data scarcity
This term describes a situation where there is a limited amount of labelled data available for training machine learning models. Data scarcity can significantly hinder model performance and generalization, as models often require substantial amounts of data to learn effectively.
- A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
- Diffusion Beats Autoregressive in Data-Constrained Settings
- Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL
- From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries
- GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
- Navigating the MIL Trade-Off: Flexible Pooling for Whole Slide Image Classification
- Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring
- PANGEA: Projection-Based Augmentation with Non-Relevant General Data for Enhanced Domain Adaptation in LLMs
- Principled Model Routing for Unknown Mixtures of Source Domains
- Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
- RiboFlow: Conditional De Novo RNA Co-Design via Synergistic Flow Matching
- RoboScape: Physics-informed Embodied World Model
- STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization
- Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation
- ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On
- Spatial Understanding from Videos: Structured Prompts Meet Simulation Data
- Synthetic Series-Symbol Data Generation for Time Series Foundation Models
- Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis