The evolution of biological morphology is critical for understanding the diversity of the natural world, yet traditional analyses often involve subjective biase...
Overview Every Series 5 BrightSign player except the XC line ships with an onboard Neural Processing Unit NPU. Most people don’t know this, and even fewer have...
Multimodal Large Language Models (MLLMs) suffer from severe training inefficiency issue, which is associated with their massive model sizes and visual token num...
A key challenge in autoregressive image generation is to efficiently sample independent locations in parallel, while still modeling mutual dependencies with ser...
Assisting non-expert users to develop complex interactive websites has become a popular task for LLM-powered code agents. However, existing code agents tend to ...
Existing methods for human motion control in video generation typically rely on either 2D poses or explicit 3D parametric models (e.g., SMPL) as control signals...
Human vision is foveated, with variable resolution peaking at the center of a large field of view; this reflects an efficient trade-off for active sensing, allo...
Stereo matching is a core problem in computer vision, and performance matters, especially when working with large images or real‑time systems. This post shares...
Pixel diffusion generates images directly in pixel space in an end-to-end manner, avoiding the artifacts and bottlenecks introduced by VAEs in two-stage latent ...
Deep learning based auto segmentation is increasingly used in radiotherapy, but conventional models often produce anatomically implausible false positives, or h...
Frontier models are transitioning from multimodal large language models (MLLMs) that merely ingest visual information to unified multimodal models (UMMs) capabl...
Reranking is a critical component of modern retrieval systems, which typically pair an efficient first-stage retriever with a more expressive model to refine re...
Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing...
Tropical forests harbor most of the planet's tree biodiversity and are critical to global ecological balance. Canopy trees in particular play a disproportionate...
Out-of-distribution (OOD) detection is critical for the safe deployment of deep neural networks. State-of-the-art post-hoc methods typically derive OOD scores f...
Model editing aims to correct errors in large, pretrained models without altering unrelated behaviors. While some recent works have edited vision-language model...
Simulating deformable objects under rich interactions remains a fundamental challenge for real-to-sim robot manipulation, with dynamics jointly driven by enviro...
Human motion analysis tasks, such as temporal 3D pose estimation, motion prediction, and motion in-betweening, play an essential role in computer vision. Howeve...
Carbon Robotics' Large Plant Model will allow farmers to kill new types of weeds without having to retrain the machines....
Coronary artery stenosis is a leading cause of cardiovascular disease, diagnosed by analyzing the coronary arteries from multiple angiography views. Although nu...
Advertising image generation has increasingly focused on online metrics like Click-Through Rate (CTR), yet existing approaches adopt a ``one-size-fits-all' stra...
Recent genomic foundation models largely adopt large language model architectures that treat DNA as a one-dimensional token sequence. However, exhaustive sequen...
World models have demonstrated significant promise for data synthesis in autonomous driving. However, existing methods predominantly concentrate on single-modal...
Reconstructing 3D scenes from sparse images remains a challenging task due to the difficulty of recovering accurate geometry and texture without optimization. R...
Struggling with dull, poorly lit raw product photos that don’t sell? In 2026, AI product‑photography enhancement lets you turn raw shots into studio‑quality ima...
While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulti...
Open-set object detection (OSOD) localizes objects while identifying and rejecting unknown classes at inference. While recent OSOD models perform well on benchm...
Astronomical imaging remains noise-limited under practical observing constraints, while standard calibration pipelines mainly remove structured artifacts and le...
Despite rapid advances in autonomous AI scientists powered by language models, generating publication-ready illustrations remains a labor-intensive bottleneck i...
Vision-language models suffer performance degradation under domain shift, limiting real-world applicability. Existing test-time adaptation methods are computati...
Vision-language models (VLMs) demonstrate impressive performance on standard video understanding benchmarks yet fail systematically on simple reasoning tasks th...
In recent years, large language models (LLMs) have made rapid progress in information retrieval, yet existing research has mainly focused on text or static mult...
Existing multimodal large language models for long-video understanding predominantly rely on uniform sampling and single-turn inference, limiting their ability ...
While dense pixel-wise annotations remain the gold standard for medical image segmentation, they are costly to obtain and limit scalability. In contrast, many d...
Despite recent Multimodal Large Language Models (MLLMs)' linguistic prowess in medical diagnosis, we find even state-of-the-art MLLMs suffer from a critical per...
Early-exit neural networks have become popular for reducing inference latency by allowing intermediate predictions when sufficient confidence is achieved. Howev...
Modern diffusion/flow-based models for image generation typically exhibit two core characteristics: (i) using multi-step sampling, and (ii) operating in a laten...
We introduce UEval, a benchmark to evaluate unified models, i.e., models capable of generating both images and text. UEval comprises 1,000 expert-curated questi...
Manipulating dynamic objects remains an open challenge for Vision-Language-Action (VLA) models, which, despite strong generalization in static manipulation, str...
Large Vision-Language Models (VLMs) often answer classic visual illusions 'correctly' on original images, yet persist with the same responses when illusion fact...
Audio-Visual Foundation Models, which are pretrained to jointly generate sound and visual content, have recently shown an unprecedented ability to model multi-m...
In pruning, the Lottery Ticket Hypothesis posits that large networks contain sparse subnetworks, or winning tickets, that can be trained in isolation to match t...
Full-image relighting remains a challenging problem due to the difficulty of collecting large-scale structured paired data, the difficulty of maintaining physic...
Pancreatic ductal adenocarcinoma (PDAC), one of the deadliest solid malignancies, is often detected at a late and inoperable stage. Retrospective reviews of pre...
Current generative video models excel at producing novel content from text and image prompts, but leave a critical gap in editing existing pre-recorded videos, ...
Creative image generation has emerged as a compelling area of research, driven by the need to produce novel and high-quality images that expand the boundaries o...
We've all been there: staring at a delicious plate of pasta, trying to manually log every gram into a fitness app. It’s tedious, prone to 'optimistic' human err...
Agentic Vision is a new capability for the Gemini 3 Flash model to make image-related tasks more accurate by “grounding answers in visual evidence.” more…...
