English
Related papers

Related papers: Vocabulary In-Context Learning in Transformers: Be…

200 papers

The Abstraction and Reasoning Corpus challenges AI systems to perform abstract reasoning with minimal training data, a task intuitive for humans but demanding for machine learning models. Using CodeT5+ as a case study, we demonstrate how…

Artificial Intelligence · Computer Science 2025-02-04 Guilherme H. Bandeira Costa , Miguel Freire , Arlindo L. Oliveira

Visual In-Context Learning (VICL) is a prevailing way to transfer visual foundation models to new tasks by leveraging contextual information contained in in-context examples to enhance learning and prediction of query sample. The…

Computer Vision and Pattern Recognition · Computer Science 2024-10-11 Chengming Xu , Chen Liu , Yikai Wang , Yuan Yao , Yanwei Fu

Multimodal in-context learning (ICL) has emerged as a key capability of Large Vision-Language Models (LVLMs), driven by their increasing scale and applicability. Despite its promise, effective ICL in the multimodal setting remains…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Yanshu Li

The in-context learning (ICL) capability of pre-trained models based on the transformer architecture has received growing interest in recent years. While theoretical understanding has been obtained for ICL in reinforcement learning (RL),…

Machine Learning · Statistics 2024-11-03 Chengshuai Shi , Kun Yang , Jing Yang , Cong Shen

Large language models have demonstrated the ability to perform \textit{in-context learning} (ICL), whereby the model performs predictions by directly mapping the query and a few examples from the given task to the output variable. In this…

Signal Processing · Electrical Eng. & Systems 2025-12-02 Meng Hua , Wenjing Zhang , Chenghong Bian , Deniz Gunduz

Preventing the performance decay of Transformers on inputs longer than those used for training has been an important challenge in extending the context length of these models. Though the Transformer architecture has fundamentally no limits…

In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter updates. Existing theories primarily study ICL in single-task…

Machine Learning · Computer Science 2026-05-28 Guangyu Li , Meng Ding , Lijie Hu

Transformer models, notably large language models (LLMs), have the remarkable ability to perform in-context learning (ICL) -- to perform new tasks when prompted with unseen input-output examples without any explicit model training. In this…

Machine Learning · Computer Science 2023-11-03 Steve Yadlowsky , Lyric Doshi , Nilesh Tripuraneni

In this work, we investigate the positional encoding methods used in language pre-training (e.g., BERT) and identify several problems in the existing formulations. First, we show that in the absolute positional encoding, the addition…

Computation and Language · Computer Science 2021-03-16 Guolin Ke , Di He , Tie-Yan Liu

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Computation and Language · Computer Science 2025-09-23 Asif Shahriar , Rifat Shahriyar , M Saifur Rahman

In this paper, we explore the potential of visual in-context learning to enable a single model to handle multiple tasks and adapt to new tasks during test time without re-training. Unlike previous approaches, our focus is on training…

Computer Vision and Pattern Recognition · Computer Science 2025-07-03 Simon Reiß , Zdravko Marinov , Alexander Jaus , Constantin Seibold , M. Saquib Sarfraz , Erik Rodner , Rainer Stiefelhagen

In-context learning (ICL) is the remarkable ability displayed by some machine learning models to learn from examples provided in a user prompt without any model parameter updates. ICL was first observed in the domain of large language…

Machine Learning · Computer Science 2025-11-03 Shao-Ting Chiu , Junyuan Hong , Ulisses Braga-Neto

In-context learning (ICL) is a key building block of modern large language models, yet its theoretical mechanisms remain poorly understood. It is particularly mysterious how ICL operates in real-world applications where tasks have a common…

Disordered Systems and Neural Networks · Physics 2026-04-24 Kaito Takanami , Takashi Takahashi , Yoshiyuki Kabashima

Vision-language models (VLMs), serve as foundation models for multi-modal applications such as image captioning and text-to-image generation. Recent studies have highlighted limitations in VLM text encoders, particularly in areas like…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Sri Harsha Dumpala , David Arps , Sageev Oore , Laura Kallmeyer , Hassan Sajjad

Multimodal in-context learning (ICL) has emerged as a key mechanism for harnessing the capabilities of large vision-language models (LVLMs). However, its effectiveness remains highly sensitive to the quality of input ICL sequences,…

Computation and Language · Computer Science 2025-10-22 Yanshu Li , Jianjiang Yang , Tian Yun , Pinyuan Feng , Jinfa Huang , Ruixiang Tang

Transformer-based large language models have displayed impressive in-context learning capabilities, where a pre-trained model can handle new tasks without fine-tuning by simply augmenting the query with some input-output examples from that…

Machine Learning · Computer Science 2024-06-18 Hongkang Li , Meng Wang , Songtao Lu , Xiaodong Cui , Pin-Yu Chen

Visual In-Context Learning (VICL) has emerged as a powerful paradigm, enabling models to perform novel visual tasks by learning from in-context examples. The dominant "retrieve-then-prompt" approach typically relies on selecting the single…

Computer Vision and Pattern Recognition · Computer Science 2026-01-16 Wenwen Liao , Jianbo Yu , Yuansong Wang , Qingchao Jiang , Xiaofeng Yang

Transformers predict over a representation of a sequence. The same data can be written as bytes, characters, or subword tokens, and these representations may be lossless. Yet, under a fixed context window, they need not expose the same…

Machine Learning · Computer Science 2026-05-14 Amirmehdi Jafari Fesharaki , Mohammadamin Rami , Aslan Tchamkerten

Sequence models have demonstrated the ability to perform tasks like channel equalization and symbol detection by automatically adapting to current channel conditions. This is done without requiring any explicit optimization and by…

Signal Processing · Electrical Eng. & Systems 2024-11-01 Zihang Song , Matteo Zecchin , Bipin Rajendran , Osvaldo Simeone

With in-context learning ability, the performance of large language models can be significantly boosted when provided with appropriate context. However, existing in-context learning methods mainly rely on human-provided contexts, such as…

Machine Learning · Computer Science 2024-08-21 Jinghan Yang , Shuming Ma , Furu Wei
‹ Prev 1 8 9 10 Next ›