相关论文: From "What" to "How": Constrained Reasoning for Au…
Recent advances in text-to-image generation have produced strong single-shot models, yet no individual system reliably executes the long, compositional prompts typical of creative workflows. We introduce Image-POSER, a reflective…
We introduce ARPG, a novel visual Autoregressive model that enables Randomized Parallel Generation, addressing the inherent limitations of conventional raster-order approaches, which hinder inference efficiency and zero-shot generalization…
Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using…
The field of controllable image generation has seen significant advancements, with various architectures improving generation layout consistency with control signals. However, contemporary methods still face challenges in bridging the…
Visual generation models have made remarkable progress in creating realistic images from text prompts, yet struggle with complex prompts that specify multiple objects with precise spatial relationships and attributes. Effective handling of…
Despite rapid advances in text-to-image generation, faithfully realizing user intent remains challenging, often requiring manual multi-turn trial and error. To automate this process, existing systems rely on either simple prompt rewriting…
Chain-of-Thought (CoT) prompting has achieved remarkable success in unlocking the reasoning capabilities of Large Language Models (LLMs). Although CoT prompting enhances reasoning, its verbosity imposes substantial computational overhead.…
We present Thinking with Generated Images, a novel paradigm that fundamentally transforms how large multimodal models (LMMs) engage with visual reasoning by enabling them to natively think across text and vision modalities through…
In the last few years the systematic adoption of deep learning to visual generation has produced impressive results that, amongst others, definitely benefit from the massive exploration of convolutional architectures. In this paper, we…
Despite the promising progress of recent autoregressive models in text-to-image (T2I) generation, their ability to handle multi-attribute and ambiguous prompts remains limited. To address these limitations, existing works have applied…
Autoregressive models have recently shown great promise in visual generation by leveraging discrete token sequences akin to language modeling. However, existing approaches often suffer from inefficiency, either due to token-by-token…
Recent advancements in image generation have achieved impressive results in producing high-quality images. However, existing image generation models still generally struggle with a spatial reasoning dilemma, lacking the ability to…
The goal of image composition is merging a foreground object into a background image to obtain a realistic composite image. Recently, generative composition methods are built on large pretrained diffusion models, due to their unprecedented…
Unified generative models have shown remarkable performance in text and image generation. For image synthesis tasks, they adopt straightforward text-to-image (T2I) generation. However, direct T2I generation limits the models in handling…
Image editing with natural language has gained significant popularity, yet existing methods struggle with intricate object intersections and fine-grained spatial relationships due to the lack of an explicit reasoning process. While…
Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts, especially those describing complex sound events. We uncover a…
In-context learning allows adapting a model to new tasks given a task description at test time. In this paper, we present IMProv - a generative model that is able to in-context learn visual tasks from multimodal prompts. Given a textual…
Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent…
Making text-to-image (T2I) generative model sample both fast and well represents a promising research direction. Previous studies have typically focused on either enhancing the visual quality of synthesized images at the expense of sampling…
The capacity to learn incrementally from an online stream of data is an envied trait of human learners, as deep neural networks typically suffer from catastrophic forgetting and stability-plasticity dilemma. Several works have previously…