Lorenzo Baraldi

University of Modena and Reggio Emilia — Italy

Computer Science · Physical Sciences

29h-index3.1kcitations202works4.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Multimodal Machine Learning Applications(92), Advanced Image and Video Retrieval Techniques(73), Domain Adaptation and Few-Shot Learning(34), Human Pose and Action Recognition(31), Video Analysis and Summarization(31)

Publications197 total

MATE: Multimodal Agent that Talks and Empathizes
Lecture notes in computer science·2026
SVGauge: Towards Human-Aligned Evaluation for SVG Generation
Lecture notes in computer science·2026
ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering
arXiv (Cornell University)·2025Open Access
The Safety Challenge of World Models for Embodied AI Agents: A Review
arXiv (Cornell University)·2025Open Access
Tracing Information Flow in LLaMA Vision: A Step Toward Multimodal Understanding
Lecture notes in computer science·2025· 1 cited
Recurrence Meets Transformers for Universal Multimodal Retrieval
arXiv (Cornell University)·2025Open Access
Mitigating Hallucinations in Multimodal LLMs via Object-aware Preference Optimization
arXiv (Cornell University)·2025Open Access
Augmenting and mixing Transformers with synthetic data for image captioning
Image and Vision Computing·2025Open Access
Temperature Matters: Enhancing Watermark Robustness Against Paraphrasing Attacks
arXiv (Cornell University)·2025Open Access
Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval
2025· 3 cited
Hyperbolic Safety-Aware Vision-Language Models
2025· 2 cited
Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering
2025· 5 cited
RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors
arXiv (Cornell University)·2025Open Access
What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models
arXiv (Cornell University)·2025Open Access
Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