Multimodal Knowledge Editing

Latest papers

10 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Repairing Speech Access After Text Updates with Frozen Affine Fields
Oct 14, 2026Ming-Hao Hsu, Yuxiang Wang, Yingda Shen +1Multimodal Knowledge Editing Speech Language Models
School of Data Science, The Chinese University of Hong Kong, Shenzhen, China
Evaluating and Understanding Model Editing for Medical Vision Language Models
Jul 6, 2026Guli Zhu, Chenwei Wu, Liyue ShenKnowledge Editing Medical VLMs
EECS, University of Michigan, Ann Arbor, MI 48105, USA
Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing
Jul 2, 2026Siyuan Li, Youyuan Zhang, Ruitong Liu +2Knowledge Editing Multimodal Large Language Models
Harbin Institute of Technology, Shenzhen, China · Peng Cheng Laboratory · Peking University +1
Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs
May 30, 2026Xin Gao, Cheng Yang, Chufan Shi +1Knowledge Editing Unified Multimodal Models
University of California San Diego · University of Southern California
Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language Models
May 28, 2026Leijiang Gu, Zhen Zeng, Feng Li +2Knowledge Editing Multimodal Large Language Models
1Hefei University of Technology, Hefei, China
Beyond Binary Edits Robust Multimodal Knowledge Editing with Adversarial Subspace Alignment
May 22, 2026Haoyuan Wang, Xiaohao Liu, Jiajie Su +2Multimodal Robustness Adversarial Robustness
Zhejiang University · National University of Singapore · Jiangxi Normal University
Modality-Decoupled Online Recursive Editing
May 19, 2026Siyuan Li, Youyuan Zhang, Fangming Liu +1Continual Learning for LLMs Multimodal Large Language Models
Harbin Institute of Technology, Shenzhen, China. · Peng Cheng Laboratory, China. · Huazhong University of Science and Technology, China.
Uncovering Entity Identity Confusion in Multimodal Knowledge Editing
May 7, 2026Shu Wu, Xiaotian Ye, Xinyu Mou +3Multimodal Grounding Multimodal Large Language Models
New Laboratory of Pattern Recognition (NLPR) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation, Chinese Academy of Sciences · Beijing University of Posts and Telecommunications · School of Artificial Intelligence, University of Chinese Academy of Sciences +3
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs
Apr 20, 2026Tingchao Fu, Wenkai Wang, Fanxiao Li +6Knowledge Editing Multimodal Large Language Models
School of Information Science and Engineering, Yunnan University · School of Software, Yunnan University · 3National University of Singapore +1
MMKU-Bench: A Multimodal Update Benchmark for Diverse Visual Knowledge
Mar 16, 2026Baochen Fu, Yuntao Du, Cheng Chang +6Multimodal Knowledge Editing Multimodal Large Language Models
Shandong University, Jinan, China · Jinzhong Group, Jinan, China.

Oct 14, 2026J/K move · Enter open · S save

Repairing Speech Access After Text Updates with Frozen Affine Fields

Ming-Hao Hsu, Yuxiang Wang, Yingda Shen, Zhizheng Wu

School of Data Science, The Chinese University of Hong Kong, Shenzhen, China

Multimodal Knowledge Editing Speech Language Models Multimodal Large Language Models Spoken QA Causal Interventions in Language Models

Open paper AskPDF arXiv

Speech-capable language models inherit most of their knowledge from text-rich language backbones, and continued model maintenance is likewise dominated by text updates. Knowledge acquired through a text update can nevertheless remain difficult to access when the same query is spoken. We formulate this mismatch as post-update speech access repair, where the knowledge-bearing checkpoint stays frozen and a detachable operator repairs speech-only access in one model pass. We introduce Affine Fields for Interface Repair across Modalities (AFFIRM), which first learns and freezes a base correction for speech hidden states, then adds query-specific corrections with zero mean over the operator-training queries. Paired speech and text states provide the coordinates that condition these corrections on each query. On balanced synthetic-speech PopQA, paired comparisons do not establish a clear advantage for AFFIRM over global SALSA steering or low-rank ReFT interventions under the same frozen single-state constraint. On recorded SLUE-SQA-5 questions with text passages, a full-scale PopQA-fitted AFFIRM operator transfers without refitting and improves ROUGE-L by 0.0941 over its paired No Repair baseline. Low-rank ReFT interventions also transfer positively, whereas the matched SALSA variant falls 0.0707 below its paired baseline. These results show that text acquisition and speech access can diverge after an update and should be verified and repaired separately.