🧬Language Models

In-Context Learning

Learning from examples in the prompt without fine-tuning

83 papers1,122 total citations
Compare with other topics
Mar '24 β€” Feb '2663 papers
Also includes: in-context learning, icl, few-shot prompting, prompt-based learning

Top Papers

#1

Generative Multimodal Models are In-Context Learners

Quan Sun, Yufeng Cui, Xiaosong Zhang et al.

CVPR 2024arXiv:2312.13286
422
citations
#2

Understanding Catastrophic Forgetting in Language Models via Implicit Inference

Suhas Kotha, Jacob Springer, Aditi Raghunathan

ICLR 2024arXiv:2309.10105
103
citations
#3

Consistency-guided Prompt Learning for Vision-Language Models

Shuvendu Roy, Ali Etemad

ICLR 2024arXiv:2306.01195
91
citations
#4

Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering

Han Zhou, Xingchen Wan, Lev Proleev et al.

ICLR 2024arXiv:2309.17249
81
citations
#5

In-Context Learning Learns Label Relationships but Is Not Conventional Learning

Jannik Kossen, Yarin Gal, Tom Rainforth

ICLR 2024arXiv:2307.12375
53
citations
#6

Visual In-Context Prompting

Feng Li, Qing Jiang, Hao Zhang et al.

CVPR 2024arXiv:2311.13601
52
citations
#7

Two-stage LLM Fine-tuning with Less Specialization and More Generalization

Yihan Wang, Si Si, Daliang Li et al.

ICLR 2024arXiv:2211.00635
42
citations
#8

When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations

Aleksandar Petrov, Philip Torr, Adel Bibi

ICLR 2024arXiv:2310.19698
38
citations
#9

Which Attention Heads Matter for In-Context Learning?

Kayo Yin, Jacob Steinhardt

ICML 2025arXiv:2502.14010
34
citations
#10

Understanding In-Context Learning from Repetitions

Jianhao (Elliott) Yan, Jin Xu, Chiyu Song et al.

ICLR 2024arXiv:2310.00297
29
citations
#11

Semantic Residual Prompts for Continual Learning

Martin Menabue, Emanuele Frascaroli, Matteo Boschini et al.

ECCV 2024
24
citations
#12

Customizing Language Model Responses with Contrastive In-Context Learning

Xiang Gao, Kamalika Das

AAAI 2024arXiv:2401.17390
contrastive learninglanguage model alignmentin-context learningintent customization+4
19
citations
#13

Context Diffusion: In-Context Aware Image Generation

Ivona Najdenkoska, Animesh Sinha, Abhimanyu Dubey et al.

ECCV 2024arXiv:2312.03584
16
citations
#14

Learning to Learn Better Visual Prompts

Fengxiang Wang, Wanrong Huang, Shaowu Yang et al.

AAAI 2024
14
citations
#15

Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective

Minh Le, Tien Ngoc Luu, An Nguyen The et al.

AAAI 2025arXiv:2412.08285
11
citations
#16

Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models

Can Demircan, Tankred Saanum, Akshay Jagadish et al.

ICLR 2025
11
citations
#17

Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting

Suraj Anand, Michael Lepori, Jack Merullo et al.

ICLR 2025
10
citations
#18

Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance

Sachin Goyal, Christina Baek, Zico Kolter et al.

ICLR 2025
instruction finetuningcontext relianceparametric knowledgemodel hallucinations+3
9
citations
#19

Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior

Youngjae Cho, HeeSun Bae, Seungjae Shin et al.

AAAI 2024arXiv:2401.06799
vision-language pretrained modelsprompt learningfew-shot learningbayesian modeling+4
9
citations
#20

Implicit In-context Learning

Zhuowei Li, Zihao Xu, Ligong Han et al.

ICLR 2025arXiv:2405.14660
in-context learninglarge language modelsinference-time interventioncontext vector generation+4
8
citations
#21

Mimic In-Context Learning for Multimodal Tasks

Yuchu Jiang, Jiale Fu, chenduo hao et al.

CVPR 2025arXiv:2504.08851
8
citations
#22

In-Context Learning and Occam's Razor

Eric Elmoznino, Tom Marty, Tejas Kasetty et al.

