Related papers: Pear: Pruning and Sharing Adapters in Visual Param…

Instruction tuning has shown promising potential for developing general-purpose AI capabilities by using large-scale pre-trained models and boosts growing research to integrate multimodal information for creative applications. However,…

Pruning is an effective method to reduce the memory footprint and FLOPs associated with neural network models. However, existing structured-pruning methods often result in significant accuracy degradation for moderate pruning levels. To…

Network-based transfer learning allows the reuse of deep learning features with limited data, but the resulting models can be unnecessarily large. Although network pruning can improve inference efficiency, existing algorithms usually…

Recently, foundation models based on Vision Transformers (ViTs) have become widely available. However, their fine-tuning process is highly resource-intensive, and it hinders their adoption in several edge or low-energy applications. To this…

Recently vision transformer models have become prominent models for a range of tasks. These models, however, usually suffer from intensive computational costs and heavy memory requirements, making them impractical for deployment on edge…

Despite achieving remarkable performance on various vision-language tasks, Transformer-based Vision-Language Models (VLMs) suffer from redundancy in inputs and parameters, significantly hampering their efficiency in real-world applications.…

Pruning is a widely used method for compressing Deep Neural Networks (DNNs), where less relevant parameters are removed from a DNN model to reduce its size. However, removing parameters reduces model accuracy, so pruning is typically…

Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…

Model pruning is a performance optimization technique for large language models like R1 or o3-mini. However, existing pruning methods often lead to significant performance degradation or require extensive retraining and fine-tuning. This…

Deploying deep neural networks (DNNs) on edge devices requires strong compression with minimal accuracy loss. This paper introduces Mix-and-Match Pruning, a globally guided, layer-wise sparsification framework that leverages sensitivity…

Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms. However, most of the pruning techniques are…

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…

Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to…

The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can…

Many state-of-the-art computer vision algorithms use large scale convolutional neural networks (CNNs) as basic building blocks. These CNNs are known for their huge number of parameters, high redundancy in weights, and tremendous computing…

Existing feature-interpretation pipelines typically operate on uniformly sampled units or exhaustive feature sets, incurring massive costs on units irrelevant to target behaviors. To address this, we introduce the first CLT-native…

Adapter-tuning is a paradigm that transfers a pretrained language model to downstream tasks by adding and tuning a small number of new parameters. Previously proposed adapter architectures are all feed-forward neural networks. In this…

Pruning is widely used to reduce the complexity of deep learning models, but its effects on interpretability and representation learning remain poorly understood. This paper investigates how pruning influences vision models across three key…

The continual learning literature has rapidly shifted from traditional class incremental learning (CIL) techniques to foundation model (FM)-based CIL methods without a clear understanding of how these newer approaches compare to strong,…

Large, pre-trained models are problematic to use in resource constrained applications. Fortunately, task-aware structured pruning methods offer a solution. These approaches reduce model size by dropping structural units like layers and…