Related papers: TBAC-UniImage: Unified Understanding and Generatio…

Despite recent progress, medical foundation models still struggle to unify visual understanding and generation, as these tasks have inherently conflicting goals: semantic abstraction versus pixel-level reconstruction. Existing approaches,…

Currently, the success of large language models (LLMs) illustrates that a unified multitasking approach can significantly enhance model usability, streamline deployment, and foster synergistic benefits across different tasks. However, in…

Multi-modal data-sets are ubiquitous in modern applications, and multi-modal Variational Autoencoders are a popular family of models that aim to learn a joint representation of the different modalities. However, existing approaches suffer…

Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality depends critically on the generation order. Prior work either hard-codes an ordering (e.g., blockwise…

Counting is a core capability for multimodal large language models (MLLMs), yet there is no unified counting dataset to rigorously evaluate this ability across image, text, and audio. We present UNICBench, a unified multimodal, multi level…

Recent advancements in text-to-3D generation technology have significantly advanced the conversion of textual descriptions into imaginative well-geometrical and finely textured 3D objects. Despite these developments, a prevalent limitation…

Interleaved text-image generation aims to jointly produce coherent visual frames and aligned textual descriptions within a single sequence, enabling tasks such as style transfer, compositional synthesis, and procedural tutorials. We present…

By embedding discrete representations into a continuous latent space, we can leverage continuous-space latent diffusion models to handle generative modeling of discrete data. However, despite their initial success, most latent diffusion…

Recent medical multimodal foundation models are built as multimodal LLMs (MLLMs) by connecting a CLIP-pretrained vision encoder to an LLM using LLaVA-style finetuning. This two-stage, decoupled approach introduces a projection layer that…

Visual information has been introduced for enhancing machine translation (MT), and its effectiveness heavily relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations. In this paper, we…

We introduce a diffusion-based cross-domain image translator in the absence of paired training data. Unlike GAN-based methods, our approach integrates diffusion models to learn the image translation process, allowing for more coverable…

Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems. However, evaluations of unified multimodal models (UMMs) remain decoupled, assessing their understanding and generation…

Unified multimodal models (UMMs) aim to integrate multimodal understanding and generation within a unified architecture, yet it remains unclear to what extent their representations are truly aligned across modalities. To investigate this…

In practical AI workflows, complex tasks often involve chaining multiple generative models, such as using a video or 3D generation model after a 2D image generator. However, distributional mismatches between the output of upstream models…

Diffusion models have made significant strides in language-driven and layout-driven image generation. However, most diffusion models are limited to visible RGB image generation. In fact, human perception of the world is enriched by diverse…

LiDAR scene generation is increasingly important for scalable simulation and synthetic data creation, especially under diverse sensing conditions that are costly to capture at scale. Typically, diffusion-based LiDAR generators are developed…

Medical generative models, acknowledged for their high-quality sample generation ability, have accelerated the fast growth of medical applications. However, recent works concentrate on separate medical generation models for distinct medical…

With the powerful reasoning capabilities of large language models (LLMs) and vision-language models (VLMs), many recent works have explored using them for decision-making. However, most of these approaches rely solely on language-based…

This paper studies the fundamental problem of learning multi-layer generator models. The multi-layer generator model builds multiple layers of latent variables as a prior model on top of the generator, which benefits learning complex data…

Existing MLLM benchmarks face significant challenges in evaluating Unified MLLMs (U-MLLMs) due to: 1) lack of standardized benchmarks for traditional tasks, leading to inconsistent comparisons; 2) absence of benchmarks for mixed-modality…