Few-Shot Learning

Follow this topic Ask about this topic

Recent momentum

-33%

10 papers in the last 28 days · 0.2% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

4 new papers

A weekly snapshot of new work published in Few-Shot Learning.

Period ending 2026-09-14

6 new papers

A weekly snapshot of new work published in Few-Shot Learning.

Period ending 2026-09-07

3 new papers

A weekly snapshot of new work published in Few-Shot Learning.

119 papers

Latest in Few-Shot Learning

Browse all topics →

The Geometry of Saturation: Effective Rank Predicts When Labels Stop Helping in Few-Shot Classification
Jun 12, 2026Arnav GuptaBinary Classification Saturation
Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pseudo Class-variable Training
Jun 8, 2026Yanxiong Li, Guoqing Chen, Qianqian Li +1Domain Incremental Learning Few-Shot Learning
GP-Adapter: Gaussian Process CLIP-Adapter for Few-Shot Out-of-Distribution Detection
Jun 5, 2026Taisei Saito, Koretaka Ogata, Takafumi HiroiOut-Of-Distribution Detection Few-Shot Learning
BayaHAR: Lightweight Bayesian Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition
Jun 3, 2026Maximilian Burzer, Till Riedel, Michael Beigl +1Human Activity Recognition Parameter-Efficient Adaptation
Re-Evaluating Continual Learning with Few-Shot Adaptation
Jun 2, 2026Amogh Inamdar, Matthew So, Vici Milenia +1Efficient Continual Learning Continual Learning Methods
Provable Data Scaling Law for Meta Learning via Complexity Minimization
Jun 1, 2026Kazuto Fukuchi, Ryuichiro Hataya, Kota MatsuiMeta-Learning Model Pretraining
Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation
May 29, 2026Nan Bao, Yifan Zhao, Wenzhuang Wang +1Large-Scale Image Generation Few-Shot Learning
Primitive Subspaces Mediate Few-Shot Transfer in VLAs
May 29, 2026Anya Singh, Cabrel Happi, Jai Relan +2Vision-Language-Action Models Few-Shot Learning
MEMENTO: Leveraging Web as a Learning Signal for Low-Data Domains
May 28, 2026Ashutosh Ojha, Vinay Aggarwal, Ashutosh Srivastava +3Web Few-Shot Learning
UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning
May 27, 2026Volodymyr OvcharovLegal Natural Language Processing Benchmarks Ukrainian
Learning to Translate from Soft to Hard LLM Prompts
May 26, 2026Pitipat Kongsomjit, Suryansh Goyal, Jacob WhitehillMachine Translation Models Prompt Tuning
FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations
May 26, 2026Haolong Zheng, Siyin Wang, Xulin Fan +2Large Audio Language Models Few-Shot Learning
Advancing Graph Few-Shot Learning via In-Context Learning
May 23, 2026Renchu Guan, Yajun Wang, Chunli Guo +5Few-Shot Learning In-Context Learning
Towards a General Intelligence and Interface for Wearable Health Data
May 21, 2026Girish Narayanswamy, Maxwell A. Xu, A. Ali Heydari +37Wearable Devices Few-Shot Learning
Zero-shot adaptation to order book dynamics
May 20, 2026Arip AsadulaevMatching Markets Order
PrAda: Few-Shot Visual Adaptation for Text-Prompted Segmentation
May 19, 2026Gabriele Rosi, Fabio Cermelli, Carlo Masone +1Few-Shot Segmentation Few-Shot Learning
From a Single Demonstration to a General Policy for Contact-Rich Manipulation
May 17, 2026Xing Li, Oliver BrockRobotic Manipulation Policies Real-World Manipulation Tasks
How Few-Shot Examples Add Up: A Causal Decomposition of Function Vectors in In-Context Learning
May 15, 2026Entang Wang, Yiwei Wang, Aleksandra Bakalova +1In-Context Learning Few-Shot Learning
Rethinking the Good Enough Embedding for Easy Few-Shot Learning
May 13, 2026Michael Karnes, Alper YilmazFew-Shot Learning Visual Embeddings
Teaching and Learning under Deductive Errors
May 13, 2026Jan Arne Telle, Brigt Håvardstun, Jose Hernandez-OralloReasoning Errors Errors
A $_3$ B $_2$ : Adaptive Asymmetric Adapter for Alleviating Branch Bias in Vision-Language Image Classification with Few-Shot Learning
May 13, 2026Yiyun Zhou, Zhonghua Jiang, Wenkang Han +4Vision-Language Model Adaptation Few-Shot Learning
Scaling few-shot spoken word classification with generative meta-continual learning
May 13, 2026Louise Beyers, Batsirayi Mupamhi Ziki, Ruan van der MerweFew-Shot Learning Subword Tokenization
Unlocking Compositional Generalization in Continual Few-Shot Learning
May 12, 2026Phu-Quy Nguyen-Lam, Phu-Hoa Pham, Dao Sy Duy Minh +3Few-Shot Learning Self-Supervised Vision Transformers
Reviving In-domain Fine-tuning Methods for Source-Free Cross-domain Few-shot Learning
May 12, 2026Yaze Zhao, Yicong Liu, Yixiong Zou +2Few-Shot Learning Contrastive Loss
Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning
May 11, 2026Yuna Haseyama, Tomoki Ito, Hiroki Sakaji +1Few-Shot Learning Annotated Data
When Adaptation Fails: A Gradient-Based Diagnosis of Collapsed Gating in Vision-Language Prompt Learning
May 10, 2026Yunxuan Fang, Ziwei Zhang, Xinhe WangVision-Language Model Adaptation Few-Shot Learning
Empowering VLMs for Few-Shot Multimodal Time Series Classification via Tailored Agentic Reasoning
May 10, 2026Lin Li, Jiawei Huang, Qihao Quan +7Time-Series Classification Few-Shot Learning
Large Language Models for Sequential Decision-Making: Improving In-Context Learning via Supervised Fine-Tuning
May 9, 2026Minmin Zhang, Sina Aghaei, Soroush SaghafianIn-Context Learning Large Language Model Fine-Tuning
