Imagen de Portada

DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Oh, Changdae, Li, Yixuan, Song, Kyungwoo, Yun, Sangdoo, Han, Dongyoon
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning 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

Robust Adaptation of Foundation Models with Black-Box Visual Prompting
por: Oh, Changdae, et al.
Publicado: (2024)

Rotary Position Embedding for Vision Transformer
por: Heo, Byeongho, et al.
Publicado: (2024)

Model Stock: All we need is just a few fine-tuned models
por: Jang, Dong-Hwan, et al.
Publicado: (2024)

Towards Calibrated Robust Fine-Tuning of Vision-Language Models
por: Oh, Changdae, et al.
Publicado: (2023)

Masking meets Supervision: A Strong Learning Alliance
por: Heo, Byeongho, et al.
Publicado: (2023)

RL makes MLLMs see better than SFT
por: Song, Junha, et al.
Publicado: (2025)

Match me if you can: Semi-Supervised Semantic Correspondence Learning with Unpaired Images
por: Kim, Jiwon, et al.
Publicado: (2023)

Probabilistic Language-Image Pre-Training
por: Chun, Sanghyuk, et al.
Publicado: (2024)

LongProLIP: A Probabilistic Vision-Language Model with Long Context Text
por: Chun, Sanghyuk, et al.
Publicado: (2025)

When Test-Time Adaptation Meets Self-Supervised Models
por: Han, Jisu, et al.
Publicado: (2025)

Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation
por: Wang, Zixi, et al.
Publicado: (2025)

Token Bottleneck: One Token to Remember Dynamics
por: Kim, Taekyung, et al.
Publicado: (2025)

DNNs May Determine Major Properties of Their Outputs Early, with Timing Possibly Driven by Bias
por: Park, Song, et al.
Publicado: (2025)

HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts
por: Kim, Wonjae, et al.
Publicado: (2024)

Learning to See What You Need: Gaze Attention for Multimodal Large Language Models
por: Song, Junha, et al.
Publicado: (2026)

Interpolating Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner
por: Shang, Yuzhang, et al.
Publicado: (2024)

Similarity of Neural Architectures using Adversarial Attack Transferability
por: Hwang, Jaehui, et al.
Publicado: (2022)

Motion-Oriented Compositional Neural Radiance Fields for Monocular Dynamic Human Modeling
por: Kim, Jaehyeok, et al.
Publicado: (2024)

pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation
por: Mo, Shentong, et al.
Publicado: (2026)

Angular Gradient Sign Method: Uncovering Vulnerabilities in Hyperbolic Networks
por: Jo, Minsoo, et al.
Publicado: (2025)

Scratching Visual Transformer's Back with Uniform Attention
por: Hyeon-Woo, Nam, et al.
Publicado: (2022)

Continual Learning: Forget-free Winning Subnetworks for Video Representations
por: Kang, Haeyong, et al.
Publicado: (2023)

Understanding and Improving Training-free Loss-based Diffusion Guidance
por: Shen, Yifei, et al.
Publicado: (2024)

Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models
por: Ming, Yifei, et al.
Publicado: (2024)

WeGeFT: Weight-Generative Fine-Tuning for Multi-Faceted Efficient Adaptation of Large Models
por: Savadikar, Chinmay, et al.
Publicado: (2023)

Learning to Weight Parameters for Training Data Attribution
por: Li, Shuangqi, et al.
Publicado: (2025)

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
por: Kim, Donghyun, et al.
Publicado: (2024)

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning
por: Kim, Donghu, et al.
Publicado: (2024)

Contrastive Adversarial Training for Unsupervised Domain Adaptation
por: Chen, Jiahong, et al.
Publicado: (2024)

A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
por: Wang, Zhengbo, et al.
Publicado: (2024)

AcTTA: Rethinking Test-Time Adaptation via Dynamic Activation
por: Kim, Hyeongyu, et al.
Publicado: (2026)

Expanding the Role of Diffusion Models for Robust Classifier Training
por: Huang, Pin-Han, et al.
Publicado: (2026)

Asymmetric Co-Training for Source-Free Few-Shot Domain Adaptation
por: Li, Gengxu, et al.
Publicado: (2025)

Winning the Lottery by Preserving Network Training Dynamics with Concrete Ticket Search
por: Arora, Tanay, et al.
Publicado: (2025)

Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm
por: Huang, Fuxiang, et al.
Publicado: (2025)

MVP: Winning Solution to SMP Challenge 2025 Video Track
por: Ye, Liliang, et al.
Publicado: (2025)

MosaicDiff: Training-free Structural Pruning for Diffusion Model Acceleration Reflecting Pretraining Dynamics
por: Guo, Bowei, et al.
Publicado: (2025)

Weight Averaging for Out-of-Distribution Generalization and Few-Shot Domain Adaptation
por: Xu, Shijian
Publicado: (2025)

Layer Pruning with Consensus: A Triple-Win Solution
por: Mugnaini, Leandro Giusti, et al.
Publicado: (2024)

Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks
por: Liu, Zhenyu, et al.
Publicado: (2024)