Related papers: OmniAlpha: Aligning Transparency-Aware Generation …
Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based…
Recent vision-language-action (VLA) models build upon vision-language foundations, and have achieved promising results and exhibit the possibility of task generalization in robot manipulation. However, due to the heterogeneity of tactile…
The heightened emphasis on the regulation of deep generative models, propelled by escalating concerns pertaining to privacy and compliance with regulatory frameworks, underscores the imperative need for precise control mechanisms over these…
While Retrieval Augmented Generation (RAG) is now widely adopted to enhance LLMs, evaluating its true performance benefits in a reproducible and interpretable way remains a major hurdle. Existing methods often fall short: they lack domain…
Designing a single model to address multiple tasks has been a long-standing objective in artificial intelligence. Recently, large language models have demonstrated exceptional capability in solving different tasks within the language…
Panoramic image processing is essential for omni-context perception, yet faces constraints like distortions, perspective occlusions, and limited annotations. Previous unsupervised domain adaptation methods transfer knowledge from labeled…
With the rise of diffusion models, audio-video generation has been revolutionized. However, most existing methods rely on separate modules for each modality, with limited exploration of unified generative architectures. In addition, many…
Recently, visually-situated text parsing (VsTP) has experienced notable advancements, driven by the increasing demand for automated document understanding and the emergence of Generative Large Language Models (LLMs) capable of processing…
Current multimodal medical image fusion typically assumes that source images are of high quality and perfectly aligned at the pixel level. Its effectiveness heavily relies on these conditions and often deteriorates when handling misaligned…
Large-scale generative models have shown impressive image-generation capabilities, propelled by massive data. However, this often inadvertently leads to the generation of harmful or inappropriate content and raises copyright concerns.…
This work presents an attack-aware deepfake and image-forensics detector designed for robustness, well-calibrated probabilities, and transparent evidence under realistic deployment conditions. The method combines red-team training with…
The field of visual question answering (VQA) has recently seen a surge in research focused on providing explanations for predicted answers. However, current systems mostly rely on separate models to predict answers and generate…
We present UniMotion, to our knowledge the first unified framework for simultaneous understanding and generation of human motion, natural language, and RGB images within a single architecture. Existing unified models handle only restricted…
Tremendous progress in deep generative models has led to photorealistic image synthesis. While achieving compelling results, most approaches operate in the two-dimensional image domain, ignoring the three-dimensional nature of our world.…
The multi-agent pathfinding (MAPF) problem seeks collision-free paths for a team of agents from their current positions to their pre-set goals in a known environment, and is an essential problem found at the core of many logistics,…
In the portrait matting, the goal is to predict an alpha matte that identifies the effect of each pixel on the foreground subject. Traditional approaches and most of the existing works utilized an additional input, e.g., trimap, background…
Creating an effective representation space is crucial for mitigating the curse of dimensionality, enhancing model generalization, addressing data sparsity, and leveraging classical models more effectively. Recent advancements in automated…
Natural image matting algorithms aim to predict the transparency map (alpha-matte) with the trimap guidance. However, the production of trimap often requires significant labor, which limits the widespread application of matting algorithms…
AI technologies are moving rapidly from research to production. With the popularity of Foundation Models (FMs) that generate text, images, and video, AI-based systems are increasing their complexity. Compared to traditional AI-based…
Vision-Language-Action (VLA) models show promise in embodied reasoning, yet remain far from true generalists-they often require task-specific fine-tuning, incur high compute costs, and generalize poorly to unseen tasks. We propose MetaVLA,…