Related papers: ControlThinker: Unveiling Latent Semantics for Con…

Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but they continue to struggle with spatial understanding. Existing spatial MLLMs often rely on explicit 3D inputs or architecture-specific…

Scalable Vector Graphics (SVG) is a code-based representation for 2D visuals. Leveraging recent advances in large language models (LLMs), we study text-to-SVG generation and address two persistent gaps: weak generalization and poor…

Enabling image generation models to be spatially controlled is an important area of research, empowering users to better generate images according to their own fine-grained specifications via e.g. edge maps, poses. Although this task has…

Recent progress in text-to-image (T2I) diffusion models (DMs) has enabled high-quality visual synthesis from diverse textual prompts. Yet, most existing T2I DMs, even those equipped with large language model (LLM)-based text encoders,…

Image generation today can produce somewhat realistic images from text prompts. However, if one asks the generator to synthesize a specific camera setting such as creating different fields of view using a 24mm lens versus a 70mm lens, the…

Controllable image generation has always been one of the core demands in image generation, aiming to create images that are both creative and logical while satisfying additional specified conditions. In the post-AIGC era, controllable…

Latent visual reasoning involves visual evidence more directly in multimodal reasoning by inserting continuous latent tokens before textual generation. However, the necessity of these latent tokens at inference remains ambiguous. We show…

Text-to-image generation has advanced rapidly with diffusion models, progressing from CLIP and T5 conditioning to unified systems where a single LLM backbone handles both visual understanding and generation. Despite the architectural…

Aligning language models (LMs) with user intent is becoming increasingly relevant to enhance user experience. This calls for designing methods that can allow users to control the properties of the language that LMs generate, for example,…

Video reasoning requires a fine-grained understanding of the temporal dependencies and event-level relations between objects and events in videos. Current Multimodal Large Language Models (MLLMs) are prone to severe temporal hallucinations…

When generating images from prompts that include specific entities, the model must retain as much entity-specific knowledge as possible. However, the number of entities is almost countless, and new entities emerge; memorizing all of them…

Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightThinker, a method that enables LLMs to dynamically compress…

Despite significant progress in text-to-image generation, aligning outputs with complex prompts remains challenging, particularly for fine-grained semantics and spatial relations. This difficulty stems from the feed-forward nature of…

To enhance the controllability of text-to-image diffusion models, existing efforts like ControlNet incorporated image-based conditional controls. In this paper, we reveal that existing methods still face significant challenges in generating…

As generative models become ubiquitous, there is a critical need for fine-grained control over the generation process. Yet, while controlled generation methods from prompting to fine-tuning proliferate, a fundamental question remains…

Progress in image generation raises significant public security concerns. We argue that fake image detection should not operate as a "black box". Instead, an ideal approach must ensure both strong generalization and transparency. Recent…

Generative Models are a valuable tool for the controlled creation of high-quality image data. Controlled diffusion models like the ControlNet have allowed the creation of labeled distributions. Such synthetic datasets can augment the…

Diffusion models emerged as a leading approach in text-to-image generation, producing high-quality images from textual descriptions. However, attempting to achieve detailed control to get a desired image solely through text remains a…

Generative cross-modal retrieval, which treats retrieval as a generation task, has emerged as a promising direction with the rise of Multimodal Large Language Models (MLLMs). In this setting, the model responds to a text query by generating…

ControlNet has enabled detailed spatial control in text-to-image diffusion models by incorporating additional visual conditions such as depth or edge maps. However, its effectiveness heavily depends on the availability of visual conditions…