Cover Image

SMoLoRA: Exploring and Defying Dual Catastrophic Forgetting in Continual Visual Instruction Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Ziqi, Che, Chang, Wang, Qi, Li, Yangyang, Shi, Zenglin, Wang, Meng
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning
by: Che, Chang, et al.
Published: (2025)

StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs
by: Che, Chang, et al.
Published: (2026)

Harmonious Parameter Adaptation in Continual Visual Instruction Tuning for Safety-Aligned MLLMs
by: Wang, Ziqi, et al.
Published: (2025)

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

Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning
by: Ge, Chendi, et al.
Published: (2025)

Multimodal Instruction Tuning with Conditional Mixture of LoRA
by: Shen, Ying, et al.
Published: (2024)

Defying Imbalanced Forgetting in Class Incremental Learning
by: Xu, Shixiong, et al.
Published: (2024)

Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual Learning
by: Jia, Ziqi, et al.
Published: (2025)

Unveiling the Tapestry: the Interplay of Generalization and Forgetting in Continual Learning
by: Shi, Zenglin, et al.
Published: (2022)

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

StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
by: Wang, Yixu, et al.
Published: (2025)

Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learning
by: Ullah, Zahid, et al.
Published: (2025)

LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement
by: Bian, Jieming, et al.
Published: (2024)

MuseumMaker: Continual Style Customization without Catastrophic Forgetting
by: Liu, Chenxi, et al.
Published: (2024)

Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning
by: Gou, Yunhao, et al.
Published: (2023)

Continual Learning and Catastrophic Forgetting
by: van de Ven, Gido M., et al.
Published: (2024)

Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation
by: Bafghi, Reza Akbarian, et al.
Published: (2025)

Solving the Catastrophic Forgetting Problem in Generalized Category Discovery
by: Cao, Xinzi, et al.
Published: (2025)

LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning
by: Gao, Chenjian, et al.
Published: (2025)

Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA Banks
by: Fang, Weibai, et al.
Published: (2026)

Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
by: Wu, Qirui, et al.
Published: (2025)

LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair
by: Song, Xue, et al.
Published: (2024)

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

LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning
by: Wang, Kaihong, et al.
Published: (2025)

Deep Generative Continual Learning using Functional LoRA: FunLoRA
by: Enescu, Victor, et al.
Published: (2025)

UnGuide: Learning to Forget with LoRA-Guided Diffusion Models
by: Polowczyk, Agnieszka, et al.
Published: (2025)

Exploring Data-Free LoRA Transferability for Video Diffusion Models
by: Wang, Yuchen, et al.
Published: (2026)

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

FreeLoRA: Enabling Training-Free LoRA Fusion for Autoregressive Multi-Subject Personalization
by: Zheng, Peng, et al.
Published: (2025)

MCF-VC: Mitigate Catastrophic Forgetting in Class-Incremental Learning for Multimodal Video Captioning
by: Xiong, Huiyu, et al.
Published: (2024)

Visual Instruction Tuning with Chain of Region-of-Interest
by: Chen, Yixin, et al.
Published: (2025)

Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models
by: Cao, Meng, et al.
Published: (2024)

Vision as LoRA
by: Wang, Han, et al.
Published: (2025)

Learning Dual Transformers for All-In-One Image Restoration from a Frequency Perspective
by: Chu, Jie, et al.
Published: (2024)

Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting
by: Xu, Runze, et al.
Published: (2026)

Instruction Tuning-free Visual Token Complement for Multimodal LLMs
by: Wang, Dongsheng, et al.
Published: (2024)

In-Context LoRA for Diffusion Transformers
by: Huang, Lianghua, et al.
Published: (2024)

OASIS: Online Sample Selection for Continual Visual Instruction Tuning
by: Lee, Minjae, et al.
Published: (2025)

LLaVA-c: Continual Improved Visual Instruction Tuning
by: Liu, Wenzhuo, et al.
Published: (2025)

What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning
by: Du, Yifan, et al.
Published: (2023)