Code for paper "Merging Multi-Task Models via Weight-Ensembling Mixture of Experts"
☆31Jun 7, 2024Updated last year
Alternatives and similar repositories for weight-ensembling_MoE
Users that are interested in weight-ensembling_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:
- Code for paper "Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion"☆14Mar 28, 2024Updated 2 years ago
- Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"☆25Sep 13, 2024Updated last year
- Official implementation of "Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent".☆22May 23, 2025Updated 10 months ago
- Codes for Merging Large Language Models☆35Aug 7, 2024Updated last year
- FusionBench: A Comprehensive Benchmark/Toolkit of Deep Model Fusion☆211Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆103Oct 28, 2024Updated last year
- ☆18Aug 19, 2024Updated last year
- ☆14May 4, 2024Updated last year
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆53Dec 22, 2025Updated 3 months ago
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆47Oct 10, 2024Updated last year
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆111Jun 8, 2023Updated 2 years ago
- [NeurIPS 2024] For paper Parameter Competition Balancing for Model Merging☆48Oct 11, 2024Updated last year
- [ICLR 2026] Official Implementation of ProxyThinker: Test-Time Guidance through Small Visual Reasoners.☆21Sep 24, 2025Updated 6 months ago
- Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.☆713Updated this week
- 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.
- The official repository of "Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors""☆49Oct 1, 2025Updated 6 months ago
- PyTorch implementation for "Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes" (ICML 2024).☆13Jul 21, 2024Updated last year
- Code for paper "Towards Efficient Pareto Set Approximation via Weight-Ensembling Mixture of Experts"☆11Sep 13, 2024Updated last year
- 🔥 🔥 [ECCV 2024 Oral ] Official code for "Weighted Ensemble Models Are Strong Continual Learners"☆30Apr 16, 2025Updated last year
- ☆13Jun 29, 2024Updated last year
- Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision☆11Jul 22, 2024Updated last year
- ☆15Sep 4, 2025Updated 7 months ago
- Reasoning Activation in LLMs via Small Model Transfer (NeurIPS 2025)☆22Oct 16, 2025Updated 6 months ago
- Code for Research Project TLDR☆25Jul 28, 2025Updated 8 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Code Repository for the NeurIPS 2024 Paper "Toward Efficient Inference for Mixture of Experts".☆19Oct 30, 2024Updated last year
- Task Singular Vectors: Reducing Task Interference in Model Merging. Merge models avoiding task interference through separable models.☆54Dec 15, 2025Updated 4 months ago
- ☆81Mar 17, 2022Updated 4 years ago
- [ICLR 2024 Oral] Improving Convergence and Generalization Using Parameter Symmetries☆31May 29, 2024Updated last year
- ☆10Sep 19, 2021Updated 4 years ago
- This is the open-source code for TokenCarve.☆26Jan 23, 2026Updated 2 months ago
- Official repository for Activation-Informed Merging (AIM) of Large Language Models☆22Feb 10, 2025Updated last year
- Package to align tokens from different tokenizations.☆16Mar 25, 2024Updated 2 years ago
- Official repository for MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models [NeurIPS 2024]☆79Nov 14, 2024Updated last year
- 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.
- Official code for "Rethinking Chain-of-Thought Reasoning for Videos"☆20Dec 14, 2025Updated 4 months ago
- [NeurIPS 24] MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks☆135Nov 23, 2024Updated last year
- [ICLR 2025] Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization☆24Oct 5, 2025Updated 6 months ago
- [NeurIPS 2025@FoRLM] R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search☆17Jan 24, 2026Updated 2 months ago
- [CVPR 2026] FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection☆31Feb 10, 2026Updated 2 months ago
- Clustered Federated Learning via Gradient-based Partitioning (ICML 2024)☆15Jun 15, 2025Updated 10 months ago
- Prioritized Generative Replay (ICLR 2025 Oral)☆28Mar 1, 2025Updated last year