Rita Cucchiara

Full Professor@Università di modena e reggio emilia·意大利·OpenReview

研究方向

Multimodal LLMs · Multimodal Retrieval · Retrieval-Augmented Generation · Responsible AI · Fake Data Analysis · Unlearning · Image Segmentation · Open Vocabulary Segmentation · Tracking · Pose Estimation · People Detection · Surveillance · Computer Vision · Motion Analysis · Image Classification

5.0

Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals

ICLR 2026Poster

5.0

Rethinking Expressivity and Degradation-Awareness in Attention for All-in-One Blind Image Restoration

ICLR 2026Poster

3.3

RAID: A Benchmark Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors

ICLR 2026Withdrawn

2.4

Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling

合作者 (20)

Rita Cucchiara

Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals

Rethinking Expressivity and Degradation-Awareness in Attention for All-in-One Blind Image Restoration

RAID: A Benchmark Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors

Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling

A Second-Order Perspective on Model Compositionality and Incremental Learning

DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection

Causal Graphical Models for Vision-Language Compositional Understanding