snap-stanford / zerocLinks
ZeroC is a neuro-symbolic method that trained with elementary visual concepts and relations, can zero-shot recognize and acquire more complex, hierarchical concepts, even across domains
☆32Updated 2 years ago
Alternatives and similar repositories for zeroc
Users that are interested in zeroc are comparing it to the libraries listed below
Sorting:
- The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We…☆46Updated last year
- Code for Neural Execution Engines: Learning to Execute Subroutines☆17Updated 4 years ago
- ☆37Updated 11 months ago
- Code for the ICLR 2020 Paper, "A Theory of Usable Information under Computational Constraints"☆26Updated 4 years ago
- [NeurIPS'20] Code for the Paper Compositional Visual Generation and Inference with Energy Based Models☆45Updated 2 years ago
- ☆34Updated 6 months ago
- ☆29Updated 2 years ago
- Updated code base for GlanceNets: Interpretable, Leak-proof Concept-based models☆25Updated 2 years ago
- Distilling Model Failures as Directions in Latent Space☆47Updated 2 years ago
- ☆9Updated 2 years ago
- Google Research☆46Updated 2 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- Neural Logic Inductive Learning☆44Updated 2 years ago
- Code for LaMPP: Language Models as Probabilistic Priors for Perception and Action☆37Updated 2 years ago
- Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?" [ICML 2023]☆35Updated 10 months ago
- Official code for the paper "Compositional Generalization from First Principles" (NeurIPS 2023)☆11Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithms☆57Updated last year
- How to Turn Your Knowledge Graph Embeddings into Generative Models☆51Updated 11 months ago
- ☆24Updated 4 years ago
- A Scalable Approximate Method for Probabilistic Neurosymbolic Inference☆15Updated 5 months ago
- A centralized place for deep thinking code and experiments☆84Updated last year
- [NeurIPS 2021] Code for Unsupervised Learning of Compositional Energy Concepts☆62Updated 2 years ago
- Official source code for "Graph Neural Networks for Learning Equivariant Representations of Neural Networks". In ICLR 2024 (oral).☆81Updated 11 months ago
- Code repository for "The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks"☆17Updated last year
- ☆26Updated 2 years ago
- Official Release of NeurIPS 2020 Spotlight paper "Generative Neurosymbolic Machines"☆35Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆37Updated 2 years ago
- ☆34Updated last year
- ☆10Updated 4 years ago
- ☆11Updated 2 years ago