MSLA is the first physically deployable attack that uses adversarial lighting to break semantic alignment in VLMs such as CLIP, LLaVA, and BLIP, causing classification failures and hallucinations in real scenes.
Title resolution pending
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 11roles
background 3polarities
background 3representative citing papers
CrossMPI steers both visual and textual interpretations in LVLMs through image-only perturbations by optimizing in hidden-state space at selected middle layers with distance-based budget allocation.
A wrinkle-field perturbation method creates photorealistic non-rigid image changes that degrade state-of-the-art VLMs on image captioning and VQA more effectively than prior baselines.
TGQ-Former uses metadata-guided hybrid queries and dual-gated modulation to improve visual token selection in multimodal e-commerce retrieval, raising average Hit Rate@100 by 6.04% over baselines.
PRISM learns shared sentiment prototypes to enable structured cross-modal comparison and dynamic modality reweighting in multimodal sentiment analysis, outperforming baselines on three benchmark datasets.
CoME-VL fuses contrastive and self-supervised vision encoders via entropy-guided multi-layer aggregation and RoPE cross-attention to improve vision-language model performance on benchmarks.
A diffusion model with dynamic modality gating and cross-modal mutual learning restores missing features in VLMs bi-directionally while preserving the original model's generalization.
SKG-VLA models each complaint as a structured scene via a Scene Knowledge Graph to improve policy-grounded multimodal reasoning and decision accuracy.
CurEvo integrates curriculum guidance into self-evolution to structure autonomous improvement of video understanding models, yielding gains on VideoQA benchmarks.
citing papers explorer
-
Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks
MSLA is the first physically deployable attack that uses adversarial lighting to break semantic alignment in VLMs such as CLIP, LLaVA, and BLIP, causing classification failures and hallucinations in real scenes.
-
A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation
CrossMPI steers both visual and textual interpretations in LVLMs through image-only perturbations by optimizing in hidden-state space at selected middle layers with distance-based budget allocation.
-
When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models
A wrinkle-field perturbation method creates photorealistic non-rigid image changes that degrade state-of-the-art VLMs on image captioning and VQA more effectively than prior baselines.
-
Text-Guided Visual Representation Learning for Robust Multimodal E-Commerce Recommendation
TGQ-Former uses metadata-guided hybrid queries and dual-gated modulation to improve visual token selection in multimodal e-commerce retrieval, raising average Hit Rate@100 by 6.04% over baselines.
-
Learning Shared Sentiment Prototypes for Adaptive Multimodal Sentiment Analysis
PRISM learns shared sentiment prototypes to enable structured cross-modal comparison and dynamic modality reweighting in multimodal sentiment analysis, outperforming baselines on three benchmark datasets.
-
CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning
CoME-VL fuses contrastive and self-supervised vision encoders via entropy-guided multi-layer aggregation and RoPE cross-attention to improve vision-language model performance on benchmarks.
-
Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration
A diffusion model with dynamic modality gating and cross-modal mutual learning restores missing features in VLMs bi-directionally while preserving the original model's generalization.
-
SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making
SKG-VLA models each complaint as a structured scene via a Scene Knowledge Graph to improve policy-grounded multimodal reasoning and decision accuracy.
-
CurEvo: Curriculum-Guided Self-Evolution for Video Understanding
CurEvo integrates curriculum guidance into self-evolution to structure autonomous improvement of video understanding models, yielding gains on VideoQA benchmarks.
- Latent Denoising Improves Visual Alignment in Large Multimodal Models
- Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs