Cover Image

Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lou, Meng, Yu, Stanley, Yu, Yizhou
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts
by: Lou, Meng, et al.
Published: (2026)

OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernels
by: Lou, Meng, et al.
Published: (2025)

Less Could Be Better: Parameter-efficient Fine-tuning Advances Medical Vision Foundation Models
by: Lian, Chenyu, et al.
Published: (2024)

SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks
by: Lou, Meng, et al.
Published: (2024)

SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation
by: Fu, Yunxiang, et al.
Published: (2024)

A2Mamba: Attention-augmented State Space Models for Visual Recognition
by: Lou, Meng, et al.
Published: (2025)

TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition
by: Lou, Meng, et al.
Published: (2023)

MoVA: Adapting Mixture of Vision Experts to Multimodal Context
by: Zong, Zhuofan, et al.
Published: (2024)

Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks
by: Qu, Tingyu, et al.
Published: (2024)

Filtering Memorization from Parameter-Space in Diffusion Models
by: Zhe, Yu, et al.
Published: (2026)

Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
by: Lou, Meng, et al.
Published: (2026)

Teacher-Guided Routing for Sparse Vision Mixture-of-Experts
by: Kada, Masahiro, et al.
Published: (2026)

AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection
by: Jiang, Yichen, et al.
Published: (2025)

MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection
by: Kong, Chenqi, et al.
Published: (2024)

Vision Function Layer in Multimodal LLMs
by: Shi, Cheng, et al.
Published: (2025)

Mixture-of-Experts Models in Vision: Routing, Optimization, and Generalization
by: Rokah, Adam, et al.
Published: (2026)

Vision Transformers Need More Than Registers
by: Shi, Cheng, et al.
Published: (2026)

PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer
by: Feng, Qian, et al.
Published: (2024)

Adapting Foundation Vision-Language Models to Medical Diagnosis via Query-Driven Expert Bridging
by: Li, Yitong, et al.
Published: (2025)

Cross-Frequency Implicit Neural Representation with Self-Evolving Parameters
by: Yu, Chang, et al.
Published: (2025)

Expert Pyramid Tuning: Efficient Parameter Fine-Tuning for Expertise-Driven Task Allocation
by: Zhang, Jia-Chen, et al.
Published: (2026)

Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perception
by: Sun, Yiding, et al.
Published: (2026)

Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
by: Guo, Hang, et al.
Published: (2023)

PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks
by: Cui, Cheng, et al.
Published: (2026)

PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection
by: Dong, Sijun, et al.
Published: (2025)

Exploring Superposition and Interference in State-of-the-Art Low-Parameter Vision Models
by: Hollard, Lilian, et al.
Published: (2025)

Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning
by: Si, Chongjie, et al.
Published: (2024)

PE-CLIP: A Parameter-Efficient Fine-Tuning of Vision Language Models for Dynamic Facial Expression Recognition
by: Saadi, Ibtissam, et al.
Published: (2025)

BioVLM: Routing Prompts, Not Parameters, for Cross-Modality Generalization in Biomedical VLMs
by: Singha, Mainak, et al.
Published: (2026)

ExPLoRA: Parameter-Efficient Extended Pre-Training to Adapt Vision Transformers under Domain Shifts
by: Khanna, Samar, et al.
Published: (2024)

CGSA: Class-Guided Slot-Aware Adaptation for Source-Free Object Detection
by: Dai, Boyang, et al.
Published: (2026)

Cross-Modal Adapter: Parameter-Efficient Transfer Learning Approach for Vision-Language Models
by: Yang, Juncheng, et al.
Published: (2024)

Decompose, Mix, Adapt: A Unified Framework for Parameter-Efficient Neural Network Recombination and Compression
by: Tasnim, Nazia, et al.
Published: (2026)

Parameter Aware Mamba Model for Multi-task Dense Prediction
by: Yu, Xinzhuo, et al.
Published: (2025)

Parameter-free Video Segmentation for Vision and Language Understanding
by: Mahon, Louis, et al.
Published: (2025)

MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models
by: Guo, Yuncheng, et al.
Published: (2025)

MLAE: Masked LoRA Experts for Visual Parameter-Efficient Fine-Tuning
by: Wang, Junjie, et al.
Published: (2024)

Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer
by: Chang, Da, et al.
Published: (2024)

Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation
by: Lu, Yangxiao, et al.
Published: (2024)

AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors
by: Yuan, Kaishen, et al.
Published: (2024)