Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time
Tailin Wu, Megan Tjandrasuwita, Zhengxuan Wu, Xuelin Yang, Kevin Liu, Rok Sosic, Jure Leskovec
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add R-EBM relation term to composition (ablation) | ZeroC · HD-Letter | classification accuracy: 62.5 -> 84.5 | Improved |
| add R-EBM relation term to composition (ablation) | ZeroC · HD-Concept | classification accuracy: 32.5 -> 70.5 | Improved |
| add R-EBM relation term to composition (ablation) | ZeroC · HD-Letter+distractor | detection IoU: 45.3 -> 72.5 | Improved |
| add HC-EBM concept term to composition (ablation) | ZeroC · HD-Letter | classification accuracy: 67.0 -> 84.5 | Improved |
| add HC-EBM concept term to composition (ablation) | ZeroC · HD-Concept+distractor | detection IoU: 78.4 -> 84.7 | Improved |
| add L(pos-std) loss term (ablation) | ZeroC · HD-Letter | classification accuracy: 43.6 -> 84.5 | Improved |
| add L(pos-std) loss term (ablation) | ZeroC · HD-Letter+distractor | detection IoU: 76.1 -> 72.5 | Hurt |
| add L(neg) loss term (ablation) | ZeroC · HD-Letter | classification accuracy: 64.5 -> 84.5 | Improved |
| add L(neg) loss term (ablation) | ZeroC · HD-Letter+distractor | detection IoU: 60.0 -> 72.5 | Improved |
| add L(em) loss term (ablation) | ZeroC · HD-Letter | classification accuracy: 81.5 -> 84.5 | Mixed |
| use full objective instead of only L(Improved) (ablation) | ZeroC · HD-Letter | classification accuracy: 27.5 -> 84.5 | Improved |
| add L(pos-std) loss term (ablation) | ZeroC1 -> ZeroC2 · Domain 1 2D parsing | graph isomorphism accuracy: 55.2 -> 72.7 | Improved |
Closest papers by meaning
- SimZSL: Zero-Shot Learning Beyond a Pre-defined Semantic Embedding Space (IJCV 2025 · similarity 0.88)
- Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition (CVPR 2026 · similarity 0.87)
- Concept-RuleNet: Grounded Multi-Agent Neurosymbolic Reasoning in Vision Language Models (AAAI 2026 · similarity 0.87)
- Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization (ICML 2025 · similarity 0.86)
- ZeroMamba: Exploring Visual State Space Model for Zero-Shot Learning (AAAI 2025 · similarity 0.86)
- TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
