The development of GUI agents could revolutionize the next generation of human-computer interaction. Motivated by this vision, we present MAI-UI, a family of fo...
Prompt-driven Video Segmentation Foundation Models (VSFMs) such as SAM2 are increasingly deployed in applications like autonomous driving and digital pathology,...
The rapid advancement of generative artificial intelligence has enabled the creation of highly realistic fake facial images, posing serious threats to personal ...
Creating physically realistic content in VR often requires complex modeling tools or predefined 3D models, textures, and animations, which present significant b...
Unmanned aerial vehicles (UAVs) are crucial tools for post-disaster search and rescue, facing challenges such as high information density, rapid changes in view...
Article URL: https://github.com/ruvnet/wifi-densepose Comments URL: https://news.ycombinator.com/item?id=46388904 Points: 10 Comments: 1...
LAION-400M is a giant public resource designed to spark new ideas. It consists of about 400 million images paired with short captions, cleaned and CLIP‑filtered...
Overview AutoAugment is a method that automatically discovers effective image augmentation policies. By systematically testing many simple transformations—such...
High-resolution video generation, while crucial for digital media and film, is computationally bottlenecked by the quadratic complexity of diffusion models, mak...
We expose a significant popularity bias in state-of-the-art vision-language models (VLMs), which achieve up to 34% higher accuracy on famous buildings compared ...
We present Streamo, a real-time streaming video LLM that serves as a general-purpose interactive assistant. Unlike existing online video models that focus narro...
Segment Anything Model 2 (SAM2), a vision foundation model has significantly advanced in prompt-driven video object segmentation, yet their practical deployment...
The interpretation of small tiles in large whole slide images (WSI) often needs a larger image context. We introduce TICON, a transformer-based tile representat...
The data processing inequality is an information-theoretic principle stating that the information content of a signal cannot be increased by processing the obse...
Graphical user interface (GUI) agents can substantially improve productivity by automating frequently executed long-latency tasks on mobile devices. However, ex...
Structured data extraction from tables plays a crucial role in document image analysis for scanned documents and digital archives. Although many methods have be...
Modern surgical systems increasingly rely on intelligent scene understanding to provide timely situational awareness for enhanced intra-operative safety. Within...
Modern deep learning methods typically treat image sequences as large tensors of sequentially stacked frames. However, is this straightforward representation id...
In hard-label black-box adversarial attacks, where only the top-1 predicted label is accessible, the prohibitive query complexity poses a major obstacle to prac...
State-of-the-art video generative models typically learn the distribution of video latents in the VAE space and map them to pixels using a VAE decoder. While th...
Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods...
Cognitive science suggests that spatial ability develops progressively-from perception to reasoning and interaction. Yet in multimodal LLMs (MLLMs), this hierar...
Current video avatar generation methods excel at identity preservation and motion alignment but lack genuine agency, they cannot autonomously pursue long-term g...
This paper proposes FedPOD (Proportionally Orchestrated Derivative) for optimizing learning efficiency and communication cost in federated learning among multip...
Point tracking aims to localize corresponding points across video frames, serving as a fundamental task for 4D reconstruction, robotics, and video editing. Exis...
We introduce Cube Bench, a Rubik's-cube benchmark for evaluating spatial and sequential reasoning in multimodal large language models (MLLMs). The benchmark dec...
Simulators can generate virtually unlimited driving data, yet imitation learning policies in simulation still struggle to achieve robust closed-loop performance...
Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and su...
Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object g...
3D image display is essential for next-generation volumetric imaging; however, dense depth multiplexing for 3D image projection remains challenging because diff...
We propose a Vision-Language Simulation Model (VLSM) that unifies visual and textual understanding to synthesize executable FlexScript from layout sketches and ...
Deep representations across modalities are inherently intertwined. In this paper, we systematically analyze the spectral characteristics of various semantic and...
Generating realistic human-human interactions is a challenging task that requires not only high-quality individual body and hand motions, but also coherent coor...
We introduce Perception Encoder Audiovisual, PE-AV, a new family of encoders for audio and video understanding trained with scaled contrastive learning. Built o...
Recently, the introduction of Chain-of-Thought (CoT) has largely improved the generation ability of unified models. However, it is observed that the current thi...
We build the first system to address the problem of reconstructing in-scene object manipulation from a monocular RGB video. It is challenging due to ill-posed s...
While Multimodal Large Language Models (MLLMs) have achieved impressive performance on semantic tasks, their spatial intelligence--crucial for robust and ground...
Autoregressive (AR) visual generation relies on tokenizers to map images to and from discrete sequences. However, tokenizers are trained to reconstruct clean im...
Generating long-range, geometrically consistent video presents a fundamental dilemma: while consistency demands strict adherence to 3D geometry in pixel space, ...
Background: High-resolution MRI is critical for diagnosis, but long acquisition times limit clinical use. Super-resolution (SR) can enhance resolution post-scan...
We leverage multimodal large language models (LLMs) to construct a dataset of 306,070 German patents (1877-1918) from 9,562 archival image scans using our LLM-b...
Diabetic retinopathy (DR) is a leading cause of preventable blindness worldwide, demanding accurate automated diagnostic systems. While general-domain vision-la...
While Multimodal Large Language Models have achieved human-like performance on many visual and textual reasoning tasks, their proficiency in fine-grained spatia...
Recent breakthroughs in self-supervised Joint-Embedding Predictive Architectures (JEPAs) have established that regularizing Euclidean representations toward iso...
Overview YOLOv6 is a new step in object detection designed for factories, stores, and cameras everywhere. Built by a team focused on speed and reliability, it...
Vision-Language-Action (VLA) models align vision and language with embodied control, but their object referring ability remains limited when relying solely on t...
Artistic style transfer in generative models remains a significant challenge, as existing methods often introduce style only via model fine-tuning, additional a...
Multimodal Large Language Models (MLLMs) combine visual and textual representations to enable rich reasoning capabilities. However, the high computational cost ...