ICML 2025arXiv:2410.14086
5
citations
#23

Understanding Prompt Tuning and In-Context Learning via Meta-Learning

Tim Genewein, Kevin Li, Jordi Grau-Moya et al.

NeurIPS 2025arXiv:2505.17010
prompt tuningin-context learningmeta-learningbayesian predictors+4
4
citations
#24

The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation

Patrick Kahardipraja, Reduan Achtibat, Thomas Wiegand et al.

NeurIPS 2025arXiv:2505.15807
4
citations
#25

ARTICLE: Annotator Reliability Through In-Context Learning

Sujan Dutta, Deepak Pandita, Tharindu Cyril Weerasooriya et al.

AAAI 2025arXiv:2409.12218
4
citations
#26

Do different prompting methods yield a common task representation in language models?

Guy Davidson, Todd Gureckis, Brenden Lake et al.

NeurIPS 2025
4
citations
#27

On the Loss of Context Awareness in General Instruction Fine-tuning

Yihan Wang, Andrew Bai, Nanyun Peng et al.

NeurIPS 2025
4
citations
#28

SEC-Prompt:SEmantic Complementary Prompting for Few-Shot Class-Incremental Learning

Ye Liu, Meng Yang

CVPR 2025
2
citations
#29

Embracing Collaboration Over Competition: Condensing Multiple Prompts for Visual In-Context Learning

Jinpeng Wang, Tianci Luo, Yaohua Zha et al.

CVPR 2025
2
citations
#30

Teaching VLMs to Localize Specific Objects from In-context Examples

Sivan Doveh, Nimrod Shabtay, Eli Schwartz et al.

ICCV 2025arXiv:2411.13317
2
citations
#31

Federated In-Context Learning: Iterative Refinement for Improved Answer Quality

Ruhan Wang, Zhiyong Wang, Chengkai Huang et al.

ICML 2025arXiv:2506.07440
2
citations
#32

Exploring Task-Level Optimal Prompts for Visual In-Context Learning

Yan Zhu, Huan Ma, Changqing Zhang

AAAI 2025arXiv:2501.08841
2
citations
#33

Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning

Cheng Chen, Yunpeng Zhai, Yifan Zhao et al.

CVPR 2025arXiv:2506.09473
1
citations
#34

All You Need is One: Capsule Prompt Tuning with a Single Vector

Yiyang Liu, James Liang, Heng Fan et al.

NeurIPS 2025
1
citations
#35

Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective

Jianyu Wang, Zhiqiang Hu, Lidong Bing

ICML 2025arXiv:2506.17930
1
citations
#36

An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning

Chen Jin, Ryutaro Tanno, Amrutha Saseendran et al.

ICML 2024arXiv:2310.12274
prompt learningtextual inversionmulti-concept learningattention masking+3
β€”
not collected
#37

Convolutional Prompting meets Language Models for Continual Learning

Anurag Roy, Riddhiman Moulick, Vinay Verma et al.

CVPR 2024arXiv:2403.20317
β€”
not collected
#38

Emergence of In-Context Reinforcement Learning from Noise Distillation

Ilya Zisman, Vladislav Kurenkov, Alexander Nikulin et al.

ICML 2024
in-context reinforcement learningnoise-induced curriculumdata acquisitionsynthetic noise injection+2
β€”
not collected
#39

Active Prompt Learning in Vision Language Models

Jihwan Bang, Sumyeong Ahn, Jae-Gil Lee

CVPR 2024
β€”
not collected
#40

The mechanistic basis of data dependence and abrupt learning in an in-context classification task

Gautam Reddy Nallamala

ICLR 2024
β€”
not collected
#41

One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning

Doyoung Kim, Susik Yoon, Dongmin Park et al.

ICML 2024arXiv:2311.12048
continual learningadaptive prompt tuningsemantic shift adaptationprompt management strategies+3
β€”
not collected
#42

BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction

Jiangmeng Li, Fei Song, Yifan Jin et al.

ICLR 2024
β€”
not collected
#43

IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models

Shaokun Zhang, Xiaobo Xia, Zhaoqing Wang et al.

ICLR 2024arXiv:2310.10873
β€”
not collected
#44

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence

Gouki Minegishi, Hiroki Furuta, Shohei Taniguchi et al.

