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.
Title resolution pending
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
years
2026 12verdicts
UNVERDICTED 12representative citing papers
A method using attention head vectors detects and suppresses risky content generation in Diffusion Transformers at inference time.
DAWF introduces isolated identity attribution spaces and selective regional supervision to unify detection, localization, and source tracing for multi-face deepfakes.
OVS-DINO structurally aligns DINO with SAM to revitalize attenuated boundary features, achieving SOTA gains of 2.1% average and 6.3% on Cityscapes in weakly-supervised open-vocabulary segmentation.
Bridge-STG decouples spatio-temporal alignment via semantic bridging and query-guided localization modules to achieve state-of-the-art m_vIoU of 34.3 on VidSTG among MLLM methods.
MARINER is a new benchmark dataset and evaluation framework for fine-grained perception and causal reasoning in open-water scenes using 16,629 images across 63 vessel categories, diverse environments, and maritime incidents.
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.
RCSR is a personalization-friendly federated framework that improves cross-modal retrieval accuracy and stability under missing modalities via semantic routing and adapters.
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.
A new memory system for social robots selectively stores multimodal memories by emotional salience and novelty, achieving 0.506 Spearman correlation in selectivity and up to 13% better Recall@1 in multimodal retrieval.
MESA reduces hallucinations in LVLMs via controlled selective latent intervention that preserves the original token distribution.
A training-free region-aware attention recalibration strategy reduces object hallucinations in LVLMs on CHAIR, POPE, and MME benchmarks while preserving fluency.
citing papers explorer
-
Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding
Bridge-STG decouples spatio-temporal alignment via semantic bridging and query-guided localization modules to achieve state-of-the-art m_vIoU of 34.3 on VidSTG among MLLM methods.