paper-with-me

Papers

Modality-Decoupled Online Recursive Editing

2026-05-19 · Siyuan Li, Youyuan Zhang, Fangming Liu, Jing Li arxiv

Online model editing for multimodal large language models (MLLMs) requires assimilating a stream of corrections under tight compute and memory budgets. Yet editors developed for text-only LLMs often degrade on MLLMs: visually dominant activations skew the statistics that shape updates, causing cross-modal conflict, while sequential writes become entangled in a shared edit space and amplify long-horizon interference, causing inter-edit interference. To address these, we propose M-ORE, a modality-decoupled online recursive editor for lifelong MLLM adaptation. M-ORE is derived from a unified proximal-projection formulation and admits a closed-form update with a Sherman-Morrison recursion, yielding constant per-edit overhead. It maintains module-wise locality statistics for the text stack and the visual projector to avoid visually dominated update shaping and performs continual updates in a fixed orthogonal low-rank edit subspace via a Sherman-Morrison recursion to mitigate long-horizon interference. Experiments on multiple MLLM backbones and online editing benchmarks show that our M-ORE method consistently improves reliability, generality, and locality over strong baselines, while achieving favorable quality-efficiency scaling. Our code is publicly available at https://github.com/lab-klc/M-ORE.

📄 PDF Abstract BibTeX arXiv:2605.20273

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing

2026-07-02 · Siyuan Li, Youyuan Zhang, Ruitong Liu, Junxi Wang 외 arxiv

Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and minimal disruption to unrelated behaviors. E…

knowledge editing

MiVE: Multiscale Vision-language features for reference-guided video Editing

2026-05-14 · Tong Wang, Meng Zou, Chengjing Wu, Xiaochao Qu 외 arxiv

Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the instructed edits while preserving original motion and unedited content…

Beyond Hard Writes and Rigid Preservation: Soft Recursive Least-Squares for Lifelong LLM Editing

2026-01-22 · Xinyu Wang, Sicheng Lyu, Yu Gu, Jerry Huang 외 arxiv

Model editing updates a pre-trained LLM with new facts or rules without retraining while preserving unrelated behavior. In real deployment, edits arrive as long streams, creating a plasticity-stability dilemma: repeated …

FlowMimic: Mask-free Visual Editing and Generation with Pixel-pair Warped Flow Field for Online Video Editing Data Generation and Modality Mimicry

2026-07-20 · Dingyun Zhang, Lixue Gong, Wei Liu hf

In line with the prevailing direction of vision research, we explore the integration of both generation and editing capabilities for video and image modalities within a single model. Current approaches to collecting vide…

Referring Expression SegmentationImage Editing

SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing

2026-05-24 · Sen Liang, Cong Wang, Fengbin Guan, Zhentao Yu 외 arxiv

Visual and acoustic events in the physical world are inherently coupled, yet existing video editing methods typically adopt decoupled pipelines, lacking bidirectional modality interaction. This results in two key limitat…