ICML 2025arXiv:2505.16694
β€”
not collected
#45

On the Power of Context-Enhanced Learning in LLMs

Xingyu Zhu, Abhishek Panigrahi, Sanjeev Arora

ICML 2025arXiv:2503.01821
β€”
not collected
#46

Context is Environment

Sharut Gupta, Stefanie Jegelka, David Lopez-Paz et al.

ICLR 2024
β€”
not collected
#47

Understanding Synthetic Context Extension via Retrieval Heads

Xinyu Zhao, Fangcong Yin, Greg Durrett

ICML 2025
β€”
not collected
#48

Iterative Vectors: In-Context Gradient Steering without Backpropagation

Yiting Liu, Zhi-Hong Deng

ICML 2025
β€”
not collected
#49

Prompt Gradient Projection for Continual Learning

Jingyang Qiao, Zhizhong Zhang, Xin Tan et al.

ICLR 2024
β€”
not collected
#50

In-Context Fine-Tuning for Time-Series Foundation Models

Matthew Faw, Rajat Sen, Yichen Zhou et al.

ICML 2025arXiv:2410.24087
β€”
not collected
#51

RCS-Prompt: Learning Prompt to Rearrange Class Space for Prompt-based Continual Learning

Longrong Yang, Hanbin Zhao, Yunlong Yu et al.

ECCV 2024
β€”
not collected
#52

Rethinking and Improving Visual Prompt Selection for In-Context Learning Segmentation Framework

Wei Suo, Lanqing Lai, Mengyang Sun et al.

ECCV 2024
in-context learningimage segmentationvisual prompt selectioncontextual example diversity+2
β€”
not collected
#53

X-Prompt: Generalizable Auto-Regressive Visual Learning with In-Context Prompting

Zeyi Sun, Ziyang Chu, Pan Zhang et al.

ICCV 2025
β€”
not collected
#54

GalLop: Learning global and local prompts for vision-language models

Marc Lafon, Elias Ramzi, ClΓ©ment Rambour et al.

ECCV 2024arXiv:2407.01400
prompt learningvision-language modelsfew-shot classificationdomain generalization+4
β€”
not collected
#55

One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts

Ruochen Wang, Sohyun An, Minhao Cheng et al.

ICML 2024
instruction design automationmixture-of-expert paradigmin-context learningkernel regression theory+3
β€”
not collected
#56

Generalization to New Sequential Decision Making Tasks with In-Context Learning

Sharath Chandra Raparthy, Eric Hambro, Robert Kirk et al.

ICML 2024
in-context learningsequential decision makingoffline datasetstransformers+4
β€”
not collected
#57

In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Sheng Liu, Haotian Ye, Lei Xing et al.

ICML 2024
in-context learninglatent space steeringlarge language modelsvector arithmetic+4
β€”
not collected
#58

In-Context Principle Learning from Mistakes

Tianjun Zhang, Aman Madaan, Luyu Gao et al.

ICML 2024
in-context learningfew-shot promptingmulti-hop question answeringtextual question answering+4
β€”
not collected
#59

Conditional Language Learning with Context

Xiao Zhang, Miao Li, Ji Wu

ICML 2024
conditional language modelingselective learningdomain finetuningtopic bias mitigation+3
β€”
not collected
#60

In-Context Learning Agents Are Asymmetric Belief Updaters

Johannes A. Schubert, Akshay Kumar Jagadish, Marcel Binz et al.

ICML 2024
in-context learningbelief updatinglarge language modelscognitive psychology tasks+3
β€”
not collected
#61

DeCoOp: Robust Prompt Tuning with Out-of-Distribution Detection

Zhi Zhou, Ming Yang, Jiang-Xin Shi et al.

ICML 2024
prompt tuningvision-language modelsout-of-distribution detectionzero-shot learning+3
β€”
not collected
#62

Dual Operating Modes of In-Context Learning

Ziqian Lin, Kangwook Lee

ICML 2024
in-context learningtask retrievaltask learningprobabilistic modeling+3
β€”
not collected
#63

Revisiting the Power of Prompt for Visual Tuning

Yuzhu Wang, Lechao Cheng, Chaowei Fang et al.

