相关论文: FlowInOne:Unifying Multimodal Generation as Image-…
Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference…
Recent advancements in multimodal foundation models have yielded significant progress in vision-language understanding. Initial attempts have also explored the potential of multimodal large language models (MLLMs) for visual content…
Recent advancements in instruction-based image editing and subject-driven generation have garnered significant attention, yet both tasks still face limitations in meeting practical user needs. Instruction-based editing relies solely on…
Notable breakthroughs in unified understanding and generation modeling have led to remarkable advancements in image understanding, reasoning, production and editing, yet current foundational models predominantly focus on processing images,…
Recent advances in foundation models highlight a clear trend toward unification and scaling, showing emergent capabilities across diverse domains. While image generation and editing have rapidly transitioned from task-specific to unified…
Current multimodal models aim to transcend the limitations of single-modality representations by unifying understanding and generation, often using text-to-image (T2I) tasks to calibrate semantic consistency. However, their reliance on…
Recent advancements in unified multimodal understanding and visual generation (or multimodal generation) models have been hindered by their quadratic computational complexity and dependence on large-scale training data. We present…
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…
Although recent advances in visual generation have been remarkable, most existing architectures still depend on distinct encoders for images and text. This separation constrains diffusion models' ability to perform cross-modal reasoning and…
Generating realistic talking-head videos remains challenging due to persistent issues such as imperfect lip synchronization, unnatural motion, and evaluation metrics that correlate poorly with human perception. We propose FlowPortrait, a…
Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to…
Large language models (LLMs) are, by design, inherently capable of multi-task learning: through a unified next-token prediction paradigm, they can naturally address a wide variety of downstream tasks. Prior work in the motion domain has…
We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to…
We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike existing datasets limited to merely hundreds or thousands of examples, PhysInOne provides 2…
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…
Recent progress has shown that video diffusion models (VDMs) can be repurposed for diverse multimodal graphics tasks. However, existing methods often train separate models for each problem setting, which fixes the input-output mapping and…
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…
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…
We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation…
We present UniMotion, to our knowledge the first unified framework for simultaneous understanding and generation of human motion, natural language, and RGB images within a single architecture. Existing unified models handle only restricted…