MC-RFM: Geometry-Aware Few-Shot Adaptation via Mixed-Curvature Riemannian Flow Matching
May 8, 2026Salim Khazem, Ibrahim Mohamed Serouis, Zakaria EzzahedFew-Shot Learning
SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data
May 8, 2026Kacper Jurek, Wojciech Batko, Marek Śmieja +1Tabular Learning Semi-Supervised Learning
In-Context Fixation: When Demonstrated Labels Override Semantics in Few-Shot Classification
May 8, 2026Ming LiuFew-Shot Learning In-Context
GRaSp: Automatic Example Optimization for In-Context Learning in Low-Data Tasks
May 8, 2026Simen Bihaug-Frøyland, Henrik BrådlandIn-Context Learning Few-Shot Learning
Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation
May 6, 2026Hongxu Chen, Yanghao Wang, Bowei Zhu +6Few-Shot Learning Cross-Modal Alignment
Few-Shot Learning Pipeline for Monkeypox Skin Disease Classification Using CNN Feature Extractors
May 6, 2026Md. Safirur Rashid, Sabbir Ahmed, Muhammad Usama Islam +2Few-Shot Learning Skin Lesion Classification
AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse
May 5, 2026Jie Ou, Jinyu Guo, Shiyao Guo +5Few-Shot Learning In-Context Learning
SemEval-2026 Task 7: Everyday Knowledge Across Diverse Languages and Cultures
May 4, 2026Nedjma Ousidhoum, Junho Myung, Carla Perez-Almendros +27Multilingual Benchmark English
Ultrasound Vision-Language Alignment via Contrastive Learning
May 4, 2026Zhuoyang Lyu, Yiyang Zhang, Tongxin Wang +1Ultrasound Vision-Language Alignment
Chebyshev-Augmented One-Shot Transfer Learning for PINNs on Nonlinear Differential Equations
May 2, 2026Yiqi Rao, Pavlos ProtopapasPartial Differential Equation Benchmarks Transfer Learning
Improving Graph Few-shot Learning with Hyperbolic Space and Denoising Diffusion
Apr 30, 2026Yonghao Liu, Jialu Sun, Wei Pang +4Graph Representation Learning Few-Shot Learning
Improving Diversity in Black-box Few-shot Knowledge Distillation
Apr 28, 2026Tri-Nhan Vo, Dang Nguyen, Kien Do +1Knowledge Distillation Few-Shot Learning
Agri-CPJ: A Training-Free Explainable Framework for Agricultural Pest Diagnosis Using Caption-Prompt-Judge and LLM-as-a-Judge
Apr 26, 2026Wentao Zhang, Qi Zhang, Mingkun Xu +6Agricultural Landscapes Remote Sensing Image Change Captioning
VDLF-Net: Variational Feature Fusion for Adaptive and Few-Shot Visual Learning
Apr 26, 2026Jiawei YanFew-Shot Learning Feature Pyramid Networks
All Eyes on the Workflow: Automated and Efficient Event Discovery from Video Streams
Apr 24, 2026Marco Pegoraro, Jonas Seng, Dustin Heller +2Fine-Grained Video Understanding Streaming Video
Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models
Apr 22, 2026Sachin KumarLarge Language Model Adaptation Small Language Models
Beyond the Basics: Leveraging Large Language Model for Fine-Grained Medical Entity Recognition
Apr 19, 2026Nwe Ni Win, Jim Basilakis, Steven Thomas +6Medical Ontology Clinical Notes
SCHK-HTC: Sibling Contrastive Learning with Hierarchical Knowledge-Aware Prompt Tuning for Hierarchical Text Classification
Apr 17, 2026Ke Xiong, Qian Wu, Wangjie Gan +2Few-Shot Learning Hierarchical
HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning
Apr 17, 2026Eunju Lee, MiHyeon Kim, JuneHyoung Kwon +4Domain Incremental Learning Few-Shot Learning
Holistic Optimal Label Selection for Robust Prompt Learning under Partial Labels
Apr 8, 2026Yaqi Zhao, Haoliang Sun, Yating Wang +2Candidate Label Distributions Few-Shot Learning
When Sensing Varies with Contexts: Context Probing for Tactile Few-Shot Class-Incremental Learning
Mar 26, 2026Yifeng Lin, Aiping Huang, Wenxi Liu +4Domain Incremental Learning Few-Shot Learning
DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection
Mar 24, 2026Gautam Rajendrakumar Gare, Neehar Peri, Matvei Popov +3Open-Vocabulary Object Detection Object Detection
Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective
Dec 11, 2025Tian Liu, Anwesha Basu, James Caverlee +1Few-Shot Learning Semi-Supervised Learning
Visual Species Recognition with Large Multimodal Models as Post-Hoc Correctors
Dec 10, 2025Tian Liu, Anwesha Basu, James Caverlee +1Few-Shot Learning Post-Hoc
Context Tuning for In-Context Optimization
Jul 6, 2025Jack Lu, Ryan Teehan, Zhenbang Yang +1Few-Shot Learning Prompt Tuning
CLIP Embeddings for AI-Generated Image Detection: A Few-Shot Study with Lightweight Classifier
May 15, 2025Ziyang OuAi-Generated Image Detection Image Generation
DRESS: Disentangled Representation-based Self-Supervised Meta-Learning for Diverse Tasks
Mar 12, 2025Wei Cui, Tongzi Wu, Jesse C. Cresswell +2Meta-Learning Few-Shot Learning
Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
Jul 8, 2024Xiaojie Li, Yibo Yang, Jianlong Wu +4Domain Incremental Learning Few-Shot Learning
A Transformer-Based Contrastive Learning Approach for Few-Shot Sign Language Recognition
Apr 5, 2022Silvan Ferreira, Esdras Costa, Marcio Dahia +1Sign Language Recognition Contrastive Learning
Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptions
Date pendingAlejandro Galan-Cuenca, Marcelo Saval-Calvo, Antonio Javier GallegoFew-Shot Learning Target Domain
Ego-Dynamics-Augmented World Model for Autonomous Driving with Zero-Shot Cross-Embodiment Adaptation
Date pendingZhidong Wang, Jingsong Liang, Zirui Li +3Autonomous Driving World Models

