snap-stanford / zeroc
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
☆30Updated last year
Alternatives and similar repositories for zeroc:
Users that are interested in zeroc are comparing it to the libraries listed below
- Code for Neural Execution Engines: Learning to Execute Subroutines☆17Updated 4 years ago
- Updated code base for GlanceNets: Interpretable, Leak-proof Concept-based models☆25Updated last year
- [NeurIPS'20] Code for the Paper Compositional Visual Generation and Inference with Energy Based Models☆44Updated last year
- The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We…☆46Updated last year
- Code for the ICLR 2020 Paper, "A Theory of Usable Information under Computational Constraints"☆24Updated 4 years ago
- ☆28Updated last year
- ☆33Updated 3 months ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- Google Research☆46Updated 2 years ago
- ModelDiff: A Framework for Comparing Learning Algorithms☆56Updated last year
- [ICML'21] Improved Contrastive Divergence Training of Energy Based Models☆62Updated 2 years ago
- ☆12Updated last year
- A Scalable Approximate Method for Probabilistic Neurosymbolic Inference☆14Updated last month
- Official code for the paper "Compositional Generalization from First Principles" (NeurIPS 2023)☆10Updated last year
- ☆9Updated 2 years ago
- Distilling Model Failures as Directions in Latent Space☆46Updated 2 years ago
- ☆38Updated 3 years ago
- Deep Learning & Information Bottleneck☆58Updated last year
- ☆34Updated 4 years ago
- Sparse Autoencoder Training Library☆43Updated 4 months ago
- [NeurIPS 2021] Code for Unsupervised Learning of Compositional Energy Concepts☆59Updated 2 years ago
- ☆24Updated 2 years ago
- Universal Neurons in GPT2 Language Models☆27Updated 9 months ago
- ☆33Updated 11 months ago
- ☆27Updated last year
- This repository holds the code for the NeurIPS 2022 paper, Semantic Probabilistic Layers☆27Updated last year
- Codebase for the paper: Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts☆19Updated last year
- ☆11Updated 2 years ago
- ☆17Updated 2 years ago