Related papers: Efficient Adaptation of Large Vision Transformer v…

Fine-tuning large pre-trained models is an effective transfer mechanism in NLP. However, in the presence of many downstream tasks, fine-tuning is parameter inefficient: an entire new model is required for every task. As an alternative, we…

Visual foundation models like CLIP excel in learning feature representations from extensive datasets through self-supervised methods, demonstrating remarkable transfer learning and generalization capabilities. A growing number of…

Recent works have shown that large models pretrained on common visual learning tasks can provide useful representations for a wide range of specialized perception problems, as well as a variety of robotic manipulation tasks. While prior…

We propose a novel Auto-Regressive (AR) image generation approach that models images as hierarchical compositions of interpretable visual layers. While AR models have achieved transformative success in language modeling, replicating this…

This paper presents a framework for efficient 3D clothed avatar reconstruction. By combining the advantages of the high accuracy of optimization-based methods and the efficiency of learning-based methods, we propose a coarse-to-fine way to…

Contrastively trained vision-language models such as CLIP provide strong zero-shot transfer by aligning images and text in a shared embedding space. However, adapting these models to downstream tasks without degrading their open-vocabulary…

Following the success in NLP, the best vision models are now in the billion parameter ranges. Adapting these large models to a target distribution has become computationally and economically prohibitive. Addressing this challenge, we…

Low-rank adaptation (LoRA) has achieved remarkable success in fine-tuning pre-trained vision transformers for various downstream tasks. Existing studies mainly focus on exploring more parameter-efficient strategies or more effective…

Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep…

Graph Convolutional Networks (GCNs) have become a crucial tool on learning representations of graph vertices. The main challenge of adapting GCNs on large-scale graphs is the scalability issue that it incurs heavy cost both in computation…

The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-frequency regions (e.g., edges and textures) are most critical…

In recent years, pretrained large language models have demonstrated outstanding performance across various natural language processing tasks. However, full-parameter fine-tuning methods require adjusting all model parameters, leading to…

Deep convolutional neural networks (CNNs) have shown excellent performance in object recognition tasks and dense classification problems such as semantic segmentation. However, training deep neural networks on large and sparse datasets is…

Efficient fine-tuning methods are critical to address the high computational and parameter complexity while adapting large pre-trained models to downstream tasks. Our study is inspired by prior research that represents each convolution…

Applying feature dependent network weights have been proved to be effective in many fields. However, in practice, restricted by the enormous size of model parameters and memory footprints, scalable and versatile dynamic convolutions with…

Reducing dimensionality is a key preprocessing step in many data analysis applications to address the negative effects of the curse of dimensionality and collinearity on model performance and computational complexity, to denoise the data or…

Deep convolutional neural network based image super-resolution (SR) models have shown superior performance in recovering the underlying high resolution (HR) images from low resolution (LR) images obtained from the predefined downscaling…

In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual…

Large-scale autoregressive models have demonstrated remarkable capabilities in image generation. However, their sequential raster-scan decoding relies on strictly next-token prediction, making inference prohibitively expensive. Existing…

Model Predictive Control (MPC) is a method to control nonlinear systems with guaranteed stability and constraint satisfaction but suffers from high computation times. Approximate MPC (AMPC) with neural networks (NNs) has emerged to address…