English
Related papers

Related papers: Memory-Efficient Fine-Tuning of Transformers via T…

200 papers

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.…

Computation and Language · Computer Science 2024-02-27 Zekun Wang , Jingchang Chen , Wangchunshu Zhou , Haichao Zhu , Jiafeng Liang , Liping Shan , Ming Liu , Dongliang Xu , Qing Yang , Bing Qin

Prompt tuning is an emerging way of adapting pre-trained language models to downstream tasks. However, the existing studies are mainly to add prompts to the input sequence. This way would not work as expected due to the intermediate…

Computation and Language · Computer Science 2022-07-01 Jingping Liu , Yuqiu Song , Kui Xue , Hongli Sun , Chao Wang , Lihan Chen , Haiyun Jiang , Jiaqing Liang , Tong Ruan

The original softmax-based attention mechanism (regular attention) in the extremely successful Transformer architecture computes attention between $N$ tokens, each embedded in a $D$-dimensional head, with a time complexity of $O(N^2D)$.…

Machine Learning · Computer Science 2025-10-28 Armin Gerami , Ramani Duraiswami

Traditional transformer models often allocate a fixed amount of computational resources to every input token, leading to inefficient and unnecessary computation. To address this, the Mixture of Depths (MoD) was introduced to dynamically…

Computation and Language · Computer Science 2025-09-15 Shwai He , Tao Ge , Guoheng Sun , Bowei Tian , Xiaoyang Wang , Dong Yu

Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training…

Computation and Language · Computer Science 2026-05-20 Bowen Peng , Théo Gigant , Jeffrey Quesnelle

We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large language models struggle to solve compositional tasks, where the…

Computation and Language · Computer Science 2024-07-09 Eric Pasewark , Kyle Montgomery , Kefei Duan , Dawn Song , Chenguang Wang

Utilizing large-scale pretrained models is a well-known strategy to enhance performance on various target tasks. It is typically achieved through fine-tuning pretrained models on target tasks. However, na\"{\i}ve fine-tuning may not fully…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Seungwon Seo , Suho Lee , Sangheum Hwang

Recent works on parameter-efficient transfer learning (PETL) show the potential to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters. However, since they usually insert new…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Taolin Zhang , Jiawang Bai , Zhihe Lu , Dongze Lian , Genping Wang , Xinchao Wang , Shu-Tao Xia

Finetuning large language models (LLMs) has been empirically effective on a variety of downstream tasks. Existing approaches to finetuning an LLM either focus on parameter-efficient finetuning, which only updates a small number of trainable…

Machine Learning · Computer Science 2024-01-17 Zhengxin Zhang , Dan Zhao , Xupeng Miao , Gabriele Oliaro , Qing Li , Yong Jiang , Zhihao Jia

Transfer learning is the predominant paradigm for training deep networks on small target datasets. Models are typically pretrained on large ``upstream'' datasets for classification, as such labels are easy to collect, and then finetuned on…

Computer Vision and Pattern Recognition · Computer Science 2022-07-11 Anurag Arnab , Xuehan Xiong , Alexey Gritsenko , Rob Romijnders , Josip Djolonga , Mostafa Dehghani , Chen Sun , Mario Lučić , Cordelia Schmid

Recent works attribute the capability of in-context learning (ICL) in large pre-trained language models to implicitly simulating and fine-tuning an internal model (e.g., linear or 2-layer MLP) during inference. However, such constructions…

Computation and Language · Computer Science 2024-02-09 Abhishek Panigrahi , Sadhika Malladi , Mengzhou Xia , Sanjeev Arora

The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Chaoyu Li , Yogesh Kulkarni , Pooyan Fazli

Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the sequence level, applying uniform updates across all tokens…

Computation and Language · Computer Science 2026-05-07 Jiawei Wu , Doudou Zhou

Nowadays, AI researchers become more and more interested in fine-tuning a pre-trained LLM, whose size has grown to up to over 100B parameters, for their downstream tasks. One approach to fine-tune such huge models is to aggregate device…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-25 Changyue Liao , Mo Sun , Zihan Yang , Jun Xie , Kaiqi Chen , Binhang Yuan , Fei Wu , Zeke Wang

Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…

Machine Learning · Computer Science 2025-12-24 Shoaib Mohammad , Guanqun Song , Ting Zhu

Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying pretrained model is updated or retrained (e.g., on larger and more curated datasets), the fine-tuned model…

Deep learning models generally display catastrophic forgetting when learning new data continuously. Many incremental learning approaches address this problem by reusing data from previous tasks while learning new tasks. However, the direct…

Machine Learning · Computer Science 2024-11-12 Young Jo Choi , Min Kyoon Yoo , Yu Rang Park

Post-training alignment is central to deploying large language models (LLMs), yet practical workflows remain split across backend-specific tools and ad-hoc glue code, making experiments hard to reproduce. We identify backend interference,…

Deploying natural language processing (NLP) models on mobile platforms requires models that can adapt across diverse applications while remaining efficient in memory and computation. We investigate pre-finetuning strategies to enhance the…

Computation and Language · Computer Science 2025-10-10 Junyi Zhu , Savas Ozkan , Andrea Maracani , Sinan Mutlu , Cho Jung Min , Mete Ozay

Diffusion transformers have shown significant effectiveness in both image and video synthesis at the expense of huge computation costs. To address this problem, feature caching methods have been introduced to accelerate diffusion…

Machine Learning · Computer Science 2025-02-20 Chang Zou , Xuyang Liu , Ting Liu , Siteng Huang , Linfeng Zhang