Continual Video-MLLM Adaptation over Evolving Domains

• URL: http://arxiv.org/abs/2607.18716v1
• Date: Tue, 21 Jul 2026 05:16:36 GMT
• Title: Continual Video-MLLM Adaptation over Evolving Domains
• Abstract summary: Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored.<n>We propose Distribution-Aware Expert Routing, a parameter-efficient framework for continual Video-MLLM adaptation over evolving domains.<n> Experiments on two strong Video-MLLM backbones show that DAER consistently outperforms prior methods.
• Score: 42.6837206153246
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored. In real-world deployments, video data often arrives continuously from heterogeneous domains, requiring the model to acquire new domain-specific knowledge without overwriting previously learned capabilities. Existing continual learning methods typically rely on shared adaptation spaces, which can induce severe cross-domain interference and catastrophic forgetting. We propose Distribution-Aware Expert Routing, a parameter-efficient framework for continual Video-MLLM adaptation over evolving domains. DAER maintains domain-isolated lightweight experts while keeping the pretrained Video-MLLM backbone frozen, thereby decoupling domain-specific adaptation from the general multimodal knowledge of the pretrained model. To enable fine-grained specialization, we introduce an intra-domain distribution-aware routing mechanism that matches each input to expert-level prototype reservoirs using MMD. To address the absence of task identities at inference time, we further propose an inter-domain routing mechanism that performs prototype matching in a discriminative subspace for robust domain identification. In addition, we introduce adaptive domain merging to improve parameter scalability and adopt a two-stage optimization strategy to stabilize expert specialization during continual learning. We evaluate DAER by curating a domain-incremental benchmark built from ten VidQA datasets covering diverse visual environments and reasoning demands. Experiments on two strong Video-MLLM backbones show that DAER consistently outperforms prior methods.

Related papers

• RB-FT: Rationale-Bootstrapped Fine-Tuning for Video Classification [14.224783616912783]
  Vision Language Models (VLMs) are becoming increasingly integral to multimedia understanding.<n>They often struggle with domain-specific video classification tasks, particularly with limited data.<n>We propose two-stage self-improvement paradigm to bridge this gap without new annotations.
  arXiv  Detail & Related papers  (2025-11-19T23:12:18Z)
• Consistent and Invariant Generalization Learning for Short-video Misinformation Detection [20.688230555928104]
  Short-video misinformation detection has attracted wide attention in the multi-modal domain.<n>Current models often exhibit unsatisfactory performance on unseen domains due to domain gaps.<n>We propose a new DOmain generalization model via ConsisTency and invariance learning for shORt-video misinformation detection.
  arXiv  Detail & Related papers  (2025-07-05T14:53:32Z)
• Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization [68.41367635546183]
  Single Domain Generalization aims to train models with consistent performance across diverse scenarios using data from a single source.<n>We propose Discriminative Domain Reassembly and Soft-Fusion (DRSF), a training framework leveraging synthetic data to improve model generalization.
  arXiv  Detail & Related papers  (2025-03-17T18:08:03Z)
• What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization [10.079844840768054]
  Domain Generalization aims to develop models that can generalize to novel and unseen data distributions.<n>We study how model architectures and pre-training objectives impact feature richness.<n>Our framework improves generalization to unseen domains by a maximum test accuracy improvement of over 4%.
  arXiv  Detail & Related papers  (2025-03-09T17:29:01Z)
• META: Mimicking Embedding via oThers' Aggregation for Generalizable Person Re-identification [68.39849081353704]
  Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time. This paper presents a new approach called Mimicking Embedding via oThers' Aggregation (META) for DG ReID.
  arXiv  Detail & Related papers  (2021-12-16T08:06:50Z)
• TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification [115.31432027711202]
  We argue that both domain-specific and domain-invariant features are crucial for improving the generalization ability of re-id models. We name two-stream adaptive learning (TAL) to simultaneously model these two kinds of information. Our framework can be applied to both single-source and multi-source domain generalization tasks.
  arXiv  Detail & Related papers  (2021-11-29T01:27:42Z)
• Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation [102.42638795864178]
  We propose a principled meta-learning based approach to OCDA for semantic segmentation. We cluster target domain into multiple sub-target domains by image styles, extracted in an unsupervised manner. A meta-learner is thereafter deployed to learn to fuse sub-target domain-specific predictions, conditioned upon the style code. We learn to online update the model by model-agnostic meta-learning (MAML) algorithm, thus to further improve generalization.
  arXiv  Detail & Related papers  (2020-12-15T13:21:54Z)
• Domain Conditioned Adaptation Network [90.63261870610211]
  We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism. This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
  arXiv  Detail & Related papers  (2020-05-14T04:23:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.