Related papers: MidSteer: Optimal Affine Framework for Steering Ge…
Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limitations. Feature-correction approaches often cause uncontrolled over-correction, while…
To what extent does concept erasure eliminate generative capacity in diffusion models? While prior evaluations have primarily focused on measuring concept suppression under specific textual prompts, we explore a complementary and…
Diffusion models have become the go-to method for text-to-image generation, producing high-quality images from pure noise. However, the inner workings of diffusion models is still largely a mystery due to their black-box nature and complex,…
We propose to improve multi-concept prompt fidelity in text-to-image diffusion models. We begin with common failure cases - prompts like "a cat and a dog" that sometimes yields images where one concept is missing, faint, or colliding…
Generative image editing has recently witnessed extremely fast-paced growth. Some works use high-level conditioning such as text, while others use low-level conditioning. Nevertheless, most of them lack fine-grained control over the…
Self-conditioning has been central to the success of continuous diffusion language models, as it allows models to correct previous errors. Yet its ability degrades precisely in the regime where diffusion is most attractive for deployment:…
End-to-end autonomous driving aims to generate safe and plausible planning policies from raw sensor input. Driving world models have shown great potential in learning rich representations by predicting the future evolution of a driving…
One-step generative modeling has emerged as a leading approach to amortize the inference cost of diffusion and flow-matching models. Among distillation-free methods, MeanFlow training is notoriously unstable, with non-decreasing loss and…
Deep generative models are reported to be useful in broad applications including image generation. Repeated inference between data space and latent space in these models can denoise cluttered images and improve the quality of inferred…
It has been hypothesized that neural networks with similar architectures trained on similar data learn shared representations relevant to the learning task. We build on this idea by extending the conceptual framework where representations…
Generative AI is transforming image synthesis, enabling the creation of high-quality, diverse, and photorealistic visuals across industries like design, media, healthcare, and autonomous systems. Advances in techniques such as…
Techniques for concept extraction, such as sparse autoencoders and transcoders, aim to extract high-level symbolic concepts from low-level nonsymbolic representations. When these extracted concepts are used for downstream tasks such as…
Diffusion Models have become a cornerstone of modern generative AI for their exceptional generation quality and controllability. However, their inherent \textit{multi-step iterations} and \textit{complex backbone networks} lead to…
Having an LLM that aligns with human preferences is essential for accommodating individual needs, such as maintaining writing style or generating specific topics of interest. The majority of current alignment methods rely on fine-tuning or…
As one of the most successful generative models, diffusion models have demonstrated remarkable efficacy in synthesizing high-quality images. These models learn the underlying high-dimensional data distribution in an unsupervised manner.…
Text-driven video editing utilizing generative diffusion models has garnered significant attention due to their potential applications. However, existing approaches are constrained by the limited word embeddings provided in pre-training,…
In the transfer learning paradigm models learn useful representations (or features) during a data-rich pretraining stage, and then use the pretrained representation to improve model performance on data-scarce downstream tasks. In this work,…
Recent advancements in language models (LMs) have marked a shift toward the growing importance of post-training. Yet, post-training approaches such as supervised fine-tuning (SFT) do not guarantee the effective use of knowledge acquired…
Model-based language specification has applications in the implementation of language processors, the design of domain-specific languages, model-driven software development, data integration, text mining, natural language processing, and…
The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors. Existing concept erasing methods in academia are all based on full parameter or…