[NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
☆134Nov 23, 2024Updated last year
Alternatives and similar repositories for MoE-Jetpack
Users that are interested in MoE-Jetpack are comparing it to the libraries listed below
Sorting:
- Official code repository of Shuffle-R1☆25Feb 23, 2026Updated last week
- [ECCV 2024] Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression☆50Sep 21, 2024Updated last year
- the official code of DriveMonkey☆43May 24, 2025Updated 9 months ago
- [NAACL'25 🏆 SAC Award] Official code for "Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert…☆15Feb 4, 2025Updated last year
- [ICRA 2026] UniFuture: A 4D Driving World Model for Future Generation and Perception☆138Updated this week
- ☆30Sep 28, 2023Updated 2 years ago
- [NeurIPS 2024] A Unified Framework for 3D Scene Understanding☆172Jul 7, 2025Updated 7 months ago
- The code for "MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Tracking"☆19Jan 25, 2025Updated last year
- [NAACL 2025] Representing Rule-based Chatbots with Transformers☆23Feb 9, 2025Updated last year
- [ICML 2025] This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality…☆53Mar 25, 2025Updated 11 months ago
- Awesome GPT-4 with Applications. This is a collection of resources related to GPT-4, including news, official documents, demo and applica…☆20Mar 15, 2023Updated 2 years ago
- Official code repository of Shuffle-R1☆35Feb 23, 2026Updated last week
- [ICCV 2025] HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation☆234Jul 14, 2025Updated 7 months ago
- [ECCV 2024] This is the official implementation of "Stitched ViTs are Flexible Vision Backbones".☆29Jan 23, 2024Updated 2 years ago
- Code release for Dilated-Scale-Aware Category-Attention ConvNet for Multi-Class Object Counting☆23Mar 15, 2023Updated 2 years ago
- ☆12Mar 5, 2025Updated 11 months ago
- [ICLR 2026] Official Implementation of ProxyThinker: Test-Time Guidance through Small Visual Reasoners.☆20Sep 24, 2025Updated 5 months ago
- Code for paper: "Executing Arithmetic: Fine-Tuning Large Language Models as Turing Machines"☆11Oct 11, 2024Updated last year
- A much powerful probing method to tune your model with promising performance and linear probing training cost!☆15Jul 26, 2023Updated 2 years ago
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆139Jun 12, 2024Updated last year
- The official implementation of "2024NeurIPS Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation"☆53Dec 30, 2024Updated last year
- [ICLR 2025] Adaptive prompt tailored pruning of T2I diffusion models.☆15Feb 1, 2025Updated last year
- The implementation for FREE-Merging: Fourier Transform for Model Merging with Lightweight Experts (ICCV25)☆14Jun 26, 2025Updated 8 months ago
- ☆12Jul 18, 2024Updated last year
- ☆34Jan 25, 2026Updated last month
- Code Repository for the NeurIPS 2024 Paper "Toward Efficient Inference for Mixture of Experts".☆19Oct 30, 2024Updated last year
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆88Feb 18, 2026Updated last week
- User-friendly implementation of the Mixture-of-Sparse-Attention (MoSA). MoSA selects distinct tokens for each head with expert choice rou…☆28May 3, 2025Updated 9 months ago
- Code for paper "Merging Multi-Task Models via Weight-Ensembling Mixture of Experts"☆30Jun 7, 2024Updated last year
- [ACMMM 2025] Officially implement of the paper "DriVerse: Navigation World Model for Driving Simulation via Multimodal Trajectory Prompti…☆218May 7, 2025Updated 9 months ago
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆91Dec 3, 2024Updated last year
- [ICLR 2025] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts☆265Oct 16, 2024Updated last year
- Codebase for Instruction Following without Instruction Tuning☆36Sep 24, 2024Updated last year
- ☆15Oct 19, 2024Updated last year
- ☆42Sep 15, 2025Updated 5 months ago
- Codes for DATA: Differentiable ArchiTecture Approximation.☆11Jul 22, 2021Updated 4 years ago
- [ICLR 2025] Weighted-Reward Preference Optimization for Implicit Model Fusion☆14Mar 17, 2025Updated 11 months ago
- [ICCV 23] A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection☆12Apr 12, 2024Updated last year
- StreamPETR with 3dppe Extension☆51Jan 16, 2024Updated 2 years ago