chinese embodied AI teams competing across nearly 100 rounds. The event, which banned remote control and pre…

Researchers at a major AI lab trained a 350M-parameter generative world model on 210 tasks and found that hallucination in world models is predictable and preventable, primarily a data-coverage problem. They introduced M…

A developer explores the uncanny valley of AI-generated children's books, highlighting how current generative models produce surreal and unsettling illustrations that veer into body horror. The project demonstrates the g…

Researchers used AI and virtual unwrapping to reveal texts inside charred Roman scrolls buried by Mount Vesuvius in 79 A.D., opening a new window into the ancient world. NBC News reported on the discovery on June 26, 202…

Reka AI released CS2-10k, a large-scale egocentric dataset built from professional Counter-Strike 2 matches, containing over 600,000 player-round videos totaling 10,000+ hours of first-person footage with per-frame annot…

Reka released CS2-10k, a large-scale dataset and rendering pipeline built from Counter-Strike 2 professional match demos, providing over 10,000 hours of egocentric video with per-frame action annotations to advance world…