相关论文: STARFlow2: Bridging Language Models and Normalizin…

Unified image understanding and generation has emerged as a promising paradigm in multimodal artificial intelligence. Despite recent progress, the optimal architectural design for such unified models remains an open challenge. In this work,…

Recent advances in Artificial Intelligence Generated Content (AIGC) have garnered significant interest, accompanied by an increasing need to transmit and compress the vast number of AI-generated images (AIGIs). However, there is a…

Vision-Language-Action (VLA) models are emerging as a promising paradigm for end-to-end autonomous driving, valued for their potential to leverage world knowledge and reason about complex driving scenes. However, existing methods suffer…

Large language models and large multimodal models (LLMs and LMMs) deliver strong generative performance but suffer from slow decoding, a problem that becomes more severe when handling visual inputs, whose sequences typically contain many…

Diffusion-based generative models represent a forefront direction in generative AI research today. Recent studies in physics have suggested that the renormalization group (RG) can be conceptualized as a diffusion process. This insight…

Normalizing flows model complex probability distributions using maps obtained by composing invertible layers. Special linear layers such as masked and 1x1 convolutions play a key role in existing architectures because they increase…

Text-based image segmentation aims to delineate object boundaries within an image from text prompts, offering higher flexibility and broader application scope compared to traditional fixed-category segmentation tasks. Recent studies have…

Beyond high-fidelity image synthesis, diffusion models have recently exhibited promising results in dense visual perception tasks. However, most existing work treats diffusion models as a standalone component for perception tasks, employing…

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…

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,…

We present Omni-Video 2, a scalable and computationally efficient model that connects pretrained multimodal large-language models (MLLMs) with video diffusion models for unified video generation and editing. Our key idea is to exploit the…

We present UniModel, a unified generative model that jointly supports visual understanding and visual generation within a single pixel-to-pixel diffusion framework. Our goal is to achieve unification along three axes: the model, the tasks,…

Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image editing. By shifting the editing paradigm from noise…

Building generalist embodied agents requires integrating perception, language understanding, and action, which are core capabilities addressed by Vision-Language-Action (VLA) approaches based on multimodal foundation models, including…

Video-conditioned audio generation, including Video-to-Sound (V2S) and Visual Text-to-Speech (VisualTTS), has traditionally been treated as distinct tasks, leaving the potential for a unified generative framework largely underexplored. In…

Unified generation models aim to handle diverse tasks across modalities -- such as text generation, image generation, and vision-language reasoning -- within a single architecture and decoding paradigm. Autoregressive unified models suffer…

We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive…

A recent study showed that large language models (LLMs) can reconstruct surprisingly long texts - up to thousands of tokens - via autoregressive generation from just one trained input embedding. In this work, we explore whether…

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…

Controllable generation, which enables fine-grained control over generated outputs, has emerged as a critical focus in visual generative models. Currently, there are two primary technical approaches in visual generation: diffusion models…