PyTorch implementation of "From Sparse to Soft Mixtures of Experts"
☆72Aug 22, 2023Updated 3 years ago
Alternatives and similar repositories for soft-moe
Users that are interested in soft-moe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)☆83Oct 5, 2023Updated 3 years ago
- Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch☆349Apr 2, 2025Updated last year
- ☆20Nov 5, 2024Updated 2 years ago
- ☆728Oct 28, 2026Updated last week
- The official repository for the experiments included in the paper titled "Patch-level Routing in Mixture-of-Experts is Provably Sample-ef…☆15Feb 12, 2026Updated 8 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆12Aug 19, 2025Updated last year
- arXiv 2024 | ZIP: entropy-law data selection for efficient LLM alignment.☆28Jun 10, 2026Updated 4 months ago
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆390Jun 17, 2024Updated 2 years ago
- The official implementation of ICLR 2025 paper "Polynomial Composition Activations: Unleashing the Dynamics of Large Language Models".☆18Apr 25, 2025Updated last year
- ☆15Oct 12, 2026Updated 3 weeks ago
- Official implementation of "MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning"☆11Aug 23, 2025Updated last year
- GoldFinch and other hybrid transformer components☆47Jul 20, 2024Updated 2 years ago
- 🏥Generate task cohort for the YAIB framework.☆15Nov 19, 2025Updated 11 months ago
- [CVPR 2024] LoSh: Long-Short Text Joint Prediction Network for Referring Video Object Segmentation☆13Jun 17, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ECCV 2022] AMixer: Adaptive Weight Mixing for Self-attention Free Vision Transformers☆29Nov 14, 2022Updated 3 years ago
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆165Jul 9, 2025Updated last year
- Code for the paper "Interpreting and Improving Diffusion Models from an Optimization Perspective", appearing in ICML 2024☆15Sep 30, 2024Updated 2 years ago
- PELA: Learning Parameter-Efficient Models with Low-Rank Approximation [CVPR 2024]☆19Apr 14, 2024Updated 2 years ago
- Learning generative models with Sinkhorn Loss☆32Nov 9, 2018Updated 7 years ago
- ☆20Jun 3, 2026Updated 5 months ago
- An unofficial implementation for paper "DenseCLIP: Extract Free Dense Labels from CLIP"☆24Jan 27, 2022Updated 4 years ago
- ☆17Jun 20, 2024Updated 2 years ago
- ☆53Jan 28, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Kolmogorov-Arnold Attention: Is Learnable Attention Better for Vision Transformers?☆17Jul 9, 2025Updated last year
- [CVPR 2024] Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior☆10Oct 5, 2026Updated last month
- Source code for paper "VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution"☆10Nov 1, 2022Updated 4 years ago
- NeuralDMD for Imaging from Sparse Observations☆12Jul 9, 2025Updated last year
- [ICLR'25] Code for KaSA, an official implementation of "KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models"☆22Jan 16, 2025Updated last year
- ☆11Sep 2, 2026Updated 2 months ago
- Using image captions with LLM for zero-shot VQA☆19Mar 14, 2024Updated 2 years ago
- ☆39Jul 30, 2024Updated 2 years ago
- Saliency Prediction on Omnidirectional Image with Generative Adversarial Imitation Learning (TIP 2021)☆10Sep 17, 2023Updated 3 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Based on https://github.com/Project-MONAI/research-contributions/tree/main/SwinUNETR/Pretrain☆10Apr 24, 2023Updated 3 years ago
- Building language models to predict more than one token ahead to enable further ahead predictions.☆12May 22, 2025Updated last year
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆56Feb 28, 2023Updated 3 years ago
- Related papers about Referring Image Segmentation (RIS)☆16Dec 26, 2023Updated 2 years ago
- ☆11May 17, 2024Updated 2 years ago
- [MICCAI 2024] Swin SMT: Global Sequential Modeling for Enhancing 3D Medical Image Segmentation☆29Oct 10, 2024Updated 2 years ago
- Clinical risk prediction based on machine learning algorithms plays a vital role in modern healthcare. A crucial component in developing …☆13Jul 27, 2026Updated 3 months ago