English
Related papers

Related papers: AdapterTune: Zero-Initialized Low-Rank Adapters fo…

200 papers

Vision-language models (VLMs) have achieved impressive performance on multimodal reasoning tasks such as visual question answering, image captioning and so on, but their inference cost remains a significant challenge due to the large number…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Weichen Zhang , Zhui Zhu , Ningbo Li , Shilong Tao , Kebin Liu , Yunhao Liu

As the computational needs of Large Vision-Language Models (LVLMs) increase, visual token pruning has proven effective in improving inference speed and memory efficiency. Traditional pruning methods in LVLMs predominantly focus on attention…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Bozhi Luan , Wengang Zhou , Hao Feng , Zhe Wang , Xiaosong Li , Houqiang Li

When quantizing neural networks, assigning each floating-point weight to its nearest fixed-point value is the predominant approach. We find that, perhaps surprisingly, this is not the best we can do. In this paper, we propose AdaRound, a…

Machine Learning · Computer Science 2020-07-01 Markus Nagel , Rana Ali Amjad , Mart van Baalen , Christos Louizos , Tijmen Blankevoort

Image Coding for Machines (ICM) focuses on optimizing image compression for AI-driven analysis rather than human perception. Existing ICM frameworks often rely on separate codecs for specific tasks, leading to significant storage…

Image and Video Processing · Electrical Eng. & Systems 2025-05-30 Yichi Zhang , Zhihao Duan , Yuning Huang , Fengqing Zhu

Deploying vision foundation models typically relies on efficient adaptation strategies, whereas conventional full fine-tuning suffers from prohibitive costs and low efficiency. While delta-tuning has proven effective in boosting the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-12 Dongshuo Yin , Xue Yang , Deng-Ping Fan , Shi-Min Hu

We analyze the operation of transformer language adapters, which are small modules trained on top of a frozen language model to adapt its predictions to new target languages. We show that adapted predictions mostly evolve in the source…

Computation and Language · Computer Science 2024-06-11 Jesujoba O. Alabi , Marius Mosbach , Matan Eyal , Dietrich Klakow , Mor Geva

Adapting large pre-trained models to unseen tasks under tight data and compute budgets remains challenging. Meta-learning approaches explicitly learn good initializations, but they require an additional meta-training phase over many tasks,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Junghwan Park , Woojin Cho , Junhyuk Heo , Darongsae Kwon , Kookjin Lee

Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which…

Computer Vision and Pattern Recognition · Computer Science 2024-08-13 Sungyeon Kim , Boseung Jeong , Donghyun Kim , Suha Kwak

Frozen pretrained image representations are widely used for transfer learning: a backbone is kept fixed, feature vectors are extracted, and a lightweight classifier is trained on top. This pipeline usually feeds the full feature vector to…

Machine Learning · Computer Science 2026-05-12 Indar Kumar , Girish Karhana , Sai Krishna Jasti , Ankit Hemant Lade

Advanced compiler technology is crucial for enabling machine learning applications to run on novel hardware, but traditional compilers fail to deliver performance, popular auto-tuners have long search times and expert-optimized libraries…

Machine Learning · Computer Science 2023-11-09 Dejan Grubisic , Bram Wasti , Chris Cummins , John Mellor-Crummey , Aleksandar Zlateski

We develop a continual learning method for pretrained models that \emph{requires no access to old-task data}, addressing a practical barrier in foundation model adaptation where pretraining distributions are often unavailable. Our key…

Machine Learning · Computer Science 2026-02-04 Romain Cosentino

State-of-the-art neural (re)rankers are notoriously data-hungry which -- given the lack of large-scale training data in languages other than English -- makes them rarely used in multilingual and cross-lingual retrieval settings. Current…

Computation and Language · Computer Science 2022-09-20 Robert Litschko , Ivan Vulić , Goran Glavaš

Point cloud video understanding is critical for robotics as it accurately encodes motion and scene interaction. We recognize that 4D datasets are far scarcer than 3D ones, which hampers the scalability of self-supervised 4D models. A…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Yiding Sun , Jihua Zhu , Haozhe Cheng , Chaoyi Lu , Zhichuan Yang , Lin Chen , Yaonan Wang

Cloud segmentation is a critical challenge in remote sensing image interpretation, as its accuracy directly impacts the effectiveness of subsequent data processing and analysis. Recently, vision foundation models (VFM) have demonstrated…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Xuechao Zou , Shun Zhang , Kai Li , Shiying Wang , Junliang Xing , Lei Jin , Congyan Lang , Pin Tao

How many of a neural network's parameters actually encode task-specific information? We investigate this question with LottaLoRA, a training paradigm in which every backbone weight is drawn at random and frozen; only low-rank LoRA adapters…

Machine Learning · Computer Science 2026-04-14 Hananel Hazan , Yanbo Zhang , Benedikt Hartl , Michael Levin

Parameter-efficient transfer learning (PETL) is an emerging research spot aimed at inexpensively adapting large-scale pre-trained models to downstream tasks. Recent advances have achieved great success in saving storage costs for various…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Gen Luo , Minglang Huang , Yiyi Zhou , Xiaoshuai Sun , Guannan Jiang , Zhiyu Wang , Rongrong Ji

As natural image understanding moves towards the pretrain-finetune era, research in pathology imaging is concurrently evolving. Despite the predominant focus on pretraining pathological foundation models, how to adapt foundation models to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Jiaxuan Lu , Fang Yan , Xiaofan Zhang , Yue Gao , Shaoting Zhang

With the development of deep networks on various large-scale datasets, a large zoo of pretrained models are available. When transferring from a model zoo, applying classic single-model based transfer learning methods to each source model…

Machine Learning · Computer Science 2021-06-30 Yang Shu , Zhi Kou , Zhangjie Cao , Jianmin Wang , Mingsheng Long

Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compression are typically composed in sequence. This decoupled practice first…

Artificial Intelligence · Computer Science 2026-05-05 Jingze Ge , Yun Liu , Xue Geng , Wanqi Dong , Wang Zhe Mark , Min Wu , Xulei Yang

Approximate computing is known for enhancing deep neural network accelerators' energy efficiency by introducing inexactness with a tolerable accuracy loss. However, small accuracy variations may increase the sensitivity of these…

Hardware Architecture · Computer Science 2023-02-23 Ayesha Siddique , Khaza Anuarul Hoque