aryol / inductive-scratchpad
Implementation for our paper "How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad"
☆12Updated 10 months ago
Alternatives and similar repositories for inductive-scratchpad:
Users that are interested in inductive-scratchpad are comparing it to the libraries listed below
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆40Updated last year
- ☆9Updated 2 years ago
- Code for testing DCT plus Sparse (DCTpS) networks☆14Updated 3 years ago
- Transformers with doubly stochastic attention☆45Updated 2 years ago
- Code for "SAM as an Optimal Relaxation of Bayes", ICLR 2023.☆25Updated last year
- ☆11Updated 2 years ago
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated last year
- ☆22Updated 2 years ago
- Code for Accelerated Linearized Laplace Approximation for Bayesian Deep Learning (ELLA, NeurIPS 22')☆16Updated 2 years ago
- Latest Weight Averaging (NeurIPS HITY 2022)☆30Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithms☆56Updated last year
- Code for "Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations"☆23Updated 2 years ago
- A modern look at the relationship between sharpness and generalization [ICML 2023]☆43Updated last year
- Deep Learning & Information Bottleneck☆60Updated last year
- ☆52Updated 7 months ago
- Towards Understanding Sharpness-Aware Minimization [ICML 2022]☆35Updated 2 years ago
- Code for paper "Compositional Sculpting of Iterative Generative Processes"☆21Updated last year
- Laplace Redux -- Effortless Bayesian Deep Learning☆43Updated 2 years ago
- ☆13Updated 2 years ago
- ☆67Updated 4 months ago
- Implementation of the models and datasets used in "An Information-theoretic Approach to Distribution Shifts"☆25Updated 3 years ago
- Official source code for "Graph Neural Networks for Learning Equivariant Representations of Neural Networks". In ICLR 2024 (oral).☆79Updated 9 months ago
- Pytorch code for "Improving Self-Supervised Learning by Characterizing Idealized Representations"☆41Updated 2 years ago
- Source code of "What can linearized neural networks actually say about generalization?☆20Updated 3 years ago
- Euclidean Wasserstein-2 optimal transportation☆47Updated last year
- NeurIPS 2022: Tree Mover’s Distance: Bridging Graph Metrics and Stability of Graph Neural Networks☆36Updated last year
- Code for the paper "Data Feedback Loops: Model-driven Amplification of Dataset Biases"☆16Updated 2 years ago
- Official implementation of ORCA proposed in the paper "Cross-Modal Fine-Tuning: Align then Refine"☆71Updated last year
- Deep Networks Grok All the Time and Here is Why☆34Updated 11 months ago
- [NeurIPS'20] Code for the Paper Compositional Visual Generation and Inference with Energy Based Models☆44Updated 2 years ago