Imagen de Portada

Resolving Interference (RI): Disentangling Models for Improved Model Merging

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ramesh, Pratik, Stoica, George, Iyer, Arun, Choshen, Leshem, Hoffman, Judy
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Model merging with SVD to tie the Knots
por: Stoica, George, et al.
Publicado: (2024)

ZipIt! Merging Models from Different Tasks without Training
por: Stoica, George, et al.
Publicado: (2023)

Efficient Benchmarking of Language Models
por: Perlitz, Yotam, et al.
Publicado: (2023)

Parameter Competition Balancing for Model Merging
por: Du, Guodong, et al.
Publicado: (2024)

Towards Reversible Model Merging For Low-rank Weights
por: Alipour, Mohammadsajad, et al.
Publicado: (2025)

MAGIC: Achieving Superior Model Merging via Magnitude Calibration
por: Li, Yayuan, et al.
Publicado: (2025)

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
por: Yang, Enneng, et al.
Publicado: (2024)

When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
por: Li, Yayuan, et al.
Publicado: (2026)

Transferring Textual Preferences to Vision-Language Understanding through Model Merging
por: Li, Chen-An, et al.
Publicado: (2025)

Efficient Pruning of Text-to-Image Models: Insights from Pruning Stable Diffusion
por: Ramesh, Samarth N, et al.
Publicado: (2024)

ATM: Improving Model Merging by Alternating Tuning and Merging
por: Zhou, Luca, et al.
Publicado: (2024)

Exploring Model Kinship for Merging Large Language Models
por: Hu, Yedi, et al.
Publicado: (2024)

FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
por: Fan, Ziyang, et al.
Publicado: (2026)

ZJUKLAB at SemEval-2025 Task 4: Unlearning via Model Merging
por: Xu, Haoming, et al.
Publicado: (2025)

Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion
por: Zaman, Kerem, et al.
Publicado: (2023)

Stylus: Automatic Adapter Selection for Diffusion Models
por: Luo, Michael, et al.
Publicado: (2024)

Finding DoRI: Discovery of Retained Images in Diffusion Models
por: Kowalczuk, Antoni, et al.
Publicado: (2025)

Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models
por: Jun, Youngjun, et al.
Publicado: (2024)

Multi-Task Model Merging via Adaptive Weight Disentanglement
por: Xiong, Feng, et al.
Publicado: (2024)

DAM: Dynamic Adapter Merging for Continual Video QA Learning
por: Cheng, Feng, et al.
Publicado: (2024)

Coordinated Robustness Evaluation Framework for Vision-Language Models
por: Babu, Ashwin Ramesh, et al.
Publicado: (2025)

Improving Automatic VQA Evaluation Using Large Language Models
por: Mañas, Oscar, et al.
Publicado: (2023)

SpecPL: Disentangling Spectral Granularity for Prompt Learning
por: Zhou, Jingtao, et al.
Publicado: (2026)

Vision-Language Models Can Self-Improve Reasoning via Reflection
por: Cheng, Kanzhi, et al.
Publicado: (2024)

Improving Medical Large Vision-Language Models with Abnormal-Aware Feedback
por: Zhou, Yucheng, et al.
Publicado: (2025)

VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models
por: Jiang, Lingjie, et al.
Publicado: (2025)

LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
por: Shang, Yuzhang, et al.
Publicado: (2024)

SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
por: Li, Jialu, et al.
Publicado: (2024)

Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training
por: Wan, David, et al.
Publicado: (2024)

Analyzing domain shift when using additional data for the MICCAI KiTS23 Challenge
por: Stoica, George, et al.
Publicado: (2023)

Structured Captions Improve Prompt Adherence in Text-to-Image Models (Re-LAION-Caption 19M)
por: Merchant, Nicholas, et al.
Publicado: (2025)

From Consistency to Complementarity: Aligned and Disentangled Multi-modal Learning for Time Series Understanding and Reasoning
por: Ni, Hang, et al.
Publicado: (2026)

Subspace-Boosted Model Merging
por: Skorobogat, Ronald, et al.
Publicado: (2025)

A Hitchhiker's Guide to Scaling Law Estimation
por: Choshen, Leshem, et al.
Publicado: (2024)

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation
por: Qu, Leigang, et al.
Publicado: (2024)

Semantically-Prompted Language Models Improve Visual Descriptions
por: Ogezi, Michael, et al.
Publicado: (2023)

Mordal: Automated Pretrained Model Selection for Vision Language Models
por: He, Shiqi, et al.
Publicado: (2025)

Bridging the Gap Between Multimodal Foundation Models and World Models
por: He, Xuehai
Publicado: (2025)

Evolutionary Negative Module Pruning for Better LoRA Merging
por: Cao, Anda, et al.
Publicado: (2026)

Matryoshka Multimodal Models
por: Cai, Mu, et al.
Publicado: (2024)