StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs

• URL: http://arxiv.org/abs/2605.16353v2
• Date: Tue, 19 May 2026 02:02:00 GMT
• Title: StrLoRA: Towards Streaming Continual Visual Instruction Tuning for MLLMs
• Abstract summary: We introduce Streaming CVIT (StrCVIT), where models learn from a stream of data chunks containing a dynamic mixture of tasks.<n>In StrCVIT, a model must simultaneously acquire new abilities, reinforce recurring abilities, and forgetting.<n>We propose StrLoRA, a regularized two-stage expert routing framework.
• Score: 9.912407135967836
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual Visual Instruction Tuning (CVIT) enables Multimodal Large Language Models to incrementally acquire new abilities. However, existing CVIT methods operate under a restrictive task-incremental setting, where each training phase corresponds to a single, predefined task. This does not reflect real-world conditions, where data arrives as a continuous stream of interleaved and dynamically evolving tasks. To bridge this gap, we introduce Streaming CVIT (StrCVIT), a more general and realistic setting where models learn from a stream of data chunks containing a dynamic mixture of tasks. In StrCVIT, a model must simultaneously acquire new abilities, reinforce recurring abilities, and mitigate forgetting. Existing CVIT methods fail here as they cannot reliably distinguish or adapt to the heterogeneous task samples within each chunk. We therefore propose StrLoRA, a regularized two-stage expert routing framework. StrLoRA first performs task-aware expert selection using the textual instruction to activate a sparse subset of relevant experts, reducing cross-task interference. It then applies token-wise expert weighting within this subset, where contribution weights are computed via cross-modal attention between local visual tokens and the global instruction representation. To maintain stability across the non-stationary stream, a routing-stability regularization aligns current routing distributions with a historical exponential moving average reference. Extensive experiments on a newly developed StrCVIT benchmark show that StrLoRA substantially outperforms existing methods, effectively enhancing model's abilities from continuously evolving data streams. The code is available at https://github.com/chanceche/StrCVIT.

Related papers

• Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach [78.4812458793128]
  We propose textbfTACO, a test-time-scaling framework that applies a lightweight pseudo-count estimator as a high-fidelity verifier of action chunks.<n>Our method resembles the classical anti-exploration principle in offline reinforcement learning (RL), and being gradient-free, it incurs significant computational benefits.
  arXiv  Detail & Related papers  (2025-12-02T14:42:54Z)
• Learning with Preserving for Continual Multitask Learning [4.847042727427382]
  We introduce Learning with Preserving (LwP), a novel framework that shifts the focus from preserving task outputs to maintaining the shared representation space.<n>LwP not only mitigates catastrophic forgetting but also consistently outperforms state-of-the-art baselines in CMTL tasks.
  arXiv  Detail & Related papers  (2025-11-11T22:23:20Z)
• CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning [80.18781219542016]
  Continual Learning (CL) empowers AI models to continuously learn from sequential task streams.<n>Recent parameter-efficient fine-tuning (PEFT)-based CL methods have garnered increasing attention due to their superior performance.<n>We propose Cross-subspace Knowledge Alignment and Aggregation (CKAA) to enhance robustness against misleading task-ids.
  arXiv  Detail & Related papers  (2025-07-13T03:11:35Z)
• Scalable In-Context Q-Learning [68.9917436397079]
  We propose textbfScalable textbfIn-textbfContext textbfQ-textbfLearning (textbfSICQL) to steer in-context reinforcement learning.<n>textbfSICQL harnesses dynamic programming and world modeling to steer ICRL toward efficient reward and task generalization.
  arXiv  Detail & Related papers  (2025-06-02T04:21:56Z)
• One Train for Two Tasks: An Encrypted Traffic Classification Framework Using Supervised Contrastive Learning [18.63871240173137]
  We propose an effective model named a Contrastive Learning Enhanced Temporal Fusion (CLE-TFE) In particular, we utilize supervised contrastive learning to enhance the packet-level and flow-level representations. We also propose cross-level multi-task learning, which simultaneously accomplishes the packet-level and flow-level classification tasks in the same model with one training.
  arXiv  Detail & Related papers  (2024-02-12T09:10:09Z)
• Task-Distributionally Robust Data-Free Meta-Learning [99.56612787882334]
  Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data. For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift ( TDS) and Task-Distribution Corruption (TDC)
  arXiv  Detail & Related papers  (2023-11-23T15:46:54Z)
• Task Residual for Tuning Vision-Language Models [69.22958802711017]
  We propose a new efficient tuning approach for vision-language models (VLMs) named Task Residual Tuning (TaskRes) TaskRes explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task. The proposed TaskRes is simple yet effective, which significantly outperforms previous methods on 11 benchmark datasets.
  arXiv  Detail & Related papers  (2022-11-18T15:09:03Z)
• Task-Customized Self-Supervised Pre-training with Scalable Dynamic Routing [76.78772372631623]
  A common practice for self-supervised pre-training is to use as much data as possible. For a specific downstream task, however, involving irrelevant data in pre-training may degenerate the downstream performance. It is burdensome and infeasible to use different downstream-task-customized datasets in pre-training for different tasks.
  arXiv  Detail & Related papers  (2022-05-26T10:49:43Z)
• A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning [11.076005074172516]
  reinforcement learning algorithms can easily encounter catastrophic forgetting or interference when faced with lifelong streaming information. We propose a scalable lifelong RL method that dynamically expands the network capacity to accommodate new knowledge. We show that our method successfully facilitates scalable lifelong RL and outperforms relevant existing methods.
  arXiv  Detail & Related papers  (2022-05-22T09:48:41Z)
• Task-agnostic Continual Learning with Hybrid Probabilistic Models [75.01205414507243]
  We propose HCL, a Hybrid generative-discriminative approach to Continual Learning for classification. The flow is used to learn the data distribution, perform classification, identify task changes, and avoid forgetting. We demonstrate the strong performance of HCL on a range of continual learning benchmarks such as split-MNIST, split-CIFAR, and SVHN-MNIST.
  arXiv  Detail & Related papers  (2021-06-24T05:19:26Z)

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.