ICML 2024
visual prompt tuningprompt initializationself-supervised pretrainingtoken prototypes+4
β€”
not collected
#64

In-Context Language Learning: Architectures and Algorithms

Ekin AkyΓΌrek, Bailin Wang, Yoon Kim et al.

ICML 2024
in-context learningformal language learningregular languagestransformer architecture+4
β€”
not collected
#65

AIM: Let Any Multimodal Large Language Models Embrace Efficient In-Context Learning

Jun Gao, Qian Qiao, Tianxiang Wu et al.

AAAI 2025
β€”
not collected
#66

Teaching LLMs How to Learn with Contextual Fine-Tuning

Younwoo Choi, Muhammad Adil Asif, Ziwen Han et al.

ICLR 2025
β€”
not collected
#67

CoPL: Contextual Prompt Learning for Vision-Language Understanding

Koustava Goswami, Srikrishna Karanam, Prateksha Udhayanan et al.

AAAI 2024arXiv:2307.00910
β€”
not collected
#68

Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts

Jiawen Zhu, Guansong Pang

CVPR 2024
β€”
not collected
#69

Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learning

Jian Lang, Zhangtao Cheng, Ting Zhong et al.

AAAI 2025
β€”
not collected
#70

Unsupervised Continual Anomaly Detection with Contrastively-Learned Prompt

Jiaqi Liu, Kai Wu, Qiang Nie et al.

AAAI 2024
β€”
not collected
#71

Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models

Yubin Wang, Xinyang Jiang, De Cheng et al.

AAAI 2024arXiv:2312.06323
prompt learningvision-language modelsstructured linguistic knowledgehierarchical prompt tuning+4
β€”
not collected
#72

Evolving Parameterized Prompt Memory for Continual Learning

Muhammad Rifki Kurniawan, Xiang Song, Zhiheng Ma et al.

AAAI 2024
β€”
not collected
#73

CLiC: Concept Learning in Context

Mehdi Safaee, Aryan Mikaeili, Or Patashnik et al.

CVPR 2024arXiv:2311.17083
β€”
not collected
#74

Why In-Context Learning Models are Good Few-Shot Learners?

Shiguang Wu, Yaqing Wang, Quanming Yao

ICLR 2025
in-context learningfew-shot learningmeta-learningtransformer architecture+4
β€”
not collected
#75

Vision and Language Synergy for Rehearsal Free Continual Learning

Muhammad Anwar Masum, Mahardhika Pratama, Savitha Ramasamy et al.

ICLR 2025
β€”
not collected
#76

Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks

Vishnu Sarukkai, Zhiqiang Xie, Kayvon Fatahalian

NeurIPS 2025arXiv:2505.00234
in-context learningsequential decision-makingllm agentstrajectory bootstrapping+3
β€”
not collected
#77

Toward Understanding In-context vs. In-weight Learning

Bryan Chan, Xinyi Chen, Andras Gyorgy et al.

ICLR 2025arXiv:2410.23042
β€”
not collected
#78

Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt Tuning

Yilun Li, Miaomiao Cheng, Xu Han et al.

ICLR 2025
prompt tuningvision-language modelsknowledge-guided context optimizationhilbert-schmidt independence criterion+3
β€”
not collected
#79

Is In-Context Learning Sufficient for Instruction Following in LLMs?

Hao Zhao, Maksym Andriushchenko, francesco croce et al.

ICLR 2025arXiv:2405.19874
in-context learninginstruction followingllm alignmentinstruction fine-tuning+2
β€”
not collected
#80

In-Context Editing: Learning Knowledge from Self-Induced Distributions

Siyuan Qi, Bangcheng Yang, Kailin Jiang et al.

ICLR 2025
β€”
not collected
#81

Chain-of-Focus Prompting: Leveraging Sequential Visual Cues to Prompt Large Autoregressive Vision Models

Jiyang Zheng, Jialiang Shen, Yu Yao et al.

ICLR 2025
β€”
not collected
#82

Technical Debt in In-Context Learning: Diminishing Efficiency in Long Context

Taejong Joo, Diego Klabjan

NeurIPS 2025arXiv:2502.04580
in-context learningtransformer architecturesample complexitybayes optimal estimator+4
β€”
not collected
#83

Disentangling Latent Shifts of In-Context Learning with Weak Supervision

Josip Jukić, Jan Šnajder

NeurIPS 2025
β€”
not collected