相关论文: Does Understanding Inform Generation in Unified Mu…

Unified Multimodal Models struggle to bridge the fundamental gap between the abstract representations needed for visual understanding and the detailed primitives required for generation. Existing approaches typically compromise by employing…

In recent years, integrating multimodal understanding and generation into a single unified model has emerged as a promising paradigm. While this approach achieves strong results in text-to-image (T2I) generation, it still struggles with…

Unified multimodal generative models aim to integrate image understanding and generation abilities, offering significant advantages in harnessing multimodal corpora, particularly interleaved text-image data. However, existing unified models…

With growing demand for interpretability in deep learning, especially in high stakes domains, Concept Bottleneck Models (CBMs) address this by inserting human understandable concepts into the prediction pipeline, but they are generally…

Modern artificial intelligence systems depend heavily on large datasets for both training and transferring knowledge between models. Knowledge distillation, transfer learning, and dataset distillation have made such transfers more…

Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end…

Over the past decade, higher education has undergone successive shifts driven by three major developments: Massive Open Online Courses (MOOCs), Smart Teaching technologies, and AI-enhanced learning. Each paradigm emerged to address specific…

Subject-driven image generation has advanced from single- to multi-subject composition, while neglecting distinction, the ability to distinguish and generate the correct subject when inputs contain multiple candidates. This limitation…

Weather modeling requires both accurate prediction and mechanistic interpretation, yet existing methods treat these goals in isolation, separating generation from understanding. To address this gap, we present Omni-Weather, the first…

When answering a question, humans utilize the information available across different modalities to synthesize a consistent and complete chain of thought (CoT). This process is normally a black box in the case of deep learning models like…

Multimodal models for text-to-image generation have achieved strong visual fidelity, yet they remain brittle under compositional structural constraints-notably generative numeracy, attribute binding, and part-level relations. To address…

Unified Vision-Language Models (UVLMs) aim to advance multimodal learning by supporting both understanding and generation within a single framework. However, existing approaches largely focus on architectural unification while overlooking…

Existing datasets for tabular question answering typically focus exclusively on text within cells. However, real-world data is inherently multimodal, often blending images such as symbols, faces, icons, patterns, and charts with textual…

This paper introduces TBAC-UniImage, a novel unified model for multimodal understanding and generation. We achieve this by deeply integrating a pre-trained Diffusion Model, acting as a generative ladder, with a Multimodal Large Language…

Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment. Distilling Step-by-Step~(DSS), a novel method utilizing chain-of-thought~(CoT)…

This paper addresses the problems of missing reasoning chains and insufficient entity-level semantic understanding in large language models when dealing with tasks that require structured knowledge. It proposes a fine-tuning algorithm…

The recent series of innovations in deep learning (DL) have shown enormous potential to impact individuals and society, both positively and negatively. The DL models utilizing massive computing power and enormous datasets have significantly…

We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and…

In designing generative models, it is commonly believed that in order to learn useful latent structure, we face a fundamental tension between expressivity and structure. In this paper we challenge this view by proposing a new approach to…

Despite the impressive progress on understanding and generating images shown by the recent unified architectures, the integration of 3D tasks remains challenging and largely unexplored. In this paper, we introduce UniUGG, the first unified…