Related papers: JointTuner: Appearance-Motion Adaptive Joint Train…
With the advance of text-to-image (T2I) diffusion models (e.g., Stable Diffusion) and corresponding personalization techniques such as DreamBooth and LoRA, everyone can manifest their imagination into high-quality images at an affordable…
Video Diffusion Models (VDMs) have demonstrated remarkable capabilities in synthesizing realistic videos by learning from large-scale data. Although vanilla Low-Rank Adaptation (LoRA) can learn specific spatial or temporal movement to…
Low-Rank Adaptation (LoRA) has emerged as an effective technique for reducing memory overhead in fine-tuning large language models. However, it often suffers from sub-optimal performance compared with full fine-tuning since the update is…
Low-Rank Adaptation (LoRA) has emerged as a powerful and popular technique for personalization, enabling efficient adaptation of pre-trained image generation models for specific tasks without comprehensive retraining. While employing…
Differentially private federated fine-tuning of large models with LoRA suffers from aggregation error caused by LoRA's multiplicative structure, which is further amplified by DP noise and degrades both stability and accuracy. Existing…
Fine-Tuning Diffusion Models enable a wide range of personalized generation and editing applications on diverse visual modalities. While Low-Rank Adaptation (LoRA) accelerates the fine-tuning process, it still requires multiple reference…
In recent years, motion generative models have undergone significant advancement, yet pose challenges in aligning with downstream objectives. Recent studies have shown that using differentiable rewards to directly align the preference of…
Video outpainting is a challenging task, aiming at generating video content outside the viewport of the input video while maintaining inter-frame and intra-frame consistency. Existing methods fall short in either generation quality or…
Low-Rank Adaptation (LoRA) has emerged as a promising paradigm for Continual Learning. It independently updates its low-rank factors ($A$ and $B$), creating a composite update to the full weight matrix through their interaction. To prevent…
Fine-tuning text-to-image diffusion models is widely used for personalization and adaptation for new domains. In this paper, we identify a critical vulnerability of fine-tuning: safety alignment methods designed to filter harmful content…
Generating realistic talking-head videos remains challenging due to persistent issues such as imperfect lip synchronization, unnatural motion, and evaluation metrics that correlate poorly with human perception. We propose FlowPortrait, a…
Fine-tuning facilitates the adaptation of text-to-image generative models to novel concepts (e.g., styles and portraits), empowering users to forge creatively customized content. Recent efforts on fine-tuning focus on reducing training data…
Recent video diffusion models generate photorealistic, temporally coherent videos, yet they fall short as reliable world models for autonomous driving, where structured motion and physically consistent interactions are essential. Adapting…
Video segmentation approaches are of great importance for numerous vision tasks especially in video manipulation for entertainment. Due to the challenges associated with acquiring high-quality per-frame segmentation annotations and large…
The rapid development of Large Language Models (LLMs) has been pivotal in advancing AI, with pre-trained LLMs being adaptable to diverse downstream tasks through fine-tuning. Federated learning (FL) further enhances fine-tuning in a…
Filmmaking and animation production often require sophisticated techniques for coordinating camera transitions and object movements, typically involving labor-intensive real-world capturing. Despite advancements in generative AI for video…
The foundation models have recently shown excellent performance on a variety of downstream tasks in computer vision. However, most existing vision foundation models simply focus on image-level pretraining and adpation, which are limited for…
Low-Rank Adaptation (LoRA) is a crucial method for efficiently fine-tuning large language models (LLMs), with its effectiveness influenced by two key factors: rank selection and weight initialization. While numerous LoRA variants have been…
Prompt learning is effective for fine-tuning foundation models to improve their generalization across a variety of downstream tasks. However, the prompts that are independently optimized along a single modality path, may sacrifice the…
Face videos accompanied by audio have become integral to our daily lives, while they often suffer from complex degradations. Most face video restoration methods neglect the intrinsic correlations between the visual and audio features,…