Cover Image

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Ke, Dimitriadis, Nikolaos, Favero, Alessandro, Ortiz-Jimenez, Guillermo, Fleuret, Francois, Frossard, Pascal
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Localizing Task Information for Improved Model Merging and Compression
by: Wang, Ke, et al.
Published: (2024)

Single-Input Multi-Output Model Merging: Leveraging Foundation Models for Dense Multi-Task Learning
by: Giraldo, Juan Garcia, et al.
Published: (2025)

Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences
by: Dimitriadis, Nikolaos, et al.
Published: (2024)

Backdoor Unlearning by Linear Task Decomposition
by: Abdelraheem, Amel, et al.
Published: (2025)

MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs
by: Wang, Ke, et al.
Published: (2025)

Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels
by: Wang, Ke, et al.
Published: (2023)

PivotMerge: Bridging Heterogeneous Multimodal Pre-training via Post-Alignment Model Merging
by: Shao, Zibo, 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)

Laminating Representation Autoencoders for Efficient Diffusion
by: Calvo-González, Ramón, et al.
Published: (2026)

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising
by: Saied, Youssef, et al.
Published: (2026)

Continual Forgetting for Pre-trained Vision Models
by: Zhao, Hongbo, et al.
Published: (2024)

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

Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling
by: Hazimeh, Adam, et al.
Published: (2025)

Model soups need only one ingredient
by: Abdollahpoorrostam, Alireza, et al.
Published: (2026)

LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures
by: He, Wenzhe, et al.
Published: (2025)

Sequential Representation Learning via Static-Dynamic Conditional Disentanglement
by: Simon, Mathieu Cyrille, et al.
Published: (2024)

Preventing Catastrophic Forgetting through Memory Networks in Continuous Detection
by: Bhatt, Gaurav, et al.
Published: (2024)

Task Addition and Weight Disentanglement in Closed-Vocabulary Models
by: Hazimeh, Adam, et al.
Published: (2025)

PreSight: Enhancing Autonomous Vehicle Perception with City-Scale NeRF Priors
by: Yuan, Tianyuan, et al.
Published: (2024)

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

Slowing Down Forgetting in Continual Learning
by: Janetzky, Pascal, et al.
Published: (2024)

When Slots Compete: Slot Merging in Object-Centric Learning
by: Chatzisavvas, Christos, et al.
Published: (2026)

NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields
by: Zhang, Junge, et al.
Published: (2023)

LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes
by: Qu, Zefan, et al.
Published: (2024)

IOVS4NeRF:Incremental Optimal View Selection for Large-Scale NeRFs
by: Xie, Jingpeng, et al.
Published: (2024)

ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Field
by: Nakayama, Kiyohiro, et al.
Published: (2024)

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

Efficient World Models with Context-Aware Tokenization
by: Micheli, Vincent, et al.
Published: (2024)

Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMs
by: Ding, Xuan, et al.
Published: (2025)

TalkinNeRF: Animatable Neural Fields for Full-Body Talking Humans
by: Chatziagapi, Aggelina, et al.
Published: (2024)

To View Transform or Not to View Transform: NeRF-based Pre-training Perspective
by: Jeong, Hyeonjun, et al.
Published: (2026)

LiWi: Layering in the Wild
by: He, Yu, et al.
Published: (2026)

InfNeRF: Towards Infinite Scale NeRF Rendering with O(log n) Space Complexity
by: Liang, Jiabin, et al.
Published: (2024)

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

Practical Continual Forgetting for Pre-trained Vision Models
by: Zhao, Hongbo, et al.
Published: (2025)

IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection
by: Yin, Junbo, et al.
Published: (2024)

Material Transforms from Disentangled NeRF Representations
by: Lopes, Ivan, et al.
Published: (2024)

Anti-Forgetting Adaptation for Unsupervised Person Re-identification
by: Chen, Hao, et al.
Published: (2024)

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

Multi-modal NeRF Self-Supervision for LiDAR Semantic Segmentation
by: Timoneda, Xavier, et al.
Published: (2024)