English
Related papers

Related papers: Scaling Laws for Many-Shot In-Context Learning wit…

200 papers

Long-context large language models (LLMs) are able to process inputs containing up to several million tokens. In the scope of in-context learning (ICL), this translates into using hundreds/thousands of demonstrations in the input prompt,…

Computation and Language · Computer Science 2025-09-03 Shahriar Golchin , Yanfei Chen , Rujun Han , Manan Gandhi , Tianli Yu , Swaroop Mishra , Mihai Surdeanu , Rishabh Agarwal , Chen-Yu Lee , Tomas Pfister

Deep learning models have achieved state-of-the-art performance in many computer vision tasks. However, in real-world scenarios, novel classes that were unseen during training often emerge, requiring models to acquire new knowledge…

Computer Vision and Pattern Recognition · Computer Science 2025-09-01 Lucas Rakotoarivony

The ability of robots to manipulate objects relies heavily on their aptitude for visual perception. In domains characterized by cluttered scenes and high object variability, most methods call for vast labeled datasets, laboriously…

Computer Vision and Pattern Recognition · Computer Science 2025-02-13 Moshe Kimhi , David Vainshtein , Chaim Baskin , Dotan Di Castro

Training deep models with limited annotations poses a significant challenge when applied to diverse practical domains. Employing semi-supervised learning alongside the self-supervised model offers the potential to enhance label efficiency.…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Ziting Wen , Oscar Pizarro , Stefan Williams

Real-world applications of large language models (LLMs) in computational social science (CSS) tasks primarily depend on the effectiveness of instruction tuning (IT) or in-context learning (ICL). While IT has shown highly effective at…

Computation and Language · Computer Science 2024-09-24 Taihang Wang , Xiaoman Xu , Yimin Wang , Ye Jiang

Recent advances in large language models (LLMs) enable effective in-context learning (ICL) with many-shot examples, but at the cost of high computational demand due to longer input tokens. To address this, we propose cheat-sheet ICL, which…

Computation and Language · Computer Science 2025-09-26 Ukyo Honda , Soichiro Murakami , Peinan Zhang

In-context learning (ICL) is a few-shot learning paradigm that involves learning mappings through input-output pairs and appropriately applying them to new instances. Despite the remarkable ICL capabilities demonstrated by Large Language…

Computation and Language · Computer Science 2024-08-06 Peng Wang , Xiaobin Wang , Chao Lou , Shengyu Mao , Pengjun Xie , Yong Jiang

In-context learning (ICL) allows large language models (LLMs) to adapt to new tasks from a few examples, making it promising for languages underrepresented in pre-training. Recent work on many-shot ICL suggests that modern LLMs can further…

Computation and Language · Computer Science 2026-04-07 Yinhan Lu , Gaganpreet Jhajj , Chen Zhang , Anietie Andy , David Ifeoluwa Adelani

Vision-language foundation models have shown promising zero-shot generalization for Cross-Domain Few-Shot Object Detection (CD-FSOD). However, they face two critical challenges in fine-tuning: insufficient support set utilization due to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Jiacong Liu , Shu Luo , Yikai Qin , Yaze Zhao , Yongwei Jiang , Yixiong Zou

The emergence of in-context learning (ICL) enables large pre-trained language models (PLMs) to make predictions for unseen inputs without updating parameters. Despite its potential, ICL's effectiveness heavily relies on the quality,…

Machine Learning · Computer Science 2024-07-02 Xiaoling Zhou , Wei Ye , Yidong Wang , Chaoya Jiang , Zhemg Lee , Rui Xie , Shikun Zhang

Previous studies have shown that demonstrations can significantly help Large Language Models (LLMs ) perform better on the given tasks. However, this so-called In-Context Learning ( ICL ) ability is very sensitive to the presenting context,…

Artificial Intelligence · Computer Science 2024-09-27 Weixing Wang , Haojin Yang , Christoph Meinel

Humans are capable of learning new concepts from only a few (labeled) exemplars, incrementally and continually. This happens within the context that we can differentiate among the exemplars, and between the exemplars and large amounts of…

Machine Learning · Computer Science 2022-02-08 Daniel T. Chang

We study in-context learning (ICL) of linear regression in a deep linear self-attention model, characterizing how performance depends on various computational and statistical resources (width, depth, number of training steps, batch size and…

Machine Learning · Statistics 2025-10-02 Blake Bordelon , Mary I. Letey , Cengiz Pehlevan

While semi-supervised learning (SSL) algorithms provide an efficient way to make use of both labelled and unlabelled data, they generally struggle when the number of annotated samples is very small. In this work, we consider the problem of…

Computer Vision and Pattern Recognition · Computer Science 2020-04-23 Sylvestre-Alvise Rebuffi , Sebastien Ehrhardt , Kai Han , Andrea Vedaldi , Andrew Zisserman

In-context learning (ICL) leverages in-context examples as prompts for the predictions of Large Language Models (LLMs). These prompts play a crucial role in achieving strong performance. However, the selection of suitable prompts from a…

Machine Learning · Computer Science 2024-09-16 Jian Qian , Miao Sun , Sifan Zhou , Ziyu Zhao , Ruizhi Hun , Patrick Chiang

Large Language Models (LLMs) have shown strong performance on NLP classification tasks. However, they typically rely on aggregated labels-often via majority voting-which can obscure the human disagreement inherent in subjective annotations.…

Computation and Language · Computer Science 2025-06-09 Benedetta Muscato , Yue Li , Gizem Gezici , Zhixue Zhao , Fosca Giannotti

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Computer Vision and Pattern Recognition · Computer Science 2024-06-28 Qian-Wei Wang , Yuqiu Xie , Letian Zhang , Zimo Liu , Shu-Tao Xia

Large language models (LLMs) excel at few-shot in-context learning (ICL) without requiring parameter updates. However, as ICL demonstrations increase from a few to many, performance tends to plateau and eventually decline. We identify two…

Machine Learning · Computer Science 2025-05-28 Xiaoqing Zhang , Ang Lv , Yuhan Liu , Flood Sung , Wei Liu , Jian Luan , Shuo Shang , Xiuying Chen , Rui Yan

Few-Shot Class-Incremental Learning has shown remarkable efficacy in efficient learning new concepts with limited annotations. Nevertheless, the heuristic few-shot annotations may not always cover the most informative samples, which largely…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Zitong Huang , Ze Chen , Yuanze Li , Bowen Dong , Erjin Zhou , Yong Liu , Rick Siow Mong Goh , Chun-Mei Feng , Wangmeng Zuo

In-context learning (ICL) is a powerful paradigm emerged from large language models (LLMs). Despite its promises, ICL performance is known to be highly sensitive to input examples. In this work, we use $\textit{in-context influences}$ to…

Computation and Language · Computer Science 2023-06-06 Tai Nguyen , Eric Wong