[ICML 2025] No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces (official repository)
☆47Aug 7, 2025Updated last year
Alternatives and similar repositories for iso-merging
Users that are interested in iso-merging 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 code for NeurIPS 2025 paper "Accurate and Efficient Low-Rank Model Merging in Core Space"☆42Feb 2, 2026Updated 8 months ago
- Task Singular Vectors: Reducing Task Interference in Model Merging. Merge models avoiding task interference through separable models.☆59Dec 15, 2025Updated 10 months ago
- official code repo for paper "Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging"☆26Oct 11, 2025Updated last year
- FusionBench: A Comprehensive Benchmark/Toolkit of Deep Model Fusion☆243Aug 5, 2026Updated 2 months ago
- [ICLR 2026] - Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery☆23Mar 18, 2026Updated 6 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- The Land-Diffuser is a novel application of the Denoising Diffusion Probabilistic Model (DDPM) in the realm of 3D Talking Head generation…☆13Dec 23, 2023Updated 2 years ago
- Official repository for Activation-Informed Merging (AIM) of Large Language Models☆25Feb 10, 2025Updated last year
- The official repository of "Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors""☆50Oct 1, 2025Updated last year
- [ICLR 2024, IJCV 2026] - Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learning☆36Sep 29, 2026Updated 2 weeks ago
- Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.☆794Updated this week
- Model Merging with SVD to Tie the KnOTS [ICLR 2025]☆98Apr 3, 2025Updated last year
- [COG24] - Official repository of "OfflineMania: A Benchmark Environment for Offline Reinforcement Learning in Racing Games"☆12Jul 15, 2024Updated 2 years ago
- Model merging, task-vector rebasin, and fine-tuning for vision and LLM models.☆36Updated this week
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆82Mar 1, 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.
- Official implementation of "On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning"☆14Oct 13, 2022Updated 4 years ago
- [ECCV 2024] MagMax: Leveraging Model Merging for Seamless Continual Learning (official repository)☆32Jul 29, 2024Updated 2 years ago
- [ICLR 2026 Oral] Invisible Safety Threat: Malicious Finetuning for LLM via Steganography☆22Mar 22, 2026Updated 6 months ago
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆115Jun 8, 2023Updated 3 years ago
- ☆22Apr 3, 2026Updated 6 months ago
- Vico: Compositional Video Generation as Flow Equalization☆59Nov 15, 2024Updated last year
- [CVPR 2026] Official Implementation of DC-Merge: Improving Model Merging with Directional Consistency☆20Apr 29, 2026Updated 5 months ago
- Code and benchmark for the paper: "A Practitioner's Guide to Continual Multimodal Pretraining" [NeurIPS'24]☆62Dec 10, 2024Updated last year
- Implementation of <Orthogonal Model Merging>☆37Aug 5, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [CCS-LAMPS'24] LLM IP Protection Against Model Merging☆16Oct 14, 2024Updated 2 years ago
- ☆33Jul 8, 2024Updated 2 years ago
- ☆13Oct 2, 2023Updated 3 years ago
- [ECCV 2026] Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models☆28Jun 20, 2026Updated 3 months ago
- Editing Models with Task Arithmetic☆554Jan 11, 2024Updated 2 years ago
- 🔥 🔥 [ECCV 2024 Oral ] Official code for "Weighted Ensemble Models Are Strong Continual Learners"☆30Apr 16, 2025Updated last year
- [ICML 2023] "Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?" by Ruisi Cai, Zhenyu Zhang, Zhangyang Wang☆16May 4, 2023Updated 3 years ago
- [ICML 2024] Code release for "On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm"☆11Feb 20, 2025Updated last year
- Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation☆14Jan 2, 2026Updated 9 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ICLR2024 paper on Continual Learning☆37Apr 21, 2024Updated 2 years ago
- PyTorch implementation of paper "StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization" in ICML 2024.☆16Jun 4, 2024Updated 2 years ago
- ☆224Feb 3, 2024Updated 2 years ago
- Official code for ICLR 2026 Oral paper, "Taming Momentum: Rethinking Optimizer States Through Low-Rank Approximation"☆37Feb 26, 2026Updated 7 months ago
- Learnable drift compensation (LDC) reduces semantic drift in continual learning using a trainable projector to map between tasks.☆19Nov 13, 2024Updated last year
- ☆15Apr 3, 2026Updated 6 months ago
- [Preprint arXiv: 2506.18810 ] ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation☆27Oct 1, 2025Updated last year