相关论文: Uni-EDEN: Universal Encoder-Decoder Network by Mul…

Performing 3D dense captioning and visual grounding requires a common and shared understanding of the underlying multimodal relationships. However, despite some previous attempts on connecting these two related tasks with highly…

Current unified multimodal models typically rely on discrete visual tokenizers to bridge the modality gap. However, discretization inevitably discards fine-grained semantic information, leading to suboptimal performance in visual…

This paper presents a multimodal framework that attempts to unify visual understanding and generation within a shared discrete semantic representation. At its core is the Text-Aligned Tokenizer (TA-Tok), which converts images into discrete…

Unified understanding and generation is a highly appealing research direction in multimodal learning. There exist two approaches: one trains a transformer via an auto-regressive paradigm, and the other adopts a two-stage scheme connecting…

The recently developed discrete diffusion models perform extraordinarily well in the text-to-image task, showing significant promise for handling the multi-modality signals. In this work, we harness these traits and present a unified…

Vision-Language Models (VLMs) trained via contrastive learning have achieved notable success in natural image tasks. However, their application in the medical domain remains limited due to the scarcity of openly accessible, large-scale…

We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with…

Vision Transformers (ViT)s have recently become popular due to their outstanding modeling capabilities, in particular for capturing long-range information, and scalability to dataset and model sizes which has led to state-of-the-art…

While originally designed for unidirectional generative modeling, decoder-only large language models (LLMs) are increasingly being adapted for bidirectional modeling. However, unidirectional and bidirectional models are typically trained…

Text-to-image generation has advanced rapidly with diffusion models, progressing from CLIP and T5 conditioning to unified systems where a single LLM backbone handles both visual understanding and generation. Despite the architectural…

Multimodal large-scale datasets for outdoor scenes are mostly designed for urban driving problems. The scenes are highly structured and semantically different from scenarios seen in nature-centered scenes such as gardens or parks. To…

In recent years, open-vocabulary (OV) dense visual prediction (such as OV object detection, semantic, instance and panoptic segmentations) has attracted increasing research attention. However, most of existing approaches are task-specific…

Conventional methods for the image-text generation tasks mainly tackle the naturally bidirectional generation tasks separately, focusing on designing task-specific frameworks to improve the quality and fidelity of the generated samples.…

We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…

In this paper, we propose a new progressive pre-training method for image understanding tasks which leverages RGB-D datasets. The method utilizes Multi-Modal Contrastive Masked Autoencoder and Denoising techniques. Our proposed approach…

Multi-modal learning relates information across observation modalities of the same physical phenomenon to leverage complementary information. Most multi-modal machine learning methods require that all the modalities used for training are…

Self-supervised vision-and-language pretraining (VLP) aims to learn transferable multi-modal representations from large-scale image-text data and to achieve strong performances on a broad scope of vision-language tasks after finetuning.…

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each…

Medical vision-language pre-training (Med-VLP) models have recently accelerated the fast-growing medical diagnostics application. However, most Med-VLP models learn task-specific representations independently from scratch, thereby leading…

Large-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes…