Copertina

Representation Surgery for Multi-Task Model Merging

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yang, Enneng, Shen, Li, Wang, Zhenyi, Guo, Guibing, Chen, Xiaojun, Wang, Xingwei, Tao, Dacheng
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery
di: Yang, Enneng, et al.
Pubblicazione: (2024)

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

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

Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
di: Shen, Li, et al.
Pubblicazione: (2024)

A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
di: Wang, Zhenyi, et al.
Pubblicazione: (2023)

Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning
di: Hu, Zixuan, et al.
Pubblicazione: (2023)

Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
di: Hu, Zixuan, et al.
Pubblicazione: (2023)

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications
di: Hu, Zixuan, et al.
Pubblicazione: (2025)

AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning
di: Yang, Enneng, et al.
Pubblicazione: (2022)

Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
di: Tang, Anke, et al.
Pubblicazione: (2024)

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport
di: Pan, Zecheng, et al.
Pubblicazione: (2025)

A Unified and General Framework for Continual Learning
di: Wang, Zhenyi, et al.
Pubblicazione: (2024)

Efficient Prompt Tuning by Multi-Space Projection and Prompt Fusion
di: Lan, Pengxiang, et al.
Pubblicazione: (2024)

Distributionally Robust Graph Out-of-Distribution Recommendation via Diffusion Model
di: Zhao, Chu, et al.
Pubblicazione: (2025)

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
di: Hu, Zixuan, et al.
Pubblicazione: (2024)

Image Captions are Natural Prompts for Text-to-Image Models
di: Lei, Shiye, et al.
Pubblicazione: (2023)

Text-Guided Multi-Scale Frequency Representation Adaptation
di: Yan, Weicai, et al.
Pubblicazione: (2026)

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

Mesh-Gait: A Unified Framework for Gait Recognition Through Multi-Modal Representation Learning from 2D Silhouettes
di: Wang, Zhao-Yang, et al.
Pubblicazione: (2025)

A Cascading Cooperative Multi-agent Framework for On-ramp Merging Control Integrating Large Language Models
di: Zhang, Miao, et al.
Pubblicazione: (2025)

Few-Shot Class Incremental Learning with Attention-Aware Self-Adaptive Prompt
di: Liu, Chenxi, et al.
Pubblicazione: (2024)

Symmetric Graph Contrastive Learning against Noisy Views for Recommendation
di: Zhao, Chu, et al.
Pubblicazione: (2024)

Label-Free Cross-Task LoRA Merging with Null-Space Compression
di: Lee, Wonyoung, et al.
Pubblicazione: (2026)

Subspace-Boosted Model Merging
di: Skorobogat, Ronald, et al.
Pubblicazione: (2025)

MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning
di: Nedungadi, Vishal, et al.
Pubblicazione: (2024)

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

Continual Learning From a Stream of APIs
di: Yang, Enneng, et al.
Pubblicazione: (2023)

LARV: Data-Free Layer-wise Adaptive Rescaling Veneer for Model Merging
di: Wang, Xinyu, et al.
Pubblicazione: (2026)

FunduSegmenter: Leveraging the RETFound Foundation Model for Joint Optic Disc and Optic Cup Segmentation in Retinal Fundus Images
di: Zhao, Zhenyi, et al.
Pubblicazione: (2025)

AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective
di: Wang, Zhenyi, et al.
Pubblicazione: (2026)

MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings
di: Li, Zijie, et al.
Pubblicazione: (2026)

Multiple Object Stitching for Unsupervised Representation Learning
di: Shen, Chengchao, et al.
Pubblicazione: (2025)

Diffusion Model-Based Video Editing: A Survey
di: Sun, Wenhao, et al.
Pubblicazione: (2024)

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

Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation
di: Zhao, Xin, et al.
Pubblicazione: (2024)

Continual Learning in Vision-Language Models via Aligned Model Merging
di: Sokar, Ghada, et al.
Pubblicazione: (2025)

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

AdaRank: Adaptive Rank Pruning for Enhanced Model Merging
di: Lee, Chanhyuk, et al.
Pubblicazione: (2025)

MagMax: Leveraging Model Merging for Seamless Continual Learning
di: Marczak, Daniel, et al.
Pubblicazione: (2024)

FREE: Faster and Better Data-Free Meta-Learning
di: Wei, Yongxian, et al.
Pubblicazione: (2024)