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
☆29Updated last year
Related projects ⓘ
Alternatives and complementary repositories for zeroc
- [NeurIPS'20] Code for the Paper Compositional Visual Generation and Inference with Energy Based Models☆43Updated 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
- This repository holds the code for the NeurIPS 2022 paper, Semantic Probabilistic Layers☆26Updated 11 months ago
- A Scalable Approximate Method for Probabilistic Neurosymbolic Inference☆14Updated last year
- Distilling Model Failures as Directions in Latent Space☆45Updated last year
- ☆24Updated 3 years ago
- Official Release of NeurIPS 2020 Spotlight paper "Generative Neurosymbolic Machines"☆35Updated 8 months ago
- Logic Explained Networks is a python repository implementing explainable-by-design deep learning models.☆45Updated last year
- ☆34Updated 3 years ago
- ☆25Updated 4 months ago
- Code for "Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?" [ICML 2023]☆31Updated 2 months ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆57Updated last year
- Code for Neural Execution Engines: Learning to Execute Subroutines☆16Updated 3 years ago
- Codebase for Neuro-Symbolic Continual Learning.☆19Updated last year
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆94Updated 11 months ago
- Code for LaMPP: Language Models as Probabilistic Priors for Perception and Action☆35Updated last year
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆42Updated last year
- Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)☆47Updated last year
- [ICLR2024] (EvALign-ICL Benchmark) Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context …☆20Updated 8 months ago
- ModelDiff: A Framework for Comparing Learning Algorithms☆52Updated last year
- An adaptive training algorithm for residual network☆14Updated 4 years ago
- ☆18Updated last year
- A centralized place for deep thinking code and experiments☆76Updated last year
- ☆13Updated 11 months ago
- ☆21Updated 2 years ago
- ☆28Updated last year
- ☆41Updated last year
- Updated code base for GlanceNets: Interpretable, Leak-proof Concept-based models☆25Updated last year
- Code for paper "Can contrastive learning avoid shortcut solutions?" NeurIPS 2021.☆47Updated 2 years ago