Image de couverture de livre

Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Oh, Youngtaek, Cho, Jae Won, Kim, Dong-Jin, Kweon, In So, Kim, Junmo
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence 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

Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition
par: Oh, Youngtaek, et autres
Publié: (2024)

ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search
par: Kim, Myungchul, et autres
Publié: (2026)

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
par: Kim, Sanghwan, et autres
Publié: (2024)

Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models
par: Kim, Donghoon, et autres
Publié: (2024)

MATE: Meet At The Embedding -- Connecting Images with Long Texts
par: Jang, Young Kyun, et autres
Publié: (2024)

IWP: Token Pruning as Implicit Weight Pruning in Large Vision Language Models
par: Lee, Dong-Jae, et autres
Publié: (2026)

Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
par: Qiao, Yuxuan, et autres
Publié: (2024)

MTMMC: A Large-Scale Real-World Multi-Modal Camera Tracking Benchmark
par: Woo, Sanghyun, et autres
Publié: (2024)

ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object
par: Zhang, Chenshuang, et autres
Publié: (2024)

Text-to-image Diffusion Models in Generative AI: A Survey
par: Zhang, Chenshuang, et autres
Publié: (2023)

Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs
par: Hong, Weihao, et autres
Publié: (2026)

Video Inference for Human Mesh Recovery with Vision Transformer
par: Cho, Hanbyel, et autres
Publié: (2025)

VLP: A Survey on Vision-Language Pre-training
par: Chen, Feilong, et autres
Publié: (2022)

Bridging the Missing-Modality Gap: Improving Text-Only Calibration of Vision Language Models
par: Kim, Mingyeong, et autres
Publié: (2026)

EVE: Efficient Vision-Language Pre-training with Masked Prediction and Modality-Aware MoE
par: Chen, Junyi, et autres
Publié: (2023)

TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
par: Patel, Maitreya, et autres
Publié: (2024)

Anatomical Structure-Guided Medical Vision-Language Pre-training
par: Li, Qingqiu, et autres
Publié: (2024)

Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image Classification
par: Ye, Yaoqin, et autres
Publié: (2024)

MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language Models
par: Miao, Yongzhu, et autres
Publié: (2023)

Revisit What You See: Revealing Visual Semantics in Vision Tokens to Guide LVLM Decoding
par: Cho, Beomsik, et autres
Publié: (2025)

LinguDistill: Recovering Linguistic Ability in Vision-Language Models via Selective Cross-Modal Distillation
par: Irawan, Patrick Amadeus, et autres
Publié: (2026)

Pretraining Vision-Language Model for Difference Visual Question Answering in Longitudinal Chest X-rays
par: Cho, Yeongjae, et autres
Publié: (2024)

Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
par: Hur, Jiwan, et autres
Publié: (2024)

Leveraging Vision-Language Pre-training for Human Activity Recognition in Still Images
par: Mahanta, Cristina, et autres
Publié: (2025)

Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
par: Zhang, Chenshuang, et autres
Publié: (2025)

Shakti-VLMs: Scalable Vision-Language Models for Enterprise AI
par: Shakhadri, Syed Abdul Gaffar, 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)

HyperWalker: Dynamic Hypergraph-Based Deep Diagnosis for Multi-Hop Clinical Modeling across EHR and X-Ray in Medical VLMs
par: Yang, Yuezhe, et autres
Publié: (2026)

DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset
par: Lee, Young-Jun, et autres
Publié: (2022)

Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
par: Shen, Yifan, et autres
Publié: (2025)

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates
par: Ahn, Jaewoo, et autres
Publié: (2025)

Evaluating Linguistic Capabilities of Multimodal LLMs in the Lens of Few-Shot Learning
par: Dogan, Mustafa, et autres
Publié: (2024)

Superpixel Semantics Representation and Pre-training for Vision-Language Task
par: Zhang, Siyu, et autres
Publié: (2023)

Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge
par: Lee, Young-Jun, et autres
Publié: (2024)

RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability
par: Park, Jonggwon, et autres
Publié: (2025)

GeoX: Geometric Problem Solving Through Unified Formalized Vision-Language Pre-training
par: Xia, Renqiu, et autres
Publié: (2024)

Frequency-Aware Token Reduction for Efficient Vision Transformer
par: Lee, Dong-Jae, et autres
Publié: (2025)

Towards Understanding Dual BN In Hybrid Adversarial Training
par: Zhang, Chenshuang, et autres
Publié: (2024)

Natural Language Inference Improves Compositionality in Vision-Language Models
par: Cascante-Bonilla, Paola, et autres
Publié: (2024)

An Explainable Biomedical Foundation Model via Large-Scale Concept-Enhanced Vision-Language Pre-training
par: Nie, Yuxiang, et autres
Publié: (2025)