The recently introduced ZACH-ViT (Zero-token Adaptive Compact Hierarchical Vision Transformer) formalized a compact permutation-invariant Vision Transformer for...
Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable...
Video streaming analytics is a crucial workload for vision-language model serving, but the high cost of multimodal inference limits scalability. Prior systems r...
Neural network pruning can be formulated as a combinatorial optimization problem, yet most existing approaches rely on greedy heuristics that ignore complex int...
We present Vanast, a unified framework that generates garment-transferred human animation videos directly from a single human image, garment images, and a pose ...
Scene-level point cloud understanding remains challenging due to diverse geometries, imbalanced category distributions, and highly varied spatial layouts. Exist...
Local feature matching has long been a fundamental component of 3D vision systems such as Structure-from-Motion (SfM), yet progress has lagged behind the rapid ...
Most vision-language models (VLMs) apply a large language model (LLM) as the decoder, where the response tokens are generated sequentially through autoregressio...
In this paper, we explore the design space of procedural rules for multi-view stereo (MVS). We demonstrate that we can generate effective training data using Si...
Pre-trained diffusion models have enabled significant advancements in All-in-One Restoration (AiOR), offering improved perceptual quality and generalization. Ho...
Extended reasoning in large language models (LLMs) creates severe KV cache memory bottlenecks. Leading KV cache compression methods estimate KV importance using...
What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks? The strongest vision-language model...
Anticipating diverse future states is a central challenge in video world modeling. Discriminative world models produce a deterministic prediction that implicitl...
Image spatial editing performs geometry-driven transformations, allowing precise control over object layout and camera viewpoints. Current models are insufficie...
Coworking AI agents operating within local file systems are rapidly emerging as a paradigm in human-AI interaction; however, effective personalization remains l...
In Scientific Computing and modern Machine Learning (ML) workloads, sequences of dependent General Matrix Multiplications (GEMMs) often dominate execution time....
!QR codehttps://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fup...
Spiking Neural Networks (SNNs) offer a promising solution for energy-efficient edge intelligence; however, their hardware deployment is constrained by memory ov...
Recent vision-language models (VLMs) typically rely on a single vision encoder trained with contrastive image-text objectives, such as CLIP-style pretraining. W...
Most of the recent generative image super-resolution (SR) methods rely on adapting large text-to-image (T2I) diffusion models pretrained on web-scale text-image...
Non-contrast chest CTs offer a rich opportunity for both conventional pulmonary and opportunistic extra-pulmonary screening. While Multi-Task Learning (MTL) can...
Remote sensing segmentation in real deployment is inherently continual: new semantic categories emerge, and acquisition conditions shift across seasons, cities,...
Three-dimensional medical image data and computer-aided decision making, particularly using deep learning, are becoming increasingly important in the medical fi...
This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this chall...
Scaling Vision-Language-Action (VLA) models by upgrading the vision encoder is expected to improve downstream manipulation performance--as it does in vision-lan...
Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies overlook one...
The recent success of reinforcement learning (RL) in large reasoning models has inspired the growing adoption of RL for post-training Multimodal Large Language ...
Object detection in unmanned aerial vehicle (UAV) images remains a highly challenging task, primarily caused by the complexity of background noise and the imbal...
We introduce a wavelength-multiplexed massively parallel diffractive information storage platform composed of dielectric surfaces that are structurally optimize...
We propose EventHub, a novel framework for training deep-event stereo networks without ground truth annotations from costly active sensors, relying instead on s...
Recent advances in video diffusion have enabled the development of 'world models' capable of simulating interactive environments. However, these models are larg...
Scaling generative inverse and forward rendering to real-world scenarios is bottlenecked by the limited realism and temporal coherence of existing synthetic dat...
We present ModMap, a natively multiview and multimodal framework for 3D anomaly detection and segmentation. Unlike existing methods that process views independe...
Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retriev...
Existing visual grounding benchmarks primarily evaluate alignment between image regions and literal referring expressions, where models can often succeed by mat...
High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. On the one hand, multi-view studio data enables high-fidelity mo...
Training-free Vision-Language Navigation (VLN) agents powered by foundation models can follow instructions and explore 3D environments. However, existing approa...
Recent streaming video understanding methods increasingly rely on complex memory mechanisms to handle long video streams. We challenge this trend with a simple ...
Existing video object removal methods excel at inpainting content 'behind' the object and correcting appearance-level artifacts such as shadows and reflections....
Recent multimodal large language models have achieved strong performance in unified text and image understanding and generation, yet extending such native capab...
Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propag...
We present HippoCamp, a new benchmark designed to evaluate agents' capabilities on multimodal file management. Unlike existing agent benchmarks that focus on ta...
Reconstructing full spatio-temporal dynamics from sparse observations in both space and time remains a central challenge in complex systems, as measurements can...
We present TRACE, a mesh-guided 3DGS editing framework that achieves automated, high-fidelity scene transformation. By anchoring video diffusion with explicit 3...
Primitive-based methods such as 3D Gaussian Splatting have recently become the state-of-the-art for novel-view synthesis and related reconstruction tasks. Compa...
This study investigates the ability of multimodal Large Language Models (LLMs) to identify and interpret misleading visualizations, and recognize these observat...
Foundation vision-language models are becoming increasingly relevant to robotics because they can provide richer semantic perception than narrow task-specific p...
Although self-supervised 3D anomaly detection assumes that acquiring high-precision point clouds is computationally expensive, in real manufacturing scenarios i...
