Related papers: OmniAlpha: Aligning Transparency-Aware Generation …

Visual retrieval systems face significant challenges when updating models with improved representations due to misalignment between the old and new representations. The costly and resource-intensive backfilling process involves…

A generalist robotic policy needs both semantic understanding for task planning and the ability to interact with the environment through predictive capabilities. To tackle this, we present MM-ACT, a unified Vision-Language-Action (VLA)…

Scene Graph Generation (SGG) aims to detect all the visual relation triplets $<$\texttt{sub}, \texttt{pred}, \texttt{obj}$>$ in a given image. With the emergence of various advanced techniques for better utilizing both the intrinsic and…

Image coding for multi-task applications, catering to both human perception and machine vision, has been extensively investigated. Existing methods often rely on multiple task-specific encoder-decoder pairs, leading to high overhead of…

Reinforcement learning (RL) has recently achieved remarkable success in eliciting visual reasoning within Multimodal Large Language Models (MLLMs). However, existing approaches typically train separate models for different tasks and treat…

The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this…

Unified large multimodal models (LMMs) have achieved remarkable progress in general-purpose multimodal understanding and generation. However, they still operate under a ``one-size-fits-all'' paradigm and struggle to model user-specific…

Multimodal instruction tuning is the de facto recipe for adapting vision language models (VLMs), yet instruction data are highly redundant, making data selection critical for training efficiency. Existing methods derive selection signals…

Ultrasound images vary widely across scanners, operators, and anatomical targets, which often causes models trained in one setting to generalize poorly to new hospitals and clinical conditions. The Foundation Model Challenge for Ultrasound…

The ability to accurately recognize, localize and separate sound sources is fundamental to any audio-visual perception task. Historically, these abilities were tackled separately, with several methods developed independently for each task.…

Multi-subject image generation aims to synthesize user-provided subjects in a single image while preserving subject fidelity, ensuring prompt consistency, and aligning with human aesthetic preferences. Existing In-Context-Learning based…

Generating multi-view images from a single-view input is an essential yet challenging problem. It has broad applications in vision, graphics, and robotics. Our study indicates that the widely-used generative adversarial network (GAN) may…

Face filters have become a key element of short-form video content, enabling a wide array of visual effects such as stylization and face swapping. However, their performance often degrades in the presence of occlusions, where objects like…

Executing multiple tasks simultaneously in medical image analysis, including segmentation, classification, detection, and regression, often introduces significant challenges regarding model generalizability and the optimization of shared…

There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on the transparency of decisions in human-critical…

Research on multi-modal learning dominantly aligns the modalities in a unified space at training, and only a single one is taken for prediction at inference. However, for a real machine, e.g., a robot, sensors could be added or removed at…

Recent progress in diffusion models significantly advances various image generation tasks. However, the current mainstream approach remains focused on building task-specific models, which have limited efficiency when supporting a wide range…

Recent advancements in unified vision-language models (VLMs), which integrate both visual understanding and generation capabilities, have attracted significant attention. The underlying hypothesis is that a unified architecture with mixed…

This paper addresses the problem of transparent object matting. Existing image matting approaches for transparent objects often require tedious capturing procedures and long processing time, which limit their practical use. In this paper,…

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The execution of complex multi-step behaviors in VLA models can be improved by robust instruction grounding, a critical component…