Cover Image

Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dai, Wei, Wang, Haoyu, Chang, Honghao, He, Lijun, Li, Fan, Sun, Jian, Bi, Haixia
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MemOVCD: Training-Free Open-Vocabulary Change Detection via Cross-Temporal Memory Reasoning and Global-Local Adaptive Rectification
by: Kuang, Zuzheng, et al.
Published: (2026)

Invisible Triggers, Visible Threats! Road-Style Adversarial Creation Attack for Visual 3D Detection in Autonomous Driving
by: Wang, Jian, et al.
Published: (2025)

MissMAC-Bench: Building Solid Benchmark for Missing Modality Issue in Robust Multimodal Affective Computing
by: Lin, Ronghao, et al.
Published: (2026)

Learning Fourier shapes to probe the geometric world of deep neural networks
by: Wang, Jian, et al.
Published: (2025)

ADMC: Attention-based Diffusion Model for Missing Modalities Feature Completion
by: Zhang, Wei, et al.
Published: (2025)

Executable Analytic Concepts as the Missing Link Between VLM Insight and Precise Manipulation
by: Sun, Mingyang, et al.
Published: (2025)

Continual Alignment for SAM: Rethinking Foundation Models for Medical Image Segmentation in Continual Learning
by: Wang, Jiayi, et al.
Published: (2025)

Towards Multimodal Video Paragraph Captioning Models Robust to Missing Modality
by: Chen, Sishuo, et al.
Published: (2024)

OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic Workflows
by: Dai, Ruiting, et al.
Published: (2026)

What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs
by: Ren, Zhihan, et al.
Published: (2025)

IMAN: An Adaptive Network for Robust NPC Mortality Prediction with Missing Modalities
by: Huo, Yejing, et al.
Published: (2024)

HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection
by: Cai, Zhaolin, et al.
Published: (2025)

BMIP: Bi-directional Modality Interaction Prompt Learning for VLM
by: Lv, Song-Lin, et al.
Published: (2025)

Hardness-Aware Dynamic Curriculum Learning for Robust Multimodal Emotion Recognition with Missing Modalities
by: Liu, Rui, et al.
Published: (2025)

HumanVLM: Foundation for Human-Scene Vision-Language Model
by: Dai, Dawei, et al.
Published: (2024)

Bootstrapping LLM Robustness for VLM Safety via Reducing the Pretraining Modality Gap
by: Yang, Wenhan, et al.
Published: (2025)

The Agent Use of Agent Beings: Agent Cybernetics Is the Missing Science of Foundation Agents
by: Wang, Xinrun, et al.
Published: (2026)

MuAP: Multi-step Adaptive Prompt Learning for Vision-Language Model with Missing Modality
by: Dai, Ruiting, et al.
Published: (2024)

ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving
by: Nie, Tong, et al.
Published: (2026)

Dynamic VLM-Guided Negative Prompting for Diffusion Models
by: Chang, Hoyeon, et al.
Published: (2025)

Geoint-R1: Formalizing Multimodal Geometric Reasoning with Dynamic Auxiliary Constructions
by: Wei, Jingxuan, et al.
Published: (2025)

EEG-VLM: A Hierarchical Vision-Language Model with Multi-Level Feature Alignment and Visually Enhanced Language-Guided Reasoning for EEG Image-Based Sleep Stage Prediction
by: Qiu, Xihe, et al.
Published: (2025)

Frequency‐Driven Diffusion: A Hierarchical Attention Weighting Framework for Underwater Image Restoration
by: Longxiang Deng, et al.
Published: (2025)

CCSD: Cross-Modal Compositional Self-Distillation for Robust Brain Tumor Segmentation with Missing Modalities
by: Xie, Dongqing, et al.
Published: (2025)

A Clean-graph Backdoor Attack against Graph Convolutional Networks with Poisoned Label Only
by: Dai, Jiazhu, et al.
Published: (2024)

Adaptive Clinical-Aware Latent Diffusion for Multimodal Brain Image Generation and Missing Modality Imputation
by: Zhou, Rong, et al.
Published: (2026)

Diffusion-Based Restoration for Multi-Modal 3D Object Detection in Adverse Weather
by: He, Zhijian, et al.
Published: (2025)

Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solution
by: Ferrini, Francesco, et al.
Published: (2026)

Disentangling and Generating Modalities for Recommendation in Missing Modality Scenarios
by: Kim, Jiwan, et al.
Published: (2025)

GUI-Shift: Enhancing VLM-Based GUI Agents through Self-supervised Reinforcement Learning
by: Gao, Longxi, et al.
Published: (2025)

Enhancing Multimodal Sentiment Analysis for Missing Modality through Self-Distillation and Unified Modality Cross-Attention
by: Weng, Yuzhe, et al.
Published: (2024)

FediLoRA: Practical Federated Fine-Tuning of Foundation Models Under Missing-Modality Constraints
by: Yang, Lishan, et al.
Published: (2025)

CLoE: Expert Consistency Learning for Missing Modality Segmentation
by: Tong, Xinyu, et al.
Published: (2026)

Beyond Hallucinations: A Multimodal-Guided Task-Aware Generative Image Compression for Ultra-Low Bitrate
by: Wang, Kaile, et al.
Published: (2025)

FedRecon: Missing Modality Reconstruction in Heterogeneous Distributed Environments
by: Liu, Junming, et al.
Published: (2025)

Causal Debiasing Medical Multimodal Representation Learning with Missing Modalities
by: Zhu, Xiaoguang, et al.
Published: (2025)

VLM-Guided Iterative Refinement for Surgical Image Segmentation with Foundation Models
by: Lou, Ange, et al.
Published: (2026)

Unifying Visual and Semantic Feature Spaces with Diffusion Models for Enhanced Cross-Modal Alignment
by: Zheng, Yuze, et al.
Published: (2024)

PhysioME: A Robust Multimodal Self-Supervised Framework for Physiological Signals with Missing Modalities
by: Lee, Cheol-Hui, et al.
Published: (2025)

A Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks
by: Dai, Jiazhu, et al.
Published: (2025)