arXiv Machine Learning July 23, 2026 By Rong Fu, Ziming Wang, Chunlei Meng, Jiekai Wu, Kangan Qian, Hao Zhang, Simon Fong

Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis

Read the original on arXiv Machine Learning →

arXiv:2602. 16144v4 Announce Type: replace-cross Abstract: As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical requirement for privacy compliance and user autonomy.

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

arXiv AI

Jul 10

Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

arXiv:2607. 07907v1 Announce Type: cross Abstract: With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associations that originate from their training data.

By Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu, Vaidehi Patil

llms multimodal benchmarks

arXiv AI

Aug 5

Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations

arXiv:2608. 03611v1 Announce Type: new Abstract: Multimodal Sentiment Analysis (MSA) integrates text, audio, and vision to infer human affect, yet real-world multimodal observations are often incomplete.

By Chunlei Meng, Jacqueline J. Pang, Pengbin Feng, Zhenyu Yu, Chun Ouyang, Zhongxue Gan

nlp multimodal safety

Hugging Face Trending Papers

Jul 7

POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking

Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tasks by jointly training on large-scale textual and visual data, where privacy-sensitive examples could be unintentionally encoded, raising concerns about privacy or copyright violation. To this end, Multi-modality Machine Unlearning (MMU) was proposed as a mitigation that can effectively force MLLMs to forget private information.

llms fine-tuning multimodal benchmarks safety

arXiv AI

Aug 11

Multimodal Federated Learning under Dual-Axis Modality Missingness

arXiv:2608. 09240v1 Announce Type: cross Abstract: Multimodal federated learning (FL) supports collaborative modeling in privacy-sensitive health-sensing and medical settings, but realistic deployments often exhibit dual-axis modality missingness: clients have different modality sets, and individual samples may contain only subsets of the modalities available locally.

By Adiba Orzikulova, Jaehyun Kwak, Jaemin Shin, Yunqi Guo, Xiaomin Ouyang, Guoliang Xing, Steven Euijong Whang, Sung-Ju Lee

multimodal safety

arXiv Machine Learning

Jul 14

Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion

arXiv:2506. 22036v2 Announce Type: replace Abstract: With the increasing multimodal knowledge privatization requirements, multimodal knowledge graphs in different institutes are usually decentralized, lacking of effective collaboration system with both stronger reasoning ability and transmission safety guarantees.

By Ying Zhang, Yu Zhao, Xuhui Sui, Baohang Zhou, Xiangrui Cai, Li Shen, Xiaojie Yuan, Dacheng Tao

rag diffusion efficiency multimodal benchmarks safety

arXiv AI

Aug 6

C$^2$MOE: Consistency and Complementarity-guided Mixture of Experts for Incomplete Multimodal Emotion Learning

arXiv:2608. 04013v1 Announce Type: cross Abstract: Recent advances in Multimodal Emotion Recognition in Conversations (MERC) highlight its reliance on complete multimodal inputs.

By Yuntao Shou, Tao Meng, Wei Ai, Keqin Li

multimodal benchmarks

Related stories

Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks

Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations

POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking

Multimodal Federated Learning under Dual-Axis Modality Missingness

Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion

C$^2$MOE: Consistency and Complementarity-guided Mixture of Experts for Incomplete Multimodal Emotion Learning