Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment

• URL: http://arxiv.org/abs/2605.23780v1
• Date: Fri, 22 May 2026 15:46:10 GMT
• Title: Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment
• Abstract summary: Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities.<n>In intrinsic multimodal knowledge editing, it often exhibits limited generality, failing to propagate edits across semantically equivalent visual and linguistic variations.<n>This issue arises from the lack of explicit semantic supervision, rigid editing scopes, and biased anchoring to individual samples in high-dimensional multimodal spaces.<n>We address robust intrinsic multimodal knowledge editing by explicitly targeting generalization. We formalize through knowledge units that group semantically equivalent multimodal inputs and define generality as consistent predictions within each unit.
• Score: 17.054864006712318
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal large language models (MLLMs) need efficient mechanisms to update knowledge without degrading existing capabilities. While intrinsic multimodal knowledge editing achieves strong reliability and locality, it often exhibits limited generality, failing to propagate edits across semantically equivalent visual and linguistic variations. This issue arises from the lack of explicit semantic supervision, rigid editing scopes, and biased anchoring to individual samples in high-dimensional multimodal spaces. We address robust intrinsic multimodal knowledge editing by explicitly targeting generalization. We formalize robustness through knowledge units that group semantically equivalent multimodal inputs and define generality as consistent predictions within each unit. To expose fragile semantic regions, we introduce Latent Adversarial Robustification (LAR), which generates adversarial yet semantically coherent variants in the joint latent space. We further propose Rank-Constrained Subspace Learning (RCSL), enforcing low-rank alignment of adversarial representations at the edit layer via a singular value-based objective. Extensive analysis demonstrates the effectiveness of ASAM empirically.

Related papers

• Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral Domain [94.64605746540472]
  Multimodal large language models (MLLMs) have extended the capability of large language models (LLMs) to process more contextual multimodal information.<n>Recent studies reveal that MLLMs remain highly vulnerable to adversarial inputs, especially those targeting visual components.<n>We propose a novel phase-aware adversarial attack framework that explicitly restricts adversarial perturbations to structure-relevant phase regions.
  arXiv  Detail & Related papers  (2026-09-01T06:34:32Z)
• Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild [49.77540427384148]
  We present AgentHOI, a training-free, agentic framework that transfers the generalist multimodal reasoning capabilities of foundation models to HOI detection in the wild.<n>To address the challenges of incomplete interaction discovery and ambiguous localization in complex scenes, we introduce two key mechanisms.<n>AgentHOI achieves superior performance over state-of-the-art supervised and weakly supervised methods in real-world settings.
  arXiv  Detail & Related papers  (2026-07-15T14:30:20Z)
• CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection [33.94199994115719]
  CL-Anomaly is a parameter-efficient fine-tuning framework for continuous learning for anomaly detection.<n>PrivLoRA physically isolates task-specific subspaces in the parameter space to prevent semantic entanglement of anomaly knowledge.<n> Layer-Adaptive Shared Experts maintain cross-task representations within a unified feature space.
  arXiv  Detail & Related papers  (2026-07-03T03:53:58Z)
• Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Models [12.330598426331091]
  Localized and Disentangled Knowledge Editing achieves precise and generalized editing by localizing fact-specific model layers and disentangling target-relevant inputs from irrelevant ones.<n>Experiments demonstrate LDKE achieves superior performance in propagating edits to related contexts while maintaining high locality.
  arXiv  Detail & Related papers  (2026-05-28T12:06:39Z)
• Decoding the Delta: Unifying Remote Sensing Change Detection and Understanding with Multimodal Large Language Models [9.373908834130669]
  We present Delta-LLaVA, a novel MLLM framework specifically tailored for multi-temporal remote sensing interpretation.<n>It overcomes the limitations of naive feature concatenation through three core innovations.<n>It decisively outperforms leading generalist MLLMs and specialized segmentation models in complex change deduction and high-precision boundary localization.
  arXiv  Detail & Related papers  (2026-04-15T16:23:05Z)
• AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models [21.682989096955467]
  AG-VAS (Anchor-Guided Visual Anomaly) is a new framework that expands the LMM vocabulary with three learnable semantic anchor tokens.<n>AG-VAS achieves consistent state-of-the-art performance in the zero-shot setting.
  arXiv  Detail & Related papers  (2026-03-01T22:25:23Z)
• From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation [59.27094165576015]
  We propose a novel learning paradigm (UniMod) that transitions from sparse decision-making to dense reasoning traces.<n>By constructing structured trajectories encompassing evidence grounding, modality assessment, risk mapping, policy decision, and response generation, we reformulate monolithic decision tasks into a multi-dimensional boundary learning process.<n>We introduce specialized optimization strategies to decouple task-specific parameters and rebalance training dynamics, effectively resolving interference between diverse objectives in multi-task learning.
  arXiv  Detail & Related papers  (2026-01-28T09:29:40Z)
• UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception [54.53657134205492]
  UniAlignment is a unified multimodal generation framework within a single diffusion transformer.<n>It incorporates both intrinsic-modal semantic alignment and cross-modal semantic alignment, thereby enhancing the model's cross-modal consistency and instruction-following robustness.<n>We present SemGen-Bench, a new benchmark specifically designed to evaluate multimodal semantic consistency under complex textual instructions.
  arXiv  Detail & Related papers  (2025-09-28T09:11:30Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• What Makes You Unique? Attribute Prompt Composition for Object Re-Identification [70.67907354506278]
  Object Re-IDentification aims to recognize individuals across non-overlapping camera views.<n>Single-domain models tend to overfit to domain-specific features, whereas cross-domain models often rely on diverse normalization strategies.<n>We propose an Attribute Prompt Composition framework, which exploits textual semantics to jointly enhance discrimination and generalization.
  arXiv  Detail & Related papers  (2025-09-23T07:03:08Z)
• NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-Identification [17.10113184019939]
  Multi-modal object Re-Identification (ReID) aims to obtain accurate identity features across heterogeneous modalities.<n>In this paper, we propose a reliable caption generation pipeline based on attribute confidence.<n>We also propose a novel ReID framework, named NEXT, to model diverse identity patterns.
  arXiv  Detail & Related papers  (2025-05-26T13:52:28Z)
• Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration [107.31481207855835]
  Current methods, including intrinsic knowledge editing and external knowledge resorting, each possess strengths and weaknesses. We propose UniKE, a novel multimodal editing method that establishes a unified perspective for intrinsic knowledge editing and external knowledge resorting.
  arXiv  Detail & Related papers  (2024-09-30T02:13:53Z)

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.