ProjLens shows that backdoor parameters in MLLMs are encoded in low-rank subspaces of the projector and that embeddings shift toward the target direction with magnitude linear in input norm, activating only on poisoned samples.
Explainable and interpretable multimodal large language models: A comprehensive survey
7 Pith papers cite this work, alongside 10 external citations. Polarity classification is still indexing.
7
Pith papers citing it
10
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
UHR-BAT is a budget-aware framework that uses text-guided multi-scale importance estimation plus region-wise preserve and merge strategies to compress visual tokens in ultra-high-resolution remote sensing vision-language models.
An Explicit Logic Channel of LLM, VFM and probabilistic inference validates and improves zero-shot MLLMs via Consistency Rate without ground-truth labels.
Introduces 3D-CBM framework mapping raw 3D inputs to multi-tiered interpretable concepts, achieving 88.8% concept accuracy and test-time intervention on PartNet and ShapeNet.
HONES ranks feed-forward neurons by their causal contributions from task-relevant attention heads and uses lightweight scaling to steer performance on multiple vision-language tasks.
A position paper argues that post-hoc XAI explanations are unfaithful and paradoxical, proposing a shift to expert-based verification and certification of AI systems.
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.
citing papers explorer
-
ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety
ProjLens shows that backdoor parameters in MLLMs are encoded in low-rank subspaces of the projector and that embeddings shift toward the target direction with magnitude linear in input norm, activating only on poisoned samples.
-
UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing
UHR-BAT is a budget-aware framework that uses text-guided multi-scale importance estimation plus region-wise preserve and merge strategies to compress visual tokens in ultra-high-resolution remote sensing vision-language models.
-
Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks
An Explicit Logic Channel of LLM, VFM and probabilistic inference validates and improves zero-shot MLLMs via Consistency Rate without ground-truth labels.
-
3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling
Introduces 3D-CBM framework mapping raw 3D inputs to multi-tiered interpretable concepts, achieving 88.8% concept accuracy and test-time intervention on PartNet and ShapeNet.
-
From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models
HONES ranks feed-forward neurons by their causal contributions from task-relevant attention heads and uses lightweight scaling to steer performance on multiple vision-language tasks.
-
Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions
A position paper argues that post-hoc XAI explanations are unfaithful and paradoxical, proposing a shift to expert-based verification and certification of AI systems.
-
Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning
Position paper claims multimodal LLMs can significantly advance scientific reasoning and proposes a four-stage roadmap plus challenges and suggestions.