iGSP:Implicit Gradient Subspace Projection for Efficient Continual Learning of Vision-Language Models

• URL: http://arxiv.org/abs/2605.19301v1
• Date: Tue, 19 May 2026 03:22:14 GMT
• Title: iGSP:Implicit Gradient Subspace Projection for Efficient Continual Learning of Vision-Language Models
• Abstract summary: iGSP is a novel framework that achieves efficient adaptation via implicit gradient subspace projection.<n>Experiments on the MTIL benchmark demonstrate that iGSP achieves state-of-the-art accuracy.
• Score: 14.623213614166259
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language Models require efficient adaptation to continually emerging downstream tasks. While Parameter-Efficient Fine-Tuning mitigates catastrophic forgetting, assigning isolated modules per task leads to parameter explosion. Conversely, recent similarity-driven sharing mechanisms falsely equate superficial visual similarity with underlying alignment consistency. This fundamental mismatch triggers severe negative transfer between visually similar but logically distinct tasks and fails to exploit alignment reuse across visually diverse ones. We argue thatalignment sharing is fundamentally a geometric problem of overlapping optimization trajectories within shared low-rank subspaces. Grounded in this insight, we propose iGSP, a novel framework that achieves efficient adaptation via implicit gradient subspace projection. Leveraging the early convergence of MoE routers to establish the subspace basis, iGSP bifurcates the adaptation process into two phases. First, the Subspace Identification phase introduces candidate experts via basis pre-expansion, applies a novel subspace-constrained regularization to implicitly project new task gradients onto the historical subspace, and precisely prunes redundant dimensions by treating routing probabilities as gradient flow indicators, ultimately to maximize knowledge reuse. Second, the Orthogonal Subspace Fine-Tuning phase fixes this structural basis and removes the regularization to rapidly fit the task-specific residual loss. Extensive experiments on the MTIL benchmark demonstrate that iGSP achieves state-of-the-art accuracy while significantly improving training efficiency, reducing the average trainable parameters by 42.7\% compared to current SOTA methods, and decreasing the final total parameters by 86.9\% relative to counterparts. The source code is available at https://github.com/GeoX-Lab/iGSP.

Related papers

• Multimodal Foundation Models Adaptation based on Domain-Aware Relaxed Orthogonal Subspace for Remote Sensing [16.45880716714667]
  Domain-aware Relaxed Orthogonal Subspace adaptation (DROS)<n>DROS reformulates low-rank adaptation as data-conditioned subspace learning and flexible subspace adaptation.<n>Experiments on multiple remote sensing benchmarks demonstrate that DROS achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-09-12T02:19:11Z)
• LCPNet: Latent Consistent Proximal Unfolding Network for Infrared Small Target Detection [50.3892176822492]
  Infrared small target detection (IRSTD) aims to identify long distance small targets from complex infrared backgrounds.<n>Deep learning methods have improved IRSTD by learning discriminative image-to-mask mappings.<n>Deep unfolding methods partially address this issue by embedding model-driven iterations into neural networks.<n>We propose Latent Consistent Proximal unfolding network (LCPNet) to address these limitations.
  arXiv  Detail & Related papers  (2026-07-06T02:15:09Z)
• Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models [63.169731309799324]
  Class-incremental learning aims to continuously acquire new knowledge while preserving previously learned information, thereby mitigating catastrophic forgetting.<n>We propose HDSD, a Hierarchical Dual-Subspace Decoupling framework for continual learning in vision-language models.<n> Specifically, we introduce a lightweight Feature Modulation Module (FMM) that explicitly decomposes the parameter space into general and task-specific subspaces.
  arXiv  Detail & Related papers  (2026-05-08T09:42:05Z)
• Bayesian Learning-Enhanced Navigation with Deep Smoothing for Inertial-Aided Navigation [8.510813384980262]
  BLENDS is a data-driven post-processing framework that augments the classical two-filter smoother with a transformer-based neural network.<n> BLENDS achieves horizontal position improvements of up to 63% over the baseline forward EKF.
  arXiv  Detail & Related papers  (2026-03-26T12:11:59Z)
• The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation [86.83038620308423]
  Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data.<n>We propose Guided Online Low-rank Directional adaptation (GOLD), which uses a lightweight adapter to project features onto the golden subspace and learns a compact scaling vector while the subspace is dynamically updated via AGOP.
  arXiv  Detail & Related papers  (2026-03-23T12:48:38Z)
• DRAFTO: Decoupled Reduced-space and Adaptive Feasibility-repair Trajectory Optimization for Robotic Manipulators [4.0407133618465005]
  This paper introduces a new algorithm for trajectory optimization, Decoupled Reduced-space and Adaptive Feasibility-repair Trajectory Optimization (DRAFTO)<n>To reduce the number of repeated constrained optimizations while handling joint-limit feasibility, the optimization is decoupled into a reduced-space Gauss-Newton (GN) descent.<n>The results of our benchmark tests against optimization-based planners, such as CHOMP, TrajOpt, GPMP2, and FACTO, validate the high efficiency and reliability across diverse scenarios and tasks.
  arXiv  Detail & Related papers  (2026-03-10T20:24:42Z)
• TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training [53.93696896939915]
  Training tool-use agents typically rely on Supervised Fine-Tuning (SFT) on successful trajectories and Reinforcement Learning (RL) on pass-rate-selected tasks.<n>We propose TopoCurate, an interaction-aware framework that projects multi-trial rollouts from the same task into a unified semantic quotient topology.<n>TopoCurate achieves consistent gains of 4.2% (SFT) and 6.9% (RL) over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-03-02T10:38:54Z)
• GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry [4.94446914034065]
  GIST (Gradient Isometric Subspace Transformation) replaces axis-aligned scaling with robust subspace alignment.<n>We show that GIST matches or outperforms the state-of-the-art baseline with only 0.29% of the storage and 25% of the computational time.
  arXiv  Detail & Related papers  (2026-02-20T19:44:24Z)
• Unifying Search and Recommendation in LLMs via Gradient Multi-Subspace Tuning [33.69176756907003]
  Gradient Multi-Subspace Tuning (GEMS) is a novel framework that unifies search and recommendation tasks.<n>We show that GEMS consistently outperforms the state-of-the-art baselines across both search and recommendation tasks.
  arXiv  Detail & Related papers  (2026-01-14T14:03:07Z)
• Regularizing Subspace Redundancy of Low-Rank Adaptation [54.473090597164834]
  We propose ReSoRA, a method that explicitly models redundancy between mapping subspaces and adaptively Regularizes Subspace redundancy of Low-Rank Adaptation.<n>Our proposed method consistently facilitates existing state-of-the-art PETL methods across various backbones and datasets in vision-language retrieval and standard visual classification benchmarks.<n>As a training supervision, ReSoRA can be seamlessly integrated into existing approaches in a plug-and-play manner, with no additional inference costs.
  arXiv  Detail & Related papers  (2025-07-28T11:52:56Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation [56.44946660061753]
  This paper proposes a universal regularization technique called maximum spatial perturbation consistency (MSPC) MSPC enforces a spatial perturbation function (T ) and the translation operator (G) to be commutative (i.e., TG = GT ) Our method outperforms the state-of-the-art methods on most I2I benchmarks.
  arXiv  Detail & Related papers  (2022-03-23T19:59:04Z)

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.