arXiv Machine Learning

NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple Experts

arXiv Computer Vision
Oct 19

Mitigating Task Objective Conflicts for Continual Learning in Unified Multimodal Models

The paper introduces UniDecouple, a selective decoupling framework for continual learning in unified multimodal models that addresses Task Objective Conflict (TOC). By employing a Task-Aware Mixture-of-Experts (TA‑MoE) architecture, it retains shared attention layers while adding task‑specific feed‑forward network experts to reduce optimization conflicts. Hierarchical expert routing and hybrid collaboration further balance task specialization with cross‑task knowledge sharing, and a two‑stage training strategy enhances both multimodal understanding and image generation performance.

By Jiaxing Zhang, Hao Tang
arXiv AI
Jul 3

Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails

arXiv:2607. 02020v1 Announce Type: new Abstract: Multimodal large language models must continually adapt to evolving tasks and domains, yet standard continual learning metrics mainly measure whether old answers remain correct, leaving the stability of multimodal grounding largely unexamined.

By Qianyu Chen, Canran Xiao, Runxuan Tang
arXiv AI
Oct 16

CART: Compatible Routing for Multimodal Continual Instruction Tuning

The paper introduces CART, a method for Multimodal Continual Instruction Tuning that coordinates adaptation between a projector and a language model by using task‑specific experts and weighted mixtures. CART jointly infers expert weights based on relevance and cross‑module compatibility, and it controls model growth through relevance‑guided expert consolidation. Experiments show that CART achieves state‑of‑the‑art performance on multimodal continual learning tasks.

By Ling-Xiang Zhang, Tao Hu, Da-Wei Zhou
arXiv Machine Learning
Jul 31

Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting

arXiv:2508. 04227v3 Announce Type: replace-cross Abstract: Vision-language models (VLMs), spanning predictive architectures to generative Multimodal Large Language Models (MLLMs), have revolutionized artificial intelligence through powerful cross-modal alignment and zero-shot generalization.

By Yuyang Liu, Qiuhe Hong, Linlan Huang, Alexandra Gomez-Villa, Dipam Goswami, Tiantian Peng, Xialei Liu, Joost van de Weijer, Yonghong Tian
arXiv AI
Sep 24

Parameter Importance-Driven Continual Learning for Foundation Models

The paper introduces PIECE, a Parameter Importance-Driven Continual Learning method that selectively updates only 0.1% of core parameters to preserve general abilities while learning new domain knowledge. PIECE employs two importance estimators—PIECE‑F using Fisher Information and PIECE‑S combining gradient and curvature information—to guide updates. Experiments on three language models and two multimodal models demonstrate that PIECE maintains general capabilities and achieves state‑of‑the‑art continual learning performance without accessing prior training data or adding parameter overhead.

By Lingxiang Wang, Hainan Zhang, Zhiming Zheng