mlsanityData to 14 Oct 2026

Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition

arXiv 2602.19385 ↗First posted 22 Feb 2026cs.CV cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recognizing implicit visual and textual patterns is essential in many real-world applications of modern AI. However, tackling long-tail pattern recognition tasks remains challenging for current pre-trained foundation models such as LLMs and VLMs. While finetuning pre-trained models can improve accuracy in recognizing implicit patterns, it is usually infeasible due to a lack of training data and high computational overhead. In this paper, we propose ADAMAB, an efficient embedding calibration framework for few-shot pattern recognition. To maximally reduce the computational costs, ADAMAB trains embedder-agnostic light-weight calibrators on top of fixed embedding models without accessing their parameters. To mitigate the need for large-scale training data, we introduce an adaptive data augmentation strategy based on the Multi-Armed Bandit (MAB) mechanism. With a modified upper confidence bound algorithm, ADAMAB diminishes the gradient shifting and offers theoretically guaranteed convergence in few-shot training. Our multi-modal experiments justify the superior performance of ADAMAB, with up to 40% accuracy improvement when training with less than 5 initial data samples of each class.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 51 of its 75 references that are in the map. First posted on arXiv 22 Feb 2026.

Builds on

51 of 75 references.

References · 51

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  6. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  7. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
  8. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Modelscited by 489
  9. 2022Active Example Selection for In-Context Learningcited by 196
  10. 2023Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?cited by 168
  11. 2022Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Orderingcited by 161
  12. 2023What Makes Good Examples for Visual In-Context Learning?cited by 150
38 more
  1. 2022Pretrained Language Models for Text Generation: A Surveycited by 122
  2. 2023Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!cited by 119
  3. 2023Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMscited by 115
  4. 2023A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directionscited by 105
  5. 2019A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descentcited by 84
  6. 2023Benchmarking large language models for biomedical natural language processing applications and recommendationscited by 78
  7. 2024The Neglected Tails in Vision-Language Modelscited by 63
  8. 2024Instruction-tuned Language Models are Better Knowledge Learnerscited by 55
  9. 2023Active Learning Principles for In-Context Learning with Large Language Modelscited by 54
  10. 2023How Many Demonstrations Do You Need for In-context Learning?cited by 52
  11. 2024CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendationcited by 44
  12. 2021FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learningcited by 43
  13. 2025Implicit Reasoning in Large Language Models: A Comprehensive Surveycited by 43
  14. 2024A Survey on Data Synthesis and Augmentation for Large Language Modelscited by 41
  15. 2024RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewardscited by 33
  16. 2022Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reductioncited by 32
  17. 2024Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challengescited by 30
  18. 2015Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Banditscited by 29
  19. 2025Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimizationcited by 29
  20. 2024SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domainscited by 28
  21. 2025From Selection to Generation: A Survey of LLM-based Active Learningcited by 19
  22. 2024ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarioscited by 18
  23. 2024Empowering Large Language Models for Textual Data Augmentationcited by 17
  24. 2024UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generationcited by 16
  25. 2025APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Trainingcited by 12
  26. 2024LLM-DA: Data Augmentation via Large Language Models for Few-Shot Named Entity Recognitioncited by 11
  27. 2024On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Modelscited by 10
  28. 2025LLM-based Query Expansion Fails for Unfamiliar and Ambiguous Queriescited by 10
  29. 2025ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignmentcited by 10
  30. 2024Assessing "Implicit" Retrieval Robustness of Large Language Modelscited by 9
  31. 2024VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actionscited by 8
  32. 2024Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation for Classificationcited by 7
  33. 2025Diversity-oriented Data Augmentation with Large Language Modelscited by 7
  34. 2024Language Model-Driven Data Pruning Enables Efficient Active Learningcited by 6
  35. 2025RLHF Fine-Tuning of LLMs for Alignment with Implicit User Feedback in Conversational Recommenderscited by 5
  36. 2024Building a Family of Data Augmentation Models for Low-cost LLM Fine-tuning on the Cloudcited by 4
  37. 2024Active Learning for NLP with Large Language Modelscited by 2
  38. 2024LLM-assisted Labeling Function Generation for Semantic Type Detectioncited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AFA-BANDIT: Provably Near-Optimal Online Multi-Feature Classification Under Budget Constraints
  2. 2026HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning
  3. 2023Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression
  4. 2024CIA: Controllable Image Augmentation Framework Based on Stable Diffusion
  5. 2024Multi-Armed Bandit Approach for Optimizing Training on Synthetic Data
  6. 2026Divide et Calibra: Multiclass Local Calibration via Vector Quantization
  7. 2025Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration
  8. 2025Panda: Test-Time Adaptation with Negative Data Augmentation