相关论文: Autoregressive Visual Generation Needs a Prologue

Autoregressive visual generation has garnered increasing attention due to its scalability and compatibility with other modalities compared with diffusion models. Most existing methods construct visual sequences as spatial patches for…

Traditional supervised methods for detecting AI-generated images depend on large, curated datasets for training and fail to generalize to novel, out-of-domain image generators. As an alternative, we explore pre-trained Vision-Language…

Generative recommendation has recently emerged as a promising paradigm for sequential recommendation. It formulates the task as an autoregressive generation process, predicting tokens of the next item conditioned on user interaction…

Numerous efforts have been made to extend the ``next token prediction'' paradigm to visual contents, aiming to create a unified approach for both image generation and understanding. Nevertheless, attempts to generate images through…

Engineering design optimization requires an efficient combination of a 3D shape representation, an optimization algorithm, and a design performance evaluation method, which is often computationally expensive. We present a prompt evolution…

Auto-Regressive (AR) models have recently gained prominence in image generation, often matching or even surpassing the performance of diffusion models. However, one major limitation of AR models is their sequential nature, which processes…

The practical application of Multimodal Large Language Models (MLLMs) to Video Question Answering (Video-QA) is severely hindered by the high token cost of processing numerous video frames. While keyframe selection is the dominant strategy…

We introduce Heptapod, an image autoregressive model that adheres to the foundational principles of language modeling. Heptapod employs \textbf{causal attention}, \textbf{eliminates reliance on CFG}, and \textbf{eschews the trend of…

Image degradation from blur, noise, compression, and poor illumination severely undermines multimodal understanding in real-world settings. Unified multimodal models that combine understanding and generation within a single architecture are…

Text-to-image diffusion models achieved a remarkable leap in capabilities over the last few years, enabling high-quality and diverse synthesis of images from a textual prompt. However, even the most advanced models often struggle to…

Deep autoregressive sequence-to-sequence models have demonstrated impressive performance across a wide variety of tasks in recent years. While common architecture classes such as recurrent, convolutional, and self-attention networks make…

Transformers operate as horizontal token-by-token scanners; at each generation step, attending to an ever-growing sequence of token-level states. This access pattern increases prefill latency and makes long-context decoding more…

Text-to-image generation has become increasingly popular, but achieving the desired images often requires extensive prompt engineering. In this paper, we explore how to decode textual prompts from reference images, a process we refer to as…

Vision-language large models are moving toward the unification of visual understanding and visual generation tasks. However, whether generation can enhance understanding is still under-explored on large data scale. In this work, we analysis…

While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view…

Unified multimodal understanding and generation models recently have achieve significant improvement in image generation capability, yet a large gap remains in instruction following and detail preservation compared to systems that tightly…

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…

Artificial general intelligence on graphs has shown significant advancements across various applications, yet the traditional 'Pre-train & Fine-tune' paradigm faces inefficiencies and negative transfer issues, particularly in complex and…

Proper guidance strategies are essential to achieve high-quality generation results without retraining diffusion and flow-based text-to-image models. Existing guidance either requires specific training or strong inductive biases of…

Large language models handle single-turn generation well, but multi-turn interactions still require the model to reconstruct user intent and task state from an expanding token history because internal representations do not persist across…