arXiv AI June 17, 2026 By Tingchao Fu, Wenkai Wang, Fanxiao Li, Huadong Zhang, Jinhong Zhang, Dayang Li, Yunyun Dong, Renyang Liu, Wei Zhou

Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs

Read the original on arXiv AI →

arXiv:2606. 17057v1 Announce Type: cross Abstract: Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal Large Language Models (MLLMs), we find that current paradigms still suffer from an important yet remain underexplored issue : editing decoupling failure, where entity-related knowledge can be updated when the model is triggered by multimodal inputs (text--image query pairs), however, it often reverts to outdated pre-edit facts when the paired inputs are split into unimodal ones.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jul 3

Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing

arXiv:2607. 01978v1 Announce Type: new Abstract: 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.

By Siyuan Li, Youyuan Zhang, Ruitong Liu, Junxi Wang, Jing Li

llms multimodal benchmarks

arXiv AI

Jun 12

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs

arXiv:2606. 12809v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are trained on massive multimodal data, making data unlearning increasingly important as data owners may request the removal of specific content.

By He Li, Haoang Chi, Qizhou Wang, Yunxin Mao, Zhiheng Zhang, Jie Tan, Tongliang Liu, Wenjing Yang, Bo Han

llms multimodal benchmarks safety

arXiv AI

Jun 8

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

arXiv:2602. 07026v3 Announce Type: replace-cross Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions.

By Xiaomin Yu, Yi Xin, Yuhui Zhang, Wenjie Zhang, Chonghan Liu, Hanzhen Zhao, Chen Liu, Xiaoxing Hu, Ziyue Qiao, Hao Tang, Xiaobin Hu, Chengwei Qin, Hui Xiong, Yu Qiao, Shuicheng Yan

llms rag fine-tuning multimodal safety

Hugging Face Trending Papers

Aug 4

Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation

Vision-Language Models (VLMs), like Large Language Models (LLMs), may memorize sensitive, copyrighted, or harmful knowledge from their pretraining corpora. Removing such knowledge is essential for building trustworthy AI systems.

llms multimodal benchmarks

arXiv AI

Jun 3

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models

arXiv:2605. 18160v2 Announce Type: replace-cross Abstract: In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrating visual and textual information.

By Xinpeng Dong, Min Zhang, Kairong Han, Xu Tan, Fei Wu, Kun Kuang

llms computer-vision multimodal benchmarks safety

arXiv AI

Jun 2

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition

arXiv:2606. 00959v1 Announce Type: new Abstract: Understanding modality interaction in multimodal large language models (MLLMs) is central to reliable deployment.

By Wanlong Fang, Tianle Zhang, Wen Tao, Alvin Chan

llms multimodal benchmarks safety

Related stories

Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing

MLUBench: A Benchmark for Lifelong Unlearning Evaluation in MLLMs

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning Evaluation

Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition