Related papers: LoRA-Loop: Closing the Synthetic Replay Cycle for …

The persistent challenge of medical image synthesis posed by the scarcity of annotated data and the need to synthesize `missing modalities' for multi-modal analysis, underscored the imperative development of effective synthesis methods.…

Large Language Models (LLMs) such as ChatGPT demonstrate strong few-shot adaptability without requiring fine-tuning, positioning them ideal for data-limited and real-time applications. However, this adaptability has not yet been replicated…

Continual learning in large language models (LLMs) typically encounters the critical challenge of catastrophic forgetting, where previously acquired knowledge deteriorates upon exposure to new data. While techniques like replay buffers and…

Current vision-language models (VLMs) still exhibit inferior performance on knowledge-intensive tasks, primarily due to the challenge of accurately encoding all the associations between visual objects and scenes to their corresponding…

We present Stable Video Diffusion - a latent video diffusion model for high-resolution, state-of-the-art text-to-video and image-to-video generation. Recently, latent diffusion models trained for 2D image synthesis have been turned into…

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…

Recent advances in diffusion-based generative models have demonstrated significant potential in augmenting scarce datasets for object detection tasks. Nevertheless, most recent models rely on resource-intensive full fine-tuning of…

This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. While diffusion models are widely known to provide excellent generative modeling capability, practical…

Parameter-Efficient Fine-Tuning (PEFT), particularly Low-Rank Adaptation (LoRA), has become a standard approach for adapting Large Language Models (LLMs) under limited compute. However, in continual settings where models are updated…

Advancements in deep image synthesis techniques, such as generative adversarial networks (GANs) and diffusion models (DMs), have ushered in an era of generating highly realistic images. While this technological progress has captured…

Continual learning (CL) aims to learn new tasks without erasing previous knowledge. However, current CL methods primarily emphasize improving accuracy while often neglecting training efficiency, which consequently restricts their practical…

Large-scale Vision-Language Models (VLMs) have transformed general-purpose visual recognition through strong zero-shot capabilities. However, their performance degrades significantly in niche, safety-critical domains such as industrial…

Parameter generation has emerged as a novel paradigm for neural network development, offering an alternative to traditional neural network training by synthesizing high-quality model weights directly. In the context of Low-Rank Adaptation…

Existing research has shown that large language models (LLMs) exhibit remarkable performance in language understanding and generation. However, when LLMs are continuously fine-tuned on complex and diverse domain-specific downstream tasks,…

Generalization remains a core challenge in embodied AI, as robots must adapt to diverse environments. While OpenVLA represents the State-of-the-Art (SOTA) in Vision-Language-Action models by leveraging large-scale pre-training, its…

Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning would allow for…

LoRA-based continual learning represents a promising avenue for leveraging pre-trained models in downstream continual learning tasks. Recent studies have shown that orthogonal LoRA tuning effectively mitigates forgetting. However, this work…

Although pre-trained Vision-Language-Action (VLA) models exhibit impressive generalization in robotic manipulation, post-training remains crucial to ensure reliable performance during deployment. However, standard offline Supervised…

Recent works demonstrate a remarkable ability to customize text-to-image diffusion models while only providing a few example images. What happens if you try to customize such models using multiple, fine-grained concepts in a sequential…

Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…