Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch
-
Updated
Jun 17, 2024 - Python
#
conditional-computation
Here are 13 public repositories matching this topic...
[NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
-
Updated
Nov 23, 2024 - Python
Code for Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference (CVPR2020)
deep-learning pytorch neural-networks conditional-computation dynamic-convolutions conditional-execution dynamic-execution
-
Updated
Jan 17, 2022 - Cuda
Mixture of Experts from scratch
python nlp machine-learning tutorial simple routing jupyter-notebook pytorch artificial-intelligence easy gating from-scratch small-dataset hands-on mixture-of-experts conditional-computation
-
Updated
Apr 12, 2024 - Jupyter Notebook
Google DeepMind: Mixture of Depths Unofficial Implementation.
-
Updated
May 29, 2024 - Python
Topological Manifold Control: A multi-paradigm (PyTorch/JAX) geometric morphing engine utilizing differentiable soft-gating, optimized via XLA fused kernels and autograd-isolated non-blocking pipelines.
pytorch autograd differential-geometry jit-compiler manifold-learning loss-functions mathematical-physics hypernetworks geometric-deep-learning pure-functional jax xla information-geometry conditional-computation cognitive-sciences optax stateless-architecture theoretical-ai alignment-system
-
Updated
Sep 1, 2026 - Python
通过基于“滞后梯度博弈”的内生演化压力，替代传统 MoE 的外在负载均衡约束，实现神经网络拓扑结构的自组织特化与层级化
pytorch deeplearning interpretability multi-task-learning mixture-of-experts conditional-computation disentanglement-learning gradient-conflict
-
Updated
Jan 12, 2026 - Python
Curated papers on dynamic neural networks, pruning, growing architectures, sparse training, and adaptive computation.
deep-learning pruning adaptive-computation conditional-computation dynamic-neural-network topology-adaptation dynamic-architectures
-
Updated
Jun 6, 2026
SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization
deep-learning routing language-modeling pytorch moe lora modular-networks mixture-of-experts conditional-computation vision-transformer
-
Updated
Aug 17, 2026 - Python
Official implementation of UniF-MoE: a unified framework for token-adaptive MoE computation
natural-language-processing computer-vision pytorch dynamic-routing mixture-of-experts domain-generalization conditional-computation token-adaptive-computation
-
Updated
Aug 12, 2026 - Python
Research code for testing whether causal token surprisal can guide adaptive computation, sparse refinement, and learned compute allocation in byte-level language models.
-
Updated
Aug 1, 2026 - Python
Research pilot (dormant): can attention-residual signal learn per-input depth routing?
-
Updated
May 29, 2026 - Python
A biologically inspired R&D blueprint for sparse, grounded, continual, energy-efficient AI.
neuroscience artificial-intelligence open-science biomimetics causal-inference model-compression continual-learning active-sensing world-models sensorimotor-learning adaptive-computation conditional-computation embodied-ai memory-consolidation sparse-computation predictive-processing eu-ai-act energy-efficient-ai biologically-inspired-ai modular-neural-networks
-
Updated
Sep 4, 2026 - JavaScript
Add this topic to your repo
To associate your repository with the conditional-computation topic, visit your repo's landing page and select "manage topics."