Related papers: LEGO: LoRA-Enabled Generator-Oriented Framework fo…
Recent training-free layout-to-image diffusion models have demonstrated remarkable performance in generating high-quality images with controllable layouts. These models follow a one-stage framework: Encouraging the model to focus the…
Deepfakes pose significant societal risks, motivating the development of proactive defenses that embed adversarial perturbations in facial images to prevent manipulation. However, in this paper, we show that these preemptive defenses often…
Generative models achieve remarkable results in multiple data domains, including images and texts, among other examples. Unfortunately, malicious users exploit synthetic media for spreading misinformation and disseminating deepfakes.…
In recent years, many data augmentation techniques have been proposed to increase the diversity of input data and reduce the risk of overfitting on deep neural networks. In this work, we propose an easy-to-implement and model-free data…
The December 2024 release of OpenAI's Sora, a powerful video generation model driven by natural language prompts, highlights a growing convergence between large language models (LLMs) and video synthesis. As these multimodal systems evolve…
LoRA employs lightweight modules to customize large language models (LLMs) for each downstream task or domain, where different learned additional modules represent diverse skills. Combining existing LoRAs to address new tasks can enhance…
Adversarial attacks aim to perturb images such that a predictor outputs incorrect results. Due to the limited research in structured attacks, imposing consistency checks on natural multi-object scenes is a promising yet practical defense…
The explosive growth of generative AI has saturated the internet with AI-generated images, raising security concerns and increasing the need for reliable detection methods. The primary requirement for such detection is generalizability,…
With the breakthrough of Transformer-based pre-trained models, the demand for fine-tuning (FT) to adapt the base pre-trained models to downstream applications continues to grow, so it is essential for service providers to reduce the cost of…
Although LEGO sets have entertained generations of children and adults, the challenge of designing customized builds matching the complexity of real-world or imagined scenes remains too great for the average enthusiast. In order to make…
In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient specificity, and diverse interpretations of natural language,…
Parameter-Efficient Fine-Tuning (PEFT) is essential for adapting Large Language Models (LLMs). In practice, LLMs are often required to handle a diverse set of tasks from multiple domains, a scenario naturally addressed by multi-task…
Building facial analysis systems that generalize to extreme variations in lighting and facial expressions is a challenging problem that can potentially be alleviated using natural-looking synthetic data. Towards that, we propose LEGAN, a…
Continual learning for vision-language models has achieved remarkable performance through synthetic replay, where samples are generated using Stable Diffusion to regularize during finetuning and retain knowledge. However, real-world…
Visual analogy learning enables image manipulation through demonstration rather than textual description, allowing users to specify complex transformations difficult to articulate in words. Given a triplet $\{\mathbf{a}$, $\mathbf{a}'$,…
Vision-Language-Action (VLA) models have recently emerged, demonstrating strong generalization in robotic scene understanding and manipulation. However, when confronted with long-horizon tasks that require defined goal states, such as LEGO…
Image Forgery Localization (IFL) technology aims to detect and locate the forged areas in an image, which is very important in the field of digital forensics. However, existing IFL methods suffer from feature degradation during training…
We report a new method to generate uniform large-scale optical focus arrays (LOFAs). By identifying and removing undesired phase rotation in the iterative Fourier-transform algorithm (IFTA), our approach rapidly produces computer-generated…
The rapid advancement of AI-generation models has enabled the creation of hyperrealistic imagery, posing ethical risks through widespread misinformation. Current deepfake detection methods, categorized as face specific detectors or general…
Collaborative autonomous driving with multiple vehicles usually requires the data fusion from multiple modalities. To ensure effective fusion, the data from each individual modality shall maintain a reasonably high quality. However, in…