few-shot learning
An approach in machine learning where the model learns to generalize from a very limited number of training examples, often through prior knowledge.
- Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees
- CLEVER: A Curated Benchmark for Formally Verified Code Generation
- Can LLMs Reason Over Non-Text Modalities in a Training-Free Manner? A Case Study with In-Context Representation Learning
- DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning
- Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning
- Disentangling Latent Shifts of In-Context Learning with Weak Supervision
- Do different prompting methods yield a common task representation in language models?
- Dual Alignment Framework for Few-shot Learning with Inter-Set and Intra-Set Shifts
- Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanations
- Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency
- LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits
- LLM Meeting Decision Trees on Tabular Data
- MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?
- MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning
- MolVision: Molecular Property Prediction with Vision Language Models
- Preference-driven Knowledge Distillation for Few-shot Node Classification
- Prompt Tuning Decision Transformers with Structured and Scalable Bandits
- Promptable 3-D Object Localization with Latent Diffusion Models
- Prompting as Scientific Inquiry
- QCircuitBench: A Large-Scale Dataset for Benchmarking Quantum Algorithm Design
- Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
- Self-supervised Blending Structural Context of Visual Molecules for Robust Drug Interaction Prediction
- SensorLM: Learning the Language of Wearable Sensors
- Separating the 'what' and 'how' of compositional computation to enable reuse and continual learning
- Storyboard-guided Alignment for Fine-grained Video Action Recognition
- Support Vector Generation: Kernelizing Large Language Models for Efficient Zero‑Shot NLP
- VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning
- VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models
- Variational Supervised Contrastive Learning
- Weak-shot Keypoint Estimation via Keyness and Correspondence Transfer
- Words That Unite The World: A Unified Framework for Deciphering Central Bank Communications