rahul13ramesh / compositional_capabilitiesLinks
Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
☆10Updated 11 months ago
Alternatives and similar repositories for compositional_capabilities
Users that are interested in compositional_capabilities are comparing it to the libraries listed below
Sorting:
- 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
- Codebase for Mechanistic Mode Connectivity☆14Updated last year
- Transformers with doubly stochastic attention☆45Updated 2 years ago
- ☆19Updated 3 years ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated 2 years ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- Official code for the paper "Compositional Generalization from First Principles" (NeurIPS 2023)☆11Updated last year
- [NeurIPS'20] Code for the Paper Compositional Visual Generation and Inference with Energy Based Models☆45Updated 2 years ago
- ☆37Updated 3 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- Euclidean Wasserstein-2 optimal transportation☆47Updated last year
- ☆53Updated 8 months ago
- Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021☆27Updated 3 years ago
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆41Updated 2 years ago
- ☆18Updated 2 years ago
- Deep Networks Grok All the Time and Here is Why☆36Updated last year
- ☆53Updated 10 months ago
- [ICML'21] Improved Contrastive Divergence Training of Energy Based Models☆63Updated 3 years ago
- Simple Scalable Discrete Diffusion for text in PyTorch☆33Updated 8 months ago
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆40Updated last year
- ☆32Updated 8 months ago
- SGD with large step sizes learns sparse features [ICML 2023]☆32Updated 2 years ago
- ☆33Updated 2 years ago
- General Invertible Transformations for Flow-based Generative Models☆18Updated 4 years ago
- Code for minimum-entropy coupling.☆32Updated 11 months ago
- Experiments for Meta-Learning Symmetries by Reparameterization☆56Updated 4 years ago
- A minimal implementation of a VAE with BinConcrete (relaxed Bernoulli) latent distribution in TensorFlow.☆22Updated 5 years ago
- ☆26Updated 2 years ago
- ☆20Updated last year