Copertina

Auto-Comp: An Automated Pipeline for Scalable Compositional Probing of Contrastive Vision-Language Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sbrolli, Cristian, Matteucci, Matteo, Yamasaki, Toshihiko
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PolyGen: Fully Synthetic Vision-Language Training via Multi-Generator Ensembles
di: Brusini, Leonardo, et al.
Pubblicazione: (2026)

No Captions, No Problem: Captionless 3D-CLIP Alignment with Hard Negatives via CLIP Knowledge and LLMs
di: Sbrolli, Cristian, et al.
Pubblicazione: (2024)

Can Shape-Infused Joint Embeddings Improve Image-Conditioned 3D Diffusion?
di: Sbrolli, Cristian, et al.
Pubblicazione: (2024)

SCENEFORGE: Enhancing 3D-text alignment with Structured Scene Compositions
di: Sbrolli, Cristian, et al.
Pubblicazione: (2025)

Your Image Generator Is Your New Private Dataset
di: Resmini, Nicolo, et al.
Pubblicazione: (2025)

Neuro-Symbolic Scene Graph Conditioning for Synthetic Image Dataset Generation
di: Savazzi, Giacomo, et al.
Pubblicazione: (2025)

A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation
di: Xiao, Ling, et al.
Pubblicazione: (2026)

Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving
di: Theodoridis, Nikos, et al.
Pubblicazione: (2026)

Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges
di: Catalano, Nico, et al.
Pubblicazione: (2023)

Trust in Vision-Language Models: Insights from a Participatory User Workshop
di: Chiatti, Agnese, et al.
Pubblicazione: (2025)

Data-Driven Prediction of Seismic Intensity Distributions Featuring Hybrid Classification-Regression Models
di: Mizutani, Koyu, et al.
Pubblicazione: (2024)

In-Context Learning Improves Compositional Understanding of Vision-Language Models
di: Nulli, Matteo, et al.
Pubblicazione: (2024)

Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval
di: Xiao, Ling, et al.
Pubblicazione: (2022)

AutoVDC: Automated Vision Data Cleaning Using Vision-Language Models
di: Vasa, Santosh, et al.
Pubblicazione: (2025)

Iterative Self-Improvement of Vision Language Models for Image Scoring and Self-Explanation
di: Tanji, Naoto, et al.
Pubblicazione: (2025)

Language-Guided Invariance Probing of Vision-Language Models
di: Lee, Jae Joong
Pubblicazione: (2025)

Disentanglement and Compositionality of Letter Identity and Letter Position in Variational Auto-Encoder Vision Models
di: Bianchi, Bruno, et al.
Pubblicazione: (2024)

Federated Knowledge Recycling: Privacy-Preserving Synthetic Data Sharing
di: Lomurno, Eugenio, et al.
Pubblicazione: (2024)

CompCap: Improving Multimodal Large Language Models with Composite Captions
di: Chen, Xiaohui, et al.
Pubblicazione: (2024)

AutoLTS: Automating Cycling Stress Assessment via Contrastive Learning and Spatial Post-processing
di: Lin, Bo, et al.
Pubblicazione: (2023)

Probing Perceptual Constancy in Large Vision-Language Models
di: Sun, Haoran, et al.
Pubblicazione: (2025)

Semantic Compositions Enhance Vision-Language Contrastive Learning
di: Aladago, Maxwell, et al.
Pubblicazione: (2024)

PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language Models
di: Yokomizo, Hisayuki, et al.
Pubblicazione: (2026)

AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?
di: Bao, Han, et al.
Pubblicazione: (2024)

No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models
di: Pouget, Angéline, et al.
Pubblicazione: (2024)

Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects
di: Chiatti, Agnese, et al.
Pubblicazione: (2025)

Comp-Attn: Present-and-Align Attention for Compositional Video Generation
di: Zhang, Hongyu, et al.
Pubblicazione: (2025)

Stable Diffusion Dataset Generation for Downstream Classification Tasks
di: Lomurno, Eugenio, et al.
Pubblicazione: (2024)

AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vision-Language Models
di: Metzen, Jan Hendrik, et al.
Pubblicazione: (2023)

Prompting Large Vision-Language Models for Compositional Reasoning
di: Ossowski, Timothy, et al.
Pubblicazione: (2024)

Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey
di: Miyai, Atsuyuki, et al.
Pubblicazione: (2024)

Bias Beyond Demographics: Probing Decision Boundaries in Black-Box LVLMs via Counterfactual VQA
di: Zhao, Zaiying, et al.
Pubblicazione: (2025)

AutoMR: A Universal Time Series Motion Recognition Pipeline
di: Zhang, Likun, et al.
Pubblicazione: (2025)

Probing and Inducing Combinational Creativity in Vision-Language Models
di: Peng, Yongqian, et al.
Pubblicazione: (2025)

HarmoCLIP: Harmonizing Global and Regional Representations in Contrastive Vision-Language Models
di: Zeng, Haoxi, et al.
Pubblicazione: (2025)

POMONAG: Pareto-Optimal Many-Objective Neural Architecture Generator
di: Lomurno, Eugenio, et al.
Pubblicazione: (2024)

VLM-AutoDrive: Post-Training Vision-Language Models for Safety-Critical Autonomous Driving Events
di: Bhat, Mohammad Qazim, et al.
Pubblicazione: (2026)

SDCD: Structure-Disrupted Contrastive Decoding for Mitigating Hallucinations in Large Vision-Language Models
di: Xia, Yuxuan, et al.
Pubblicazione: (2026)

Evading Visual Aphasia: Contrastive Adaptive Semantic Token Pruning for Vision-Language Models
di: Ma, Jie, et al.
Pubblicazione: (2026)

Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach
di: Guan, Jiwei, et al.
Pubblicazione: (2024)