Jun 12, 2026 · cs.LGJ/K move · Enter open · S save

The Geometry of Saturation: Effective Rank Predicts When Labels Stop Helping in Few-Shot Classification

Arnav Gupta

Independent Researcher, Nepal

Few-shot label acquisition lacks a label-free signal for when additional labels cease to improve accuracy: existing stopping criteria either require a held-out validation set (violating the few-shot premise) or rely on theoretically ungrounded heuristics, so we introduce the spectral saturation index

S(K)=\mathrm{erank}(\hatΣ_W^{(K)})/K

, the exponential spectral entropy of the pooled within-class covariance normalized by per-class support size

K

, which measures the exploration rate per label and falls below a fixed threshold

τ=0.02

once the explored spectral subspace saturates and marginal accuracy gains vanish; across 49 real tasks (binary, 5-way, 10-way) and three frozen backbones (PCA-50, CLIP ViT-B/32, DINOv2 ViT-S/14),

S(K)

correlates strongly with the marginal gain on doubling the support set (

ρ_{\text{pool}}=0.6366

p=2.9\times10^{-57}

, cluster-bootstrap 95% CI

[0.551,0.720]

), a fixed

τ=0.02

classifies stop/continue decisions with cluster-bootstrap

\mathrm{AUC}=0.787

(95% CI

[0.713,0.860]

) with high recall on meaningful gains (

ΔA>1\%

), and a partial correlation controlling for

\log K

yields

ρ_{\text{partial}}=0.324

(

p=1.65\times10^{-13}

), confirming

S(K)

carries spectral information beyond shared

K

-dependence; theory predicts this from first principles, since the population effective rank sets the saturation scale

K_{\text{sat}}\approx\mathrm{erank}(Σ_W)/τ

τ=0.02

sits at the boundary between the first and second descent (Nakkiran et al., 2021), and

O(1/K)

bias in the sample effective rank explains the small-

K

hump in

S(K)

; for unregularized linear probes (

C=\infty

), practitioners should halt when

S(K)<0.02

(PCA-50, hard stop) or monitor

S(K)

dropping from

\sim0.3\to0.05

(foundation models, diminishing-returns signal), with computation costing

\sim1

ms at

d=50

Binary Classification Saturation Spearman Correlation Intrinsic Dimensionality Covariance Estimation Few-Shot Learning

Open paper Ask about it PDF

Recent momentum

Neighbouring directions

Recent digests

4 new papers

6 new papers

3 new papers

Latest in Few-Shot Learning