English
Related papers

Related papers: Efficient Many-Shot In-Context Learning with Dynam…

200 papers

Many real-world classification problems often have classes with very few labeled training samples. Moreover, all possible classes may not be initially available for training, and may be given incrementally. Deep learning models need to deal…

Computer Vision and Pattern Recognition · Computer Science 2021-03-02 Pratik Mazumder , Pravendra Singh , Piyush Rai

In-context learning has become an important approach for few-shot learning in Large Language Models because of its ability to rapidly adapt to new tasks without fine-tuning model parameters. However, it is restricted to applications in…

Machine Learning · Computer Science 2023-10-16 Christopher Fifty , Jure Leskovec , Sebastian Thrun

Traditional recognition methods typically require large, artificially-balanced training classes, while few-shot learning methods are tested on artificially small ones. In contrast to both extremes, real world recognition problems exhibit…

Computer Vision and Pattern Recognition · Computer Science 2019-07-03 Davis Wertheimer , Bharath Hariharan

Like generic multi-task learning, continual learning has the nature of multi-objective optimization, and therefore faces a trade-off between the performance of different tasks. That is, to optimize for the current task distribution, it may…

Machine Learning · Computer Science 2023-10-11 Pengyuan Lu , Michele Caprio , Eric Eaton , Insup Lee

In-Context Learning (ICL) has significantly expanded the general-purpose nature of large language models, allowing them to adapt to novel tasks using merely the inputted context. This has motivated a series of papers that analyze tractable…

Machine Learning · Computer Science 2025-05-05 Core Francisco Park , Ekdeep Singh Lubana , Itamar Pres , Hidenori Tanaka

In-context learning (ICL) allows large models to adapt to tasks using a few examples, yet its extension to vision-language models (VLMs) remains fragile. Our analysis reveals that the fundamental limitation lies in an inductive gap, models…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Haoyu Wang , Haonan Wang , Yuyan Chen , Jun Chen , Gang Liu , Qian Wang , Jiahong Yan , Yanghua Xiao

We study the \emph{in-context learning} (ICL) ability of a \emph{Linear Transformer Block} (LTB) that combines a linear attention component and a linear multi-layer perceptron (MLP) component. For ICL of linear regression with a Gaussian…

Machine Learning · Statistics 2024-02-26 Ruiqi Zhang , Jingfeng Wu , Peter L. Bartlett

Deploying Large Language Models (LLMs) on edge devices remains challenging due to their quadratically increasing computations with the sequence length. Existing studies for dynamic attention pruning are designed for hardware with massively…

Artificial Intelligence · Computer Science 2025-07-29 Jiawen Qi , Chang Gao , Zhaochun Ren , Qinyu Chen

Few-shot object detection, the problem of modelling novel object detection categories with few training instances, is an emerging topic in the area of few-shot learning and object detection. Contemporary techniques can be divided into two…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Berkan Demirel , Orhun Buğra Baran , Ramazan Gokberk Cinbis

The continual learning setting aims to learn new tasks over time without forgetting the previous ones. The literature reports several significant efforts to tackle this problem with limited or no access to previous task data. Among such…

Computer Vision and Pattern Recognition · Computer Science 2022-10-07 Vishal Thengane , Salman Khan , Munawar Hayat , Fahad Khan

Humans possess remarkable ability to accurately classify new, unseen images after being exposed to only a few examples. Such ability stems from their capacity to identify common features shared between new and previously seen images while…

Computer Vision and Pattern Recognition · Computer Science 2024-05-07 Weihao Jiang , Chang Liu , Kun He

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…

Machine Learning · Computer Science 2025-02-19 Kan Zhu , Tian Tang , Qinyu Xu , Yile Gu , Zhichen Zeng , Rohan Kadekodi , Liangyu Zhao , Ang Li , Arvind Krishnamurthy , Baris Kasikci

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-06-06 Thomas Bouvier , Bogdan Nicolae , Hugo Chaugier , Alexandru Costan , Ian Foster , Gabriel Antoniu

Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning. However, the incremental learning issue of CL has rarely been…

Machine Learning · Computer Science 2023-01-31 Cheng Ji , Jianxin Li , Hao Peng , Jia Wu , Xingcheng Fu , Qingyun Sun , Phillip S. Yu

Few-shot learning allows pre-trained language models to adapt to downstream tasks while using a limited number of training examples. However, practical applications are limited when all model parameters must be optimized. In this work we…

Computation and Language · Computer Science 2023-02-01 Ethan Kim , Jerry Yang

Large language models (LLMs) have become the norm in natural language processing (NLP), excelling in few-shot in-context learning (ICL) with their remarkable abilities. Nonetheless, the success of ICL largely hinges on the choice of…

Computation and Language · Computer Science 2025-05-06 Xingxuan Li , Xuan-Phi Nguyen , Shafiq Joty , Lidong Bing

We argue that in-context learning (ICL) predictably arises from standard self-supervised next-token pretraining, rather than being an exotic emergent property. This work establishes the foundational principles of this emergence by focusing…

Machine Learning · Computer Science 2025-07-15 Paul M. Riechers , Henry R. Bigelow , Eric A. Alt , Adam Shai

With increasing demand for efficient image and video analysis, test-time cost of scene parsing becomes critical for many large-scale or time-sensitive vision applications. We propose a dynamic hierarchical model for anytime scene labeling…

Computer Vision and Pattern Recognition · Computer Science 2016-08-12 Buyu Liu , Xuming He

Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sensitive learning require prior-knowledge to train the system.…

Computer Vision and Pattern Recognition · Computer Science 2019-08-16 Yiru Wang , Weihao Gan , Jie Yang , Wei Wu , Junjie Yan

Large language models (LLMs) have exhibited striking in-context learning (ICL) ability to adapt to target tasks with a few input-output demonstrations. For better ICL, different methods are proposed to select representative demonstrations…

Computation and Language · Computer Science 2023-10-24 Wei-Lin Chen , Cheng-Kuang Wu , Yun-Nung Chen , Hsin-Hsi Chen