No article text was recorded for this version.
architectural homogeneity constraint (heterogeneous model merging)
Version 1 of 1465 papers552 conceptsfrozen 2026-10-04
Papers in this version
- Blog: AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
- Blog: PSO-Merging: Merging Models Based on Particle Swarm Optimization
- Blog: Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?
- Blog: LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging
- Blog: On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural Networks
- Blog: Model Assembly Learning with Heterogeneous Layer Weight Merging
- Blog: Null-Space Filtering for Data-Free Continual Model Merging: Preserving Transparency, Promoting Fidelity
- Blog: Training-free Heterogeneous Model Merging
- Blog: OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition
- Blog: OTF: Optimal Transport based Fusion of Supervised and Self-Supervised Learning Models for Automatic Speech Recognition
- Blog: Extend Model Merging from Fine-Tuned to Pre-Trained Large Language Models via Weight Disentanglement
- Blog: MoCo: A One-Stop Shop for Model Collaboration Research
- Blog: Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
- Blog: SepRep-Net: Multi-source Free Domain Adaptation via Model Separation And Reparameterization
- Blog: Reinforced Model Merging
- Blog: A correlation-permutation approach for speech-music encoders model merging
- Blog: EMR-Merging: Tuning-Free High-Performance Model Merging
- Blog: From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches
- Blog: Null-Space Filtering for Data-Free Continual Model Merging: Preserving Stability, Promoting Plasticity
- Blog: Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models
- Blog: Effective and Parameter-Efficient Reusing Fine-Tuned Models
- Blog: Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks
- Blog: Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
- Blog: Cut the Deadwood Out: Post-Training Model Purification with Selective Module Substitution
- Blog: MINGLE: Mixtures of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
- Blog: DecompNet: Enhancing Time Series Forecasting Models with Implicit Decomposition
- Blog: Deep Fusion: Efficient Network Training via Pre-trained Initializations
- Blog: KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs
- Blog: Model Fusion via Optimal Transport
- Blog: PLeaS - Merging Models with Permutations and Least Squares
- Blog: An Edge-Cloud Collaboration Framework for Generative AI Service Provision with Synergetic Big Cloud Model and Small Edge Models
- Blog: MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs
- Blog: CNN LEGO: Disassembling and Assembling Convolutional Neural Network
- Blog: MC: Multi-concept Guidance for Customized Multi-concept Generation
- Blog: Unfolding and Shrinking Neural Machine Translation Ensembles
- Blog: Efficient Multi-Source Knowledge Transfer by Model Merging
- Blog: Deep Model Fusion: A Survey
- Blog: Out-of-Distribution Graph Models Merging
- Blog: How to Merge Your Multimodal Models Over Time?
- Blog: PLeaS - Merging Models with Permutations and Least Squares
- Blog: On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural Networks
- Blog: Deep Graph Mating
- Blog: MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
- Blog: Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge
- Blog: LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging
- Blog: Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation
- Blog: DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling
- Blog: It’s Morphing Time: Unleashing the Potential of Multiple LLMs via Multi-Objective Optimization
- Blog: Deep Model Fusion: A Survey
- Blog: MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection
- Blog: Activated Parameter Locating via Causal Intervention for Model Merging
- Blog: Efficient Multi-Task Modeling through Automated Fusion of Trained Models
- Blog: Transformer Fusion with Optimal Transport
- Blog: Model Fusion via Retrofitting
- Blog: HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models
- Blog: Efficient Multi-Task Modeling through Automated Fusion of Trained Models
- Blog: Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs
- Blog: Scalable Model Merging with Progressive Layer-wise Distillation
- Blog: Unfolding and Shrinking Neural Machine Translation Ensembles
- Blog: Merging Models with Fisher-Weighted Averaging
Showing 60 of 465 papers.
History & citation
Current · Permanent link
- Weight Fusion Across Heterogeneous Model Architectures merged into this direction (74% overlap)
- Weight Space Arithmetic for Merging Specialized Models merged into this direction (71% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_architectural_homogeneity_constraint_het_dbbaca26,
title = {architectural homogeneity constraint (heterogeneous model merging)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-homogeneity-constraint-heterogeneous-model-merging/rdr_dbbaca261465428897c4af5bf4ce52a3},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_architectural_homogeneity_constraint_het_dbbaca26_v1,
title = {architectural homogeneity constraint (heterogeneous model merging)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/architectural-homogeneity-constraint-heterogeneous-model-merging/rdr_dbbaca261465428897c4af5bf4ce52a3/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}