zero-shot learning
An approach in machine learning where a model is able to make predictions on classes it has never seen during training, leveraging knowledge transfer and semantic understanding.
- CHASM: Unveiling Covert Advertisements on Chinese Social Media
- ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibiltiy Data
- Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs
- EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
- Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion Games
- Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models
- Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization
- FlySearch: Exploring how vision-language models explore
- Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems
- MolVision: Molecular Property Prediction with Vision Language Models
- Native Segmentation Vision Transformers
- OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation
- PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors
- Preference-driven Knowledge Distillation for Few-shot Node Classification
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos
- SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding
- Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
- Storyboard-guided Alignment for Fine-grained Video Action Recognition
- Support Vector Generation: Kernelizing Large Language Models for Efficient Zero‑Shot NLP
- Taming generative video models for zero-shot optical flow extraction
- Training-free Online Video Step Grounding
- Universal Video Temporal Grounding with Generative Multi-modal Large Language Models
- VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models
- Vision Transformers with Self-Distilled Registers
- Words That Unite The World: A Unified Framework for Deciphering Central Bank Communications
- ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding
- ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data
- scGeneScope: A Treatment-Matched Single Cell Imaging and Transcriptomics Dataset and Benchmark for Treatment Response Modeling