Awni00 / abstractor
This is the code repository associated with the paper "Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers"
☆13Updated 3 weeks ago
Related projects: ⓘ
- The Energy Transformer block, in JAX☆48Updated 9 months ago
- [NeurIPS'20] Code for the Paper Compositional Visual Generation and Inference with Energy Based Models☆43Updated last year
- ☆14Updated 3 years ago
- ☆12Updated 9 months ago
- Transformers with doubly stochastic attention☆40Updated 2 years ago
- ☆21Updated last year
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆38Updated 7 months ago
- ☆13Updated last year
- Repo reproducing experimental results in "Addressing the Topological Defects of Disentanglement"☆23Updated 2 years ago
- ☆25Updated last year
- ☆31Updated 3 years ago
- [NeurIPS 2021] Code for Unsupervised Learning of Compositional Energy Concepts☆56Updated 2 years ago
- Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021☆25Updated 2 years ago
- Code associated with our paper "Learning Group Structure and Disentangled Representations of Dynamical Environments"☆14Updated last year
- ☆33Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆57Updated 10 months ago
- Information-Theoretic Diffusion: A brand new diffusion model / density estimator based on information theory.☆29Updated 2 months ago
- On efficient computation in active inference☆17Updated 3 months ago
- [ICML'21] Improved Contrastive Divergence Training of Energy Based Models☆60Updated 2 years ago
- Official repository of Implicit Neural Convolutional Kernels for Steerable CNNs, Zhdanov et al.☆23Updated 6 months ago
- ☆21Updated 2 years ago
- Code for "Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations"☆23Updated last year
- Why Do We Need Weight Decay in Modern Deep Learning? [arXiv, Oct 2023]☆41Updated 11 months ago
- Official source code for "Graph Neural Networks for Learning Equivariant Representations of Neural Networks". In ICLR 2024 (oral).☆63Updated last month
- Neural Optimal Transport with Lagrangian Costs☆37Updated 2 months ago
- Official code for On Path Integration of Grid Cells: Group Representation and Isotropic Scaling (NeurIPS 2021)☆46Updated 2 years ago
- [ICML 2024] SINGD: KFAC-like Structured Inverse-Free Natural Gradient Descent (http://arxiv.org/abs/2312.05705)☆19Updated 2 months ago
- ☆17Updated 2 years ago
- Euclidean Wasserstein-2 optimal transportation☆43Updated last year
- ☆17Updated last year