Cover Image

ATLAS: Adapter-Based Multi-Modal Continual Learning with a Two-Stage Learning Strategy

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Hong, Tan, Zhiquan, Li, Xingyu, Huang, Weiran
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Provable Contrastive Continual Learning
by: Wen, Yichen, et al.
Published: (2024)

Matrix Information Theory for Self-Supervised Learning
by: Zhang, Yifan, et al.
Published: (2023)

Continual Adapter Tuning with Semantic Shift Compensation for Class-Incremental Learning
by: Zhou, Qinhao, et al.
Published: (2024)

IDER: IDempotent Experience Replay for Reliable Continual Learning
by: Liu, Zhanwang, et al.
Published: (2026)

RMAdapter: Reconstruction-based Multi-Modal Adapter for Vision-Language Models
by: Lin, Xiang, et al.
Published: (2025)

Multi-Modal Adapter for Vision-Language Models
by: Seputis, Dominykas, et al.
Published: (2024)

MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets
by: Wei, Lai, et al.
Published: (2023)

Contrastive Learning Is Spectral Clustering On Similarity Graph
by: Tan, Zhiquan, et al.
Published: (2023)

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training
by: Wei, Lai, et al.
Published: (2025)

FedPIA -- Permuting and Integrating Adapters leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning
by: Saha, Pramit, et al.
Published: (2024)

DAM: Dynamic Adapter Merging for Continual Video QA Learning
by: Cheng, Feng, et al.
Published: (2024)

Dynamic Integration of Task-Specific Adapters for Class Incremental Learning
by: Li, Jiashuo, et al.
Published: (2024)

FedDiff: Diffusion Model Driven Federated Learning for Multi-Modal and Multi-Clients
by: Li, DaiXun, et al.
Published: (2023)

Unveiling the Dynamics of Information Interplay in Supervised Learning
by: Song, Kun, et al.
Published: (2024)

A Unified and General Framework for Continual Learning
by: Wang, Zhenyi, et al.
Published: (2024)

Scalable Strategies for Continual Learning with Replay
by: Hickok, Truman
Published: (2025)

A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
by: Wang, Zhenyi, et al.
Published: (2023)

Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters
by: Smith, James Seale, et al.
Published: (2023)

Rethinking Multi-domain Generalization with A General Learning Objective
by: Tan, Zhaorui, et al.
Published: (2024)

Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation
by: Baba, Kaito, et al.
Published: (2026)

IDEA: Image Description Enhanced CLIP-Adapter
by: Ye, Zhipeng, et al.
Published: (2025)

CLoE: Expert Consistency Learning for Missing Modality Segmentation
by: Tong, Xinyu, et al.
Published: (2026)

MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning
by: Nedungadi, Vishal, et al.
Published: (2024)

Learning without Isolation: Pathway Protection for Continual Learning
by: Chen, Zhikang, et al.
Published: (2025)

Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation
by: Yan, HongWei, et al.
Published: (2024)

MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
by: Li, Xu, et al.
Published: (2025)

Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning
by: Kim, Taeheon, et al.
Published: (2025)

Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
by: Wei, Lai, et al.
Published: (2025)

RainbowPrompt: Diversity-Enhanced Prompt-Evolving for Continual Learning
by: Hong, Kiseong, et al.
Published: (2025)

Contrastive-to-Self-Supervised: A Two-Stage Framework for Script Similarity Learning
by: Roman, Claire, et al.
Published: (2026)

Mimicking or Reasoning: Rethinking Multi-Modal In-Context Learning in Vision-Language Models
by: Huang, Chengyue, et al.
Published: (2025)

Adapter Naturally Serves as Decoupler for Cross-Domain Few-Shot Semantic Segmentation
by: Tong, Jintao, et al.
Published: (2025)

Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How
by: Hess, Timm, et al.
Published: (2023)

LLMs Can Evolve Continually on Modality for X-Modal Reasoning
by: Yu, Jiazuo, et al.
Published: (2024)

AdapterTune: Zero-Initialized Low-Rank Adapters for Frozen Vision Transformers
by: Khazem, Salim
Published: (2026)

MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings
by: Li, Zijie, et al.
Published: (2026)

Training-Only Heterogeneous Image-Patch-Text Graph Supervision for Advancing Few-Shot Learning Adapters
by: Mohammad, Mohammed Rahman Sherif Khan, et al.
Published: (2026)

ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges
by: Ai, Jiaxin, et al.
Published: (2025)

ProtoMedX: Towards Explainable Multi-Modal Prototype Learning for Bone Health Classification
by: Pellicer, Alvaro Lopez, et al.
Published: (2025)

Transferability-Guided Cross-Domain Cross-Task Transfer Learning
by: Tan, Yang, et al.
Published: (2022)