Adaptation Concern

Adaptation concern in machine learning focuses on efficiently tailoring large pre-trained models to specific tasks or domains without retraining the entire model. Current research heavily emphasizes low-rank adaptation (LoRA) techniques and their variants, often applied to transformer-based models like LLMs and diffusion models, to achieve parameter efficiency and improved performance. This research area is significant because it addresses the computational cost and memory limitations associated with fine-tuning massive models, enabling broader application and deployment of advanced AI systems across diverse tasks and resource-constrained environments. Furthermore, investigations into bias mitigation and improved adaptation strategies within these frameworks are actively pursued.

Papers

November 13, 2024

Learning Robust Grasping Strategy Through Tactile Sensing and Adaption Skill
Yueming Hu, Mengde Li, Songhua Yang, Xuetao Li, Sheng Liu, Miao Li
Adaptation Concern Functional Grasping Tactile Sensing Stable Grasp Dexterous Grasping Robust Grasping

November 12, 2024

November 10, 2024

Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation
Xiaowei Yu, Zhe Huang, Zao Zhang
Convolutional Neural Network Unsupervised Domain Adaptation Adaptation Concern Feature Fusion Fusion Transformer Unsupervised Domain Transferability Measure

November 7, 2024

November 4, 2024

November 3, 2024

Federated Learning Clients Clustering with Adaptation to Data Drifts
Minghao Li (1), Dmitrii Avdiukhin (2), Rana Shahout (1), Nikita Ivkin (3), Vladimir Braverman (4), Minlan Yu (1) ((1) Harvard University, (2) Northwestern University, (3) Amazon, (4) Rice University)
Adaptation Concern Data Drift Client Heterogeneity Clustered Federated Learning Adaptive Clustering Federated Learning Client

November 2, 2024

LoRA-Contextualizing Adaptation of Large Multimodal Models for Long Document Understanding
Jian Chen, Ruiyi Zhang, Yufan Zhou, Tong Yu, Franck Dernoncourt, Jiuxiang Gu, Ryan A. Rossi, Changyou Chen, Tong Sun
Large Multimodal Model Adaptation Concern Document Understanding Visually Rich Document Long Span Multimodal Retrieval Text Rich Image

November 1, 2024

October 31, 2024

EMGBench: Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography
Jehan Yang, Maxwell Soh, Vivianna Lieu, Douglas J Weber, Zackory Erickson
Machine Learning Adaptation Concern Surface Electromyography

October 29, 2024

Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection
Gyusam Chang, Jiwon Lee, Donghyun Kim, Jinkyu Kim, Dongwook Lee, Daehyun Ji, Sujin Jang, Sangpil Kim
Data Detection 3D Object Detection Multi View 3D Object Adaptation Concern 3D Object Detector View Camera

October 26, 2024

An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation
Dongdong Lin, Yue Li, Benedetta Tondi, Bin Li, Mauro Barni
Latent Diffusion Model Adaptation Concern Watermarking Method Agnostic Watermarking Model Watermarking

Adaptation Concern

Papers

Learning Robust Grasping Strategy Through Tactile Sensing and Adaption Skill

Federated Low-Rank Adaptation with Differential Privacy over Wireless Networks

Uncertainty-Aware Test-Time Adaptation for Inverse Consistent Diffeomorphic Lung Image Registration

Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation

Dynamic Detection of Relevant Objectives and Adaptation to Preference Drifts in Interactive Evolutionary Multi-Objective Optimization

Variational Low-Rank Adaptation Using IVON

Enhancing Bronchoscopy Depth Estimation through Synthetic-to-Real Domain Adaptation

Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation

Vocal Sandbox: Continual Learning and Adaptation for Situated Human-Robot Collaboration

Dynamic Weight Adjusting Deep Q-Networks for Real-Time Environmental Adaptation

Federated Learning Clients Clustering with Adaptation to Data Drifts

LoRA-Contextualizing Adaptation of Large Multimodal Models for Long Document Understanding

Dual Low-Rank Adaptation for Continual Learning with Pre-Trained Models

C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning

EMGBench: Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography

Offline Reinforcement Learning and Sequence Modeling for Downlink Link Adaptation

Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous Clients

Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation

Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection

An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation