相关论文: UniMotion: A Unified Framework for Motion-Text-Vis…

Recent motion-language models unify tasks like comprehension and generation but operate at a coarse granularity, lacking fine-grained understanding and nuanced control over body parts needed for animation or interaction. This stems from…

The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models remains opaque. We provide empirical clarity through…

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…

Recent advancements in vision-language pre-training via contrastive learning have significantly improved performance across computer vision tasks. However, in the medical domain, obtaining multimodal data is often costly and challenging due…

We present Unified-IO 2, the first autoregressive multimodal model that is capable of understanding and generating image, text, audio, and action. To unify different modalities, we tokenize inputs and outputs -- images, text, audio, action,…

Unifying diverse image generation tasks within a single framework remains a fundamental challenge in visual generation. While large language models (LLMs) achieve unification through task-agnostic data and generation, existing visual…

Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal…

Multimodal large language models (MLLMs) have made significant progress in vision-language understanding, yet effectively aligning different modalities remains a fundamental challenge. We present a framework that unifies multimodal…

Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other. They can only utilize single-modal data (i.e. text or image) or limited multi-modal data (i.e. image-text…

While recent text-to-video models excel at generating diverse scenes, they struggle with precise motion control, particularly for complex, multi-subject motions. Although methods for single-motion customization have been developed to…

Current remote sensing change detection (CD) methods mainly rely on specialized models, which limits the scalability toward modality-adaptive Earth observation. For homogeneous CD, precise boundary delineation relies on fine-grained spatial…

Recent motion-aware large language models have demonstrated promising potential in unifying motion comprehension and generation. However, existing approaches primarily focus on coarse-grained motion-text modeling, where text describes the…

World models have demonstrated significant promise for data synthesis in autonomous driving. However, existing methods predominantly concentrate on single-modality generation, typically focusing on either multi-camera video or LiDAR…

Motion generation is a cornerstone of computer graphics, animation, gaming, and robotics, enabling the creation of realistic and varied character movements. A significant limitation of existing methods is their reliance on specific skeletal…

Latent action representations learned from unlabeled videos have recently emerged as a promising paradigm for pretraining vision-language-action (VLA) models without explicit robot action supervision. However, latent actions derived solely…

Multimodal language models (MLMs) integrate visual and textual information by coupling a vision encoder with a large language model through the specific adapter. While existing approaches commonly rely on a single pre-trained vision…

Integrating vision-language models (VLMs) into end-to-end (E2E) autonomous driving (AD) systems has shown promise in improving scene understanding. However, existing integration strategies suffer from several limitations: they either…

This paper introduces OmniMotion-X, a versatile multimodal framework for whole-body human motion generation, leveraging an autoregressive diffusion transformer in a unified sequence-to-sequence manner. OmniMotion-X efficiently supports…

Most existing vision-language pre-training methods focus on understanding tasks and use BERT-like objectives (masked language modeling and image-text matching) during pretraining. Although they perform well in many understanding downstream…

Recent advancements in large language models (LLMs) have significantly improved their ability to generate natural and contextually relevant text, enabling more human-like AI interactions. However, generating and understanding interactive…