Related papers: Unified Multimodal Models as Auto-Encoders
Although chain-of-thought reasoning and reinforcement learning (RL) have driven breakthroughs in NLP, their integration into generative vision models remains underexplored. We introduce ReasonGen-R1, a two-stage framework that first imbues…
Unified multimodal pretraining has emerged as a promising paradigm for jointly modeling language and vision within a single foundation model. However, existing approaches largely rely on implicit or indirect alignment signals and remain…
Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur and severe semantics loss at extremely low bitrates. To…
Image-to-image translation (I2I) transforms an image from a source domain to a target domain while preserving source content. Most computer vision applications are in the field of image-to-image translation, such as style transfer, image…
In this paper, we investigate the cross-media retrieval between images and text, i.e., using image to search text (I2T) and using text to search images (T2I). Existing cross-media retrieval methods usually learn one couple of projections,…
Personalized text-to-image (P-T2I) generation aims to create new, text-guided images featuring the personalized subject with a few reference images. However, balancing the trade-off relationship between prompt fidelity and identity…
Graph-to-text (G2T) generation and text-to-graph (T2G) triple extraction are two essential tasks for constructing and applying knowledge graphs. Existing unsupervised approaches turn out to be suitable candidates for jointly learning the…
Contrastive Language-Image Pre-training (CLIP) has shown impressive performance in aligning visual and textual representations. Recent studies have extended this paradigm to 3D vision to improve scene understanding for autonomous driving. A…
Referring image segmentation aims to segment the target object referred by a natural language expression. However, previous methods rely on the strong assumption that one sentence must describe one target in the image, which is often not…
Text-to-image (T2I) models have ushered in a new era of real-world image super-resolution (Real-ISR) due to their rich internal implicit knowledge for multimodal learning. Although bringing high-level semantic priors and dense pixel…
Humans have an incredible ability to process and understand information from multiple sources such as images, video, text, and speech. Recent success of deep neural networks has enabled us to develop algorithms which give machines the…
Image-to-image translation has drawn great attention during the past few years. It aims to translate an image in one domain to a given reference image in another domain. Due to its effectiveness and efficiency, many applications can be…
Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear. Existing benchmarks lack a systematic exploration of the specific tasks where…
We propose UniT, a Unified Transformer model to simultaneously learn the most prominent tasks across different domains, ranging from object detection to natural language understanding and multimodal reasoning. Based on the transformer…
Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical limitations. (1) \textit{Shared credit assignment}:…
Multimodal Large Language Models (MLLMs) are making significant progress in multimodal reasoning. Early approaches focus on pure text-based reasoning. More recent studies have incorporated multimodal information into the reasoning steps;…
Image reconstruction and image synthesis are important for handling incomplete multimodal imaging data, but existing methods require various task-specific models, complicating training and deployment workflows. We introduce Any2all, a…
End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research. However, data sparsity limits the performance of…
In this paper, we propose \textbf{UniCode}, a novel approach within the domain of multimodal large language models (MLLMs) that learns a unified codebook to efficiently tokenize visual, text, and potentially other types of signals. This…
Multi-modal magnetic resonance imaging (MRI) plays a crucial role in comprehensive disease diagnosis in clinical medicine. However, acquiring certain modalities, such as T2-weighted images (T2WIs), is time-consuming and prone to be with…