Related papers: Layout-Conditioned Autoregressive Text-to-Image Ge…
Modern LLM agents increasingly rely on dynamic structured generation, such as tool calling and response protocols. Unlike traditional structured generation with static structures, these workloads vary both across requests and within a…
Text-to-image (T2I) generation has advanced rapidly, yet faithfully capturing spatial relationships described in natural language prompts remains a major challenge. Prior efforts have addressed this issue through prompt optimization,…
ATLAS is a constraint-guided generation framework for structured engineering artifacts whose outputs must satisfy explicit schemas, domain rules, and audit requirements. Rather than treating a large language model as a standalone generator,…
Generating faithful and readable styled text images (especially for Styled Handwritten Text generation - HTG) is an open problem with several possible applications across graphic design, document understanding, and image editing. A lot of…
Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling. However, controllable generation remains challenging for Visual Autoregressive (VAR) models…
Unified multimodal models that couple visual understanding with image generation have advanced rapidly, yet most systems still focus on visual grounding-aligning language with image regions-while their generative counterpart,…
Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an…
Constructing dataset for fashion style recognition is challenging due to the inherent subjectivity and ambiguity of style concepts. Recent advances in text-to-image models have facilitated generative data augmentation by synthesizing images…
Recent visual autoregressive (AR) models have shown promising capabilities in text-to-image generation, operating in a manner similar to large language models. While test-time computation scaling has brought remarkable success in enabling…
While visual autoregressive modeling (VAR) strategies have shed light on image generation with the autoregressive models, their potential for segmentation, a task that requires precise low-level spatial perception, remains unexplored.…
Previous text-to-image synthesis algorithms typically use explicit textual instructions to generate/manipulate images accurately, but they have difficulty adapting to guidance in the form of coarsely matched texts. In this work, we attempt…
Adaptive and flexible image editing is a desirable function of modern generative models. In this work, we present a generative model with auto-encoder architecture for per-region style manipulation. We apply a code consistency loss to…
Event temporal graphs have been shown as convenient and effective representations of complex temporal relations between events in text. Recent studies, which employ pre-trained language models to auto-regressively generate linearised graphs…
We present a framework for document-centric background generation with multi-page editing and thematic continuity. To ensure text regions remain readable, we employ a \emph{latent masking} formulation that softly attenuates updates in the…
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…
Deep generative models (DGMs) have shown promise in image generation. However, most of the existing work learn the model by simply optimizing a divergence between the marginal distributions of the model and the data, and often fail to…
The task of layout-to-image generation involves synthesizing images based on the captions of objects and their spatial positions. Existing methods still struggle in complex layout generation, where common bad cases include object missing,…
AI-based text-to-image models do not only excel at generating realistic images, they also give designers more and more fine-grained control over the image content. Consequently, these approaches have gathered increased attention within the…
For deep reinforcement learning (RL) from pixels, learning effective state representations is crucial for achieving high performance. However, in practice, limited experience and high-dimensional inputs prevent effective representation…
Attaining a high degree of user controllability in visual generation often requires intricate, fine-grained inputs like layouts. However, such inputs impose a substantial burden on users when compared to simple text inputs. To address the…