SOTAVerified

Few-Shot Learning

Few-Shot Learning is an example of meta-learning, where a learner is trained on several related tasks, during the meta-training phase, so that it can generalize well to unseen (but related) tasks with just few examples, during the meta-testing phase. An effective approach to the Few-Shot Learning problem is to learn a common representation for various tasks and train task specific classifiers on top of this representation.

Source: Penalty Method for Inversion-Free Deep Bilevel Optimization

Papers

Showing 150 of 2964 papers

TitleStatusHype
Rethinking the Sample Relations for Few-Shot ClassificationCode7
LLaMA: Open and Efficient Foundation Language ModelsCode7
SGLang: Efficient Execution of Structured Language Model ProgramsCode6
GPT-4 Technical ReportCode6
Zephyr: Direct Distillation of LM AlignmentCode5
SymbolicAI: A framework for logic-based approaches combining generative models and solversCode5
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt CompressionCode5
Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue AbilitiesCode5
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time SeriesCode4
Efficient Few-Shot Learning Without PromptsCode4
What Makes Good In-Context Examples for GPT-3?Code4
Flamingo: a Visual Language Model for Few-Shot LearningCode4
iText2KG: Incremental Knowledge Graphs Construction Using Large Language ModelsCode4
MEDITRON-70B: Scaling Medical Pretraining for Large Language ModelsCode4
Prototypical Verbalizer for Prompt-based Few-shot TuningCode4
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and OpportunitiesCode4
No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene SegmentationCode4
Large Language Models Are Human-Level Prompt EngineersCode3
LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text PairsCode3
Language Models are Few-Shot LearnersCode3
Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language AlignmentCode3
LLM4Drive: A Survey of Large Language Models for Autonomous DrivingCode3
When LLMs are Unfit Use FastFit: Fast and Effective Text Classification with Many ClassesCode3
Vision-Language Pre-training: Basics, Recent Advances, and Future TrendsCode3
The Surprising Effectiveness of Test-Time Training for Few-Shot LearningCode3
PCToolkit: A Unified Plug-and-Play Prompt Compression Toolkit of Large Language ModelsCode3
Reason-RFT: Reinforcement Fine-Tuning for Visual ReasoningCode3
Low-Rank Few-Shot Adaptation of Vision-Language ModelsCode3
LongBench: A Bilingual, Multitask Benchmark for Long Context UnderstandingCode3
Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language ModelCode3
Big Transfer (BiT): General Visual Representation LearningCode2
LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process ThinkingCode2
Large Language Models are Zero-Shot ReasonersCode2
Large Language Models to Enhance Bayesian OptimizationCode2
LibFewShot: A Comprehensive Library for Few-shot LearningCode2
A Survey of Time Series Foundation Models: Generalizing Time Series Representation with Large Language ModelCode2
Language Model CascadesCode2
Improving Factuality and Reasoning in Language Models through Multiagent DebateCode2
In-BoXBART: Get Instructions into Biomedical Multi-Task LearningCode2
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and TransportationCode2
Hungry Hungry Hippos: Towards Language Modeling with State Space ModelsCode2
Global Convergence and Generalization Bound of Gradient-Based Meta-Learning with Deep Neural NetsCode2
Few-Shot Scene Classification of Optical Remote Sensing Images Leveraging Calibrated Pretext TasksCode2
Atlas: Few-shot Learning with Retrieval Augmented Language ModelsCode2
FewJoint: A Few-shot Learning Benchmark for Joint Language UnderstandingCode2
AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2Code2
Feature Learning in Infinite-Width Neural NetworksCode2
Few-Shot Bearing Fault Diagnosis Via Ensembling Transformer-Based Model With Mahalanobis Distance Metric Learning From Multiscale FeaturesCode2
AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot LearningCode2
EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health RecordsCode2
Show:102550
← PrevPage 1 of 60Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1gpt-4-0125-previewAccuracy61.91Unverified
2gpt-4-0125-previewAccuracy52.49Unverified
3gpt-3.5-turboAccuracy41.48Unverified
4gpt-3.5-turboAccuracy37.06Unverified
5johnsnowlabs/JSL-MedMNX-7BAccuracy25.63Unverified
6yikuan8/Clinical-LongformerAccuracy25.55Unverified
7BioMistral/BioMistral-7B-DAREAccuracy25.06Unverified
8yikuan8/Clinical-LongformerAccuracy25.04Unverified
9PharMolix/BioMedGPT-LM-7BAccuracy24.92Unverified
10PharMolix/BioMedGPT-LM-7BAccuracy24.75Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean67.27Unverified
2SaSPA + CAL4-shot Accuracy48.3Unverified
3Real-Guidance + CAL4-shot Accuracy41.5Unverified
4CAL4-shot Accuracy40.9Unverified
#ModelMetricClaimedVerifiedStatus
1SaSPA + CALHarmonic mean52.2Unverified
2CALHarmonic mean35.2Unverified
3Variational Prompt TuningHarmonic mean34.69Unverified
4Real-Guidance + CALHarmonic mean34.5Unverified
#ModelMetricClaimedVerifiedStatus
1BGNNAccuracy92.7Unverified
2TIM-GDAccuracy87.4Unverified
3UNEM-GaussianAccuracy66.4Unverified
#ModelMetricClaimedVerifiedStatus
1EASY (transductive)Accuracy82.75Unverified
2HCTransformers5 way 1~2 shot74.74Unverified
3HyperShotAccuracy53.18Unverified
#ModelMetricClaimedVerifiedStatus
1SaSPA + CAL4-shot Accuracy66.7Unverified
2Real-Guidance + CAL4-shot Accuracy44.3Unverified
3CAL4-shot Accuracy42.2Unverified
#ModelMetricClaimedVerifiedStatus
1HCTransformersAcc74.74Unverified
2DPGNAcc67.6Unverified
#ModelMetricClaimedVerifiedStatus
1MetaGen Blended RAG (zero-shot)Accuracy77.9Unverified
2CoT-T5-11B (1024 Shot)Accuracy73.42Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean96.44Unverified
#ModelMetricClaimedVerifiedStatus
1CoT-T5-11B (1024 Shot)Accuracy68.3Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean77.71Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean81.12Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean91.57Unverified
#ModelMetricClaimedVerifiedStatus
1CovidExpertAUC-ROC1Unverified
#ModelMetricClaimedVerifiedStatus
1CoT-T5-11B (1024 Shot)Accuracy78.02Unverified
#ModelMetricClaimedVerifiedStatus
1UNEM-GaussianAccuracy65.7Unverified
#ModelMetricClaimedVerifiedStatus
1UNEM-GaussianAccuracy73.2Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean96.82Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean73.07Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean78.51Unverified
#ModelMetricClaimedVerifiedStatus
1UNEM-GaussianAccuracy52.3Unverified
#ModelMetricClaimedVerifiedStatus
1Variational Prompt TuningHarmonic mean79Unverified