Copertina

LARV: Data-Free Layer-wise Adaptive Rescaling Veneer for Model Merging

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Xinyu, Deng, Ke, Dou, Fei, Bi, Jinbo, Lu, Jin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Tasks
di: Alcover-Couso, Roberto, et al.
Pubblicazione: (2024)

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

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

Zero-Shot Transfer Capabilities of the Sundial Foundation Model for Leaf Area Index Forecasting
di: Zhang, Peining, et al.
Pubblicazione: (2025)

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

Adaptive Negative Evidential Deep Learning for Open-set Semi-supervised Learning
di: Yu, Yang, et al.
Pubblicazione: (2023)

Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion
di: Li, Jiawei, et al.
Pubblicazione: (2024)

LP-DETR: Layer-wise Progressive Relations for Object Detection
di: Kang, Zhengjian, et al.
Pubblicazione: (2025)

Training-Free Acceleration of ViTs with Delayed Spatial Merging
di: Heo, Jung Hwan, et al.
Pubblicazione: (2023)

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

Parallel Rescaling: Rebalancing Consistency Guidance for Personalized Diffusion Models
di: Chae, JungWoo, et al.
Pubblicazione: (2025)

Explaining Model Overfitting in CNNs via GMM Clustering
di: Dou, Hui, et al.
Pubblicazione: (2024)

Representation Surgery for Multi-Task Model Merging
di: Yang, Enneng, et al.
Pubblicazione: (2024)

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

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

Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approach For Long-Tailed Recognition
di: Zhang, Shuo, et al.
Pubblicazione: (2026)

LayeredDoc: Domain Adaptive Document Restoration with a Layer Separation Approach
di: Pilligua, Maria, et al.
Pubblicazione: (2024)

Anchoring and Rescaling Attention for Semantically Coherent Inbetweening
di: Choi, Tae Eun, et al.
Pubblicazione: (2026)

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

Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
di: Jeong, Wooseong, et al.
Pubblicazione: (2026)

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

EP-CFG: Energy-Preserving Classifier-Free Guidance
di: Zhang, Kai, et al.
Pubblicazione: (2024)

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

Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving
di: Zhang, Tianyuan, et al.
Pubblicazione: (2024)

LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching Inference
di: Li, Guandong
Pubblicazione: (2026)

An Architecture Built for Federated Learning: Addressing Data Heterogeneity through Adaptive Normalization-Free Feature Recalibration
di: Siomos, Vasilis, et al.
Pubblicazione: (2024)

Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models
di: Xia, Shi-Yu, et al.
Pubblicazione: (2024)

PA-Net: Precipitation-Adaptive Mixture-of-Experts for Long-Tail Rainfall Nowcasting
di: Xiao, Xinyu, et al.
Pubblicazione: (2026)

LINA: Learning INterventions Adaptively for Physical Alignment and Generalization in Diffusion Models
di: Yu, Shu, et al.
Pubblicazione: (2025)

LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Information
di: Wang, Ke, et al.
Pubblicazione: (2024)

Adaptive Pareto-Optimal Token Merging for Edge Transformer Models in Semantic Communication
di: Erak, Omar, et al.
Pubblicazione: (2025)

Accelerating Diffusion Transformers with Token-wise Feature Caching
di: Zou, Chang, et al.
Pubblicazione: (2024)

DeepIcon: A Hierarchical Network for Layer-wise Icon Vectorization
di: Bing, Qi, et al.
Pubblicazione: (2024)

DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture
di: Xiang, Qianlong, et al.
Pubblicazione: (2024)

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

VISA: Group-wise Visual Token Selection and Aggregation via Graph Summarization for Efficient MLLMs Inference
di: Jiang, Pengfei, et al.
Pubblicazione: (2025)

VEDA: 3D Molecular Generation via Variance-Exploding Diffusion with Annealing
di: Zhang, Peining, et al.
Pubblicazione: (2025)

GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training
di: Wei, Tong, et al.
Pubblicazione: (2025)

Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm
di: Papachristodoulou, Andreas, et al.
Pubblicazione: (2023)

CSA-Net: Channel-wise Spatially Autocorrelated Attention Networks
di: Nikzad, Nick, et al.
Pubblicazione: (2024)