Image de couverture de livre

V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wang, Qidong, Hu, Junjie, Jiang, Ming
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models
par: Wang, Qidong, et autres
Publié: (2026)

SEAM: A Stochastic Benchmark for Multi-Document Tasks
par: Lior, Gili, et autres
Publié: (2024)

SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
par: Tang, Zhenwei, et autres
Publié: (2025)

Large Language Models Are Active Critics in NLG Evaluation
par: Xu, Shuying, et autres
Publié: (2024)

Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach
par: Yang, Jingyuan, et autres
Publié: (2025)

Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models
par: Deng, Ruixuan, et autres
Publié: (2025)

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
par: Marks, Samuel, et autres
Publié: (2024)

OmniV-Med: Scaling Medical Vision-Language Model for Universal Visual Understanding
par: Jiang, Songtao, et autres
Publié: (2025)

CausalVLBench: Benchmarking Visual Causal Reasoning in Large Vision-Language Models
par: Komanduri, Aneesh, et autres
Publié: (2025)

Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
par: Li, Bin, et autres
Publié: (2025)

PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
par: Xing, Long, et autres
Publié: (2024)

Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection
par: Li, Bangzheng, et autres
Publié: (2025)

Incremental Comprehension of Garden-Path Sentences by Large Language Models: Semantic Interpretation, Syntactic Re-Analysis, and Attention
par: Li, Andrew, et autres
Publié: (2024)

Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models
par: Xu, Derong, et autres
Publié: (2024)

Vision Language Models Map Logos to Text via Semantic Entanglement in the Visual Projector
par: Li, Sifan, et autres
Publié: (2025)

SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models
par: Wang, Zekun, et autres
Publié: (2023)

Vision-Language Modeling in PET/CT for Visual Grounding of Positive Findings
par: Huemann, Zachary, et autres
Publié: (2025)

Reinforced Lifelong Editing for Language Models
par: Li, Zherui, et autres
Publié: (2025)

How Well Do LLMs Identify Cultural Unity in Diversity?
par: Li, Jialin, et autres
Publié: (2024)

DFA-RAG: Conversational Semantic Router for Large Language Model with Definite Finite Automaton
par: Sun, Yiyou, et autres
Publié: (2024)

Neuron-Level Sequential Editing for Large Language Models
par: Jiang, Houcheng, et autres
Publié: (2024)

MouSi: Poly-Visual-Expert Vision-Language Models
par: Fan, Xiaoran, et autres
Publié: (2024)

Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
par: Uppaal, Rheeya, et autres
Publié: (2024)

Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts
par: Chen, Qizhou, et autres
Publié: (2024)

Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate
par: Huang, Qidong, et autres
Publié: (2024)

Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
par: Hu, Xiang, et autres
Publié: (2024)

TokenSmith: Streamlining Data Editing, Search, and Inspection for Large-Scale Language Model Training and Interpretability
par: Khan, Mohammad Aflah, et autres
Publié: (2025)

Towards Minimal Causal Representations for Human Multimodal Language Understanding
par: Jiang, Menghua, et autres
Publié: (2025)

FrameEOL: Semantic Frame Induction using Causal Language Models
par: Yano, Chihiro, et autres
Publié: (2025)

SMCLM: Semantically Meaningful Causal Language Modeling for Autoregressive Paraphrase Generation
par: Perełkiewicz, Michał, et autres
Publié: (2025)

FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models
par: Cai, Hengxing, et autres
Publié: (2025)

VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
par: Shahgir, Haz Sameen, et autres
Publié: (2026)

GeoEdit: Geometric Knowledge Editing for Large Language Models
par: Feng, Yujie, et autres
Publié: (2025)

Editing the Mind of Giants: An In-Depth Exploration of Pitfalls of Knowledge Editing in Large Language Models
par: Hsueh, Cheng-Hsun, et autres
Publié: (2024)

Optimizing Multimodal Language Models through Attention-based Interpretability
par: Sergeev, Alexander, et autres
Publié: (2025)

From Attention to Atoms: Spectral Dictionary Learning for Fast, Interpretable Language Models
par: Kiruluta, Andrew
Publié: (2025)

Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit
par: Chen, Qizhou, et autres
Publié: (2024)

VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
par: Huang, Han, et autres
Publié: (2024)

Seeing isn't Hearing: Benchmarking Vision Language Models at Interpreting Spectrograms
par: Loakman, Tyler, et autres
Publié: (2025)

LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editing
par: Wang, Peng, et autres
Publié: (2025)