How can we tell whether a video has been sped up or slowed down? How can we generate videos at different speeds? Although videos have been central to modern com...
Understanding human activities and their surrounding environments typically relies on visual perception, yet cameras pose persistent challenges in privacy, safe...
We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representations. We ...
We present Vista4D, a robust and flexible video reshooting framework that grounds the input video and target cameras in a 4D point cloud. Specifically, given an...
Despite impressive progress in capabilities of large vision-language models (LVLMs), these systems remain vulnerable to hallucinations, i.e., outputs that are n...
Humans and modern vision models can reach similar classification accuracy while making systematically different kinds of mistakes - differing not in how often t...
In recent years, significant progress has been made in both image generation and generated image detection. Despite their rapid, yet largely independent, develo...
The ability of generative AI (GenAI) methods to photorealistically alter camera images has raised awareness about the authenticity of images shared online. Inte...
Self-supervised learning (SSL) is a standard approach for representation learning in aerial imagery. Existing methods enforce invariance between augmented views...
I’m unable to convert the article because the provided content is a binary PDF stream rather than extractable text. Please supply the article’s text for example...
Recent advances in video generative models enable the synthesis of realistic human-object interaction videos across a wide range of scenarios and object categor...
Federated learning (FL) enables collaborative model training without sharing raw data; however, the presence of noisy labels across distributed clients can seve...
The offshore wind energy sector is expanding rapidly, increasing the need for independent, high-temporal-resolution monitoring of infrastructure deployment and ...
Reinforcement Learning (RL) post-training has become the standard for aligning generative models with human preferences, yet most methods rely on a single scala...
Transformer-based OCR models have shown strong performance on Latin and CJK scripts, but their application to African syllabic writing systems remains limited. ...
Large vision-language models (LVLMs) have made substantial advances in reasoning tasks at the Olympiad level. Nevertheless, current Olympiad-level multimodal re...
Reconstructing 3D Human-Object Interaction from an RGB image is essential for perceptive systems. Yet, this remains challenging as it requires capturing the sub...
We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a natively integr...
Reconstructing dynamic 3D scenes from sparse multi-view videos is highly ill-posed, often leading to geometric collapse, trajectory drift, and floating artifact...
Space-time self-similarity (STSS), which captures visual correspondences across frames, provides an effective way to represent temporal dynamics for video under...
Recent advances in image generation and editing have opened new opportunities for virtual try-on. However, existing methods still struggle to meet complex real-...
Sparse-view 3D reconstruction is essential for modeling scenes from casual captures, but remain challenging for non-generative reconstruction. Existing diffusio...
We address the problem of generating a 3D-consistent, navigable environment that is spatially grounded: a simulation of a real location. Existing video generati...
Training modern neural networks often relies on large learning rates, operating at the edge of stability, where the optimization dynamics exhibit oscillatory an...
Conditional medical image generation plays an important role in many clinically relevant imaging tasks. However, existing methods still face a fundamental chall...
We present VLA Foundry, an open-source framework that unifies LLM, VLM, and VLA training in a single codebase. Most open-source VLA efforts specialize on the ac...
Human video generation remains challenging due to the difficulty of jointly modeling human appearance, motion, and camera viewpoint under limited multi-view dat...
Distribution networks with high penetration of Distributed Energy Resources (DERs) increasingly rely on communication networks to coordinate grid-interactive co...
Vision-Language-Action (VLA) models offer a promising autonomous driving paradigm for leveraging world knowledge and reasoning capabilities, especially in long-...
Accurate reconstruction and tracking of dynamic human faces from image sequences is challenging because non-rigid deformations, expression changes, and viewpoin...
At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllabil...
Building photorealistic, animatable full-body digital humans remains a longstanding challenge in computer graphics and vision. Recent advances in animatable ava...
Story Visualization aims to generate a sequence of images that faithfully depicts a textual narrative that preserve character identity, spatial configuration, a...
Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, which hurts...
The Platonic Representation Hypothesis suggests that neural networks trained on different modalities (e.g., text and images) align and eventually converge towar...
Video world models have achieved remarkable success in simulating environmental dynamics in response to actions by users or agents. They are modeled as action-c...
Reasoning segmentation requires models to ground complex, implicit textual queries into precise pixel-level masks. Existing approaches rely on a single segmenta...
Controllable cooperative humanoid manipulation is a fundamental yet challenging problem for embodied intelligence, due to severe data scarcity, complexities in ...
In recent years, the Vision Transformer (ViT) has garnered significant attention within the computer vision community. However, the core component of ViT, Self-...
The rapid progress of subject-driven text-to-image synthesis, and in particular DreamBooth, has enabled a consent-free deepfake pipeline: an adversary needs onl...
Uniform Discrete Diffusion Model (UDM) has recently emerged as a promising paradigm for discrete generative modeling; however, its integration with reinforcemen...
A robust Multimodal Large Language Model (MLLM) for Earth Observation should maintain consistent interpretation and reasoning under realistic input variations. ...
Personalized image aesthetics assessment (PIAA) aims to predict an individual user's subjective rating of an image, which requires modeling user-specific aesthe...
Unrecovered e-waste represents a significant economic loss. Hard disk drives (HDDs) comprise a valuable e-waste stream necessitating robotic disassembly. Automa...
Breast cancer diagnosis demands rapid and precise tools, yet traditional histopathological methods often fall short in intra-operative settings. Deep Ultraviole...
Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing ...
Introduction In Part 1 of this series we introduced the architecture of the ASL‑to‑voice translation system—a five‑stage pipeline that turns real‑time webcam v...
We introduce LaviGen, a framework that repurposes 3D generative models for 3D layout generation. Unlike previous methods that infer object layouts from textual ...
