Related papers: Training-Free Disentangled Text-Guided Image Editi…

In this work, we focus on exploring explicit fine-grained control of generative facial image editing, all while generating faithful facial appearances and consistent semantic details, which however, is quite challenging and has not been…

Deep convolutional neural networks for semantic segmentation achieve outstanding accuracy, however they also have a couple of major drawbacks: first, they do not generalize well to distributions slightly different from the one of the…

We present a new paradigm for fine-tuning large-scale visionlanguage pre-trained models on downstream task, dubbed Prompt Regularization (ProReg). Different from traditional fine-tuning which easily overfits to the downstream task data,…

Parameter-efficient fine-tuning (PEFT) of pre-trained language models has recently demonstrated remarkable achievements, effectively matching the performance of full fine-tuning while utilizing significantly fewer trainable parameters, and…

Diffusion Transformers (DiTs) have achieved remarkable success in diverse and high-quality text-to-image(T2I) generation. However, how text and image latents individually and jointly contribute to the semantics of generated images, remain…

The pre-training and fine-tuning paradigm has contributed to a number of breakthroughs in Natural Language Processing (NLP). Instead of directly training on a downstream task, language models are first pre-trained on large datasets with…

Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we…

We present TALE, a novel training-free framework harnessing the generative capabilities of text-to-image diffusion models to address the cross-domain image composition task that focuses on flawlessly incorporating user-specified objects…

With the metaverse slowly becoming a reality and given the rapid pace of developments toward the creation of digital humans, the need for a principled style editing pipeline for human faces is bound to increase manifold. We cater to this…

Traditional point-based image editing methods rely on iterative latent optimization or geometric transformations, which are either inefficient in their processing or fail to capture the semantic relationships within the image. These methods…

High-quality, diverse, and photorealistic images can now be generated by unconditional GANs (e.g., StyleGAN). However, limited options exist to control the generation process using (semantic) attributes, while still preserving the quality…

Although diffusion models have achieved remarkable success in the field of image generation, their latent space remains under-explored. Current methods for identifying semantics within latent space often rely on external supervision, such…

Deep learning has brought an unprecedented progress in computer vision and significant advances have been made in predicting subjective properties inherent to visual data (e.g., memorability, aesthetic quality, evoked emotions, etc.).…

Large language models (LLMs) exhibit substantial performance disparities across languages, particularly between high- and low-resource settings. We propose a framework for improving performance in underrepresented languages while preserving…

Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world. Models trained from data in which target labels are correlated with protected attributes…

Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly influenced by…

The use of denoising diffusion models is becoming increasingly popular in the field of image editing. However, current approaches often rely on either image-guided methods, which provide a visual reference but lack control over semantic…

Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for parameter-modifying methods. Existing approaches mitigate this issue through heuristic constraints on…

Image editing using a pretrained StyleGAN generator has emerged as a powerful paradigm for facial editing, providing disentangled controls over age, expression, illumination, etc. However, the approach cannot be directly adopted for video…

Face editing represents a popular research topic within the computer vision and image processing communities. While significant progress has been made recently in this area, existing solutions: (i) are still largely focused on…