Image de couverture de livre

PostAlign: Multimodal Grounding as a Corrective Lens for MLLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Yixuan, Zhang, Yang, Wu, Jian, Torr, Philip, Gu, Jindong
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models
par: Luo, Haochen, et autres
Publié: (2024)

Influencer Backdoor Attack on Semantic Segmentation
par: Lan, Haoheng, et autres
Publié: (2023)

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
par: Li, Hang, et autres
Publié: (2023)

As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?
par: Hu, Anjun, et autres
Publié: (2024)

Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution
par: Liu, Fengyuan, et autres
Publié: (2024)

From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images
par: Chen, Yiming, et autres
Publié: (2025)

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models
par: Xing, Songlong, et autres
Publié: (2026)

Visual Jigsaw Post-Training Improves MLLMs
par: Wu, Penghao, et autres
Publié: (2025)

Improving Adversarial Transferability in MLLMs via Dynamic Vision-Language Alignment Attack
par: Gu, Chenhe, et autres
Publié: (2025)

Localizing Events in Videos with Multimodal Queries
par: Zhang, Gengyuan, et autres
Publié: (2024)

Learning Visual Prompts for Guiding the Attention of Vision Transformers
par: Rezaei, Razieh, et autres
Publié: (2024)

True Multimodal In-Context Learning Needs Attention to the Visual Context
par: Chen, Shuo, et autres
Publié: (2025)

Improving Adversarial Transferability via Model Alignment
par: Ma, Avery, et autres
Publié: (2023)

AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
par: Liu, Runtao, et autres
Publié: (2024)

DetToolChain: A New Prompting Paradigm to Unleash Detection Ability of MLLM
par: Wu, Yixuan, et autres
Publié: (2024)

SpaceMind++: Toward Allocentric Cognitive Maps for Spatially Grounded Video MLLMs
par: Gu, Bo, et autres
Publié: (2026)

GroundingME: Exposing the Visual Grounding Gap in MLLMs through Multi-Dimensional Evaluation
par: Li, Rang, et autres
Publié: (2025)

Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning?
par: Chen, Shuo, et autres
Publié: (2023)

Open Eyes, Then Reason: Fine-grained Visual Mathematical Understanding in MLLMs
par: Zhang, Shan, et autres
Publié: (2025)

Latent Guard: a Safety Framework for Text-to-image Generation
par: Liu, Runtao, et autres
Publié: (2024)

Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
par: Gao, Kuofeng, et autres
Publié: (2024)

Energy-Latency Manipulation of Multi-modal Large Language Models via Verbose Samples
par: Gao, Kuofeng, et autres
Publié: (2024)

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference
par: Zhao, Xiangyu, et autres
Publié: (2025)

CodePercept: Code-Grounded Visual STEM Perception for MLLMs
par: Guan, Tongkun, et autres
Publié: (2026)

Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark
par: Hao, Yunzhuo, et autres
Publié: (2025)

Self-Ensemble Post Learning for Noisy Domain Generalization
par: Lu, Wang, et autres
Publié: (2025)

The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs
par: Anvekar, Tejas, et autres
Publié: (2025)

AlignedGen: Aligning Style Across Generated Images
par: Zhang, Jiexuan, et autres
Publié: (2025)

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs
par: Zhang, Huanyu, et autres
Publié: (2025)

RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs
par: Li, Hongliang, et autres
Publié: (2025)

Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning
par: Zhang, Bob, et autres
Publié: (2025)

Seeing is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding
par: Guo, Pinxue, et autres
Publié: (2025)

MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs
par: Xu, Yunqiu, et autres
Publié: (2024)

Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs
par: Tong, Jintao, et autres
Publié: (2025)

Multimodal Pragmatic Jailbreak on Text-to-image Models
par: Liu, Tong, et autres
Publié: (2024)

Minimalist Concept Erasure in Generative Models
par: Zhang, Yang, et autres
Publié: (2025)

STORM: Benchmarking Visual Rating of MLLMs with a Comprehensive Ordinal Regression Dataset
par: Wang, Jinhong, et autres
Publié: (2025)

ExpAlign: Expectation-Guided Vision-Language Alignment for Open-Vocabulary Grounding
par: Hu, Junyi, et autres
Publié: (2026)

MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models
par: Liu, Xin, et autres
Publié: (2023)

SliceLens: Fine-Grained and Grounded Error Slice Discovery for Multi-Instance Vision Tasks
par: Zhang, Wei, et autres
Publié: (2025)