Cover Image

PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Shao, Zibo, Xiong, Baochen, Yang, Xiaoshan, Song, Yaguang, Zhang, Qimeng, Chen, Haifeng, Xu, Changsheng
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Pilot: Building the Federated Multimodal Instruction Tuning Framework
by: Xiong, Baochen, et al.
Published: (2025)

Libra: Building Decoupled Vision System on Large Language Models
by: Xu, Yifan, et al.
Published: (2024)

A Step Toward Federated Pretraining of Multimodal Large Language Models
by: Xiong, Baochen, et al.
Published: (2026)

Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration
by: Fang, Haipeng, et al.
Published: (2025)

Towards Domain-Generalized Open-Vocabulary Object Detection: A Progressive Domain-invariant Cross-modal Alignment Method
by: Xu, Xiaoran, et al.
Published: (2026)

HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding
by: Xiao, Linhui, et al.
Published: (2024)

SSAM: Singular Subspace Alignment for Merging Multimodal Large Language Models
by: Reza, Md Kaykobad, et al.
Published: (2026)

Training-Free Pretrained Model Merging
by: Xu, Zhengqi, et al.
Published: (2024)

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
by: Wang, Ke, et al.
Published: (2024)

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
by: Zhang, Luyuan, et al.
Published: (2026)

Progressive Local Alignment for Medical Multimodal Pre-training
by: Yan, Huimin, et al.
Published: (2025)

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
by: Du, Yiyang, et al.
Published: (2025)

FREE-Merging: Fourier Transform for Efficient Model Merging
by: Zheng, Shenghe, et al.
Published: (2024)

A Comprehensive Review of Few-shot Action Recognition
by: Wanyan, Yuyang, et al.
Published: (2024)

MergeOcc: Bridge the Domain Gap between Different LiDARs for Robust Occupancy Prediction
by: Xu, Zikun, et al.
Published: (2024)

LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
by: Kim, Jinuk, et al.
Published: (2024)

AdaMerging: Adaptive Model Merging for Multi-Task Learning
by: Yang, Enneng, et al.
Published: (2023)

A Bridge from Audio to Video: Phoneme-Viseme Alignment Allows Every Face to Speak Multiple Languages
by: Su, Zibo, et al.
Published: (2025)

RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness
by: Zeng, Fanhu, et al.
Published: (2025)

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

Layer-Aware Video Composition via Split-then-Merge
by: Kara, Ozgur, et al.
Published: (2025)

DC-Merge: Improving Model Merging with Directional Consistency
by: Zhang, Han-Chen, et al.
Published: (2026)

ProMerge: Prompt and Merge for Unsupervised Instance Segmentation
by: Li, Dylan, et al.
Published: (2024)

Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptation
by: Wanyan, Yuyang, et al.
Published: (2025)

Bridging Domains through Subspace-Aware Model Merging
by: Chaves, Levy, et al.
Published: (2026)

Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
by: Chen, Mengyuan, et al.
Published: (2024)

MedMerge: Merging Models for Effective Transfer Learning to Medical Imaging Tasks
by: Almakky, Ibrahim, et al.
Published: (2024)

EMR-Merging: Tuning-Free High-Performance Model Merging
by: Huang, Chenyu, et al.
Published: (2024)

Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training
by: Shi, Mingjia, et al.
Published: (2024)

Token Merging via Spatiotemporal Information Mining for Surgical Video Understanding
by: Jiang, Xixi, et al.
Published: (2025)

DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs
by: Wang, Zhenhailong, et al.
Published: (2025)

HoliTom: Holistic Token Merging for Fast Video Large Language Models
by: Shao, Kele, et al.
Published: (2025)

Towards Visual Grounding: A Survey
by: Xiao, Linhui, et al.
Published: (2024)

OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling
by: Xiao, Linhui, et al.
Published: (2024)

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

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
by: Yang, Huitong, et al.
Published: (2025)

DeepMerge: Deep-Learning-Based Region-Merging for Image Segmentation
by: Lv, Xianwei, et al.
Published: (2023)

CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones
by: Gong, Wenyi, et al.
Published: (2025)

Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation
by: Shin, Juncheol, et al.
Published: (2025)

Fine-tuning Pre-trained Vision-Language Models in a Human-Annotation-Free Manner
by: Wang, Qian-Wei, et al.
Published: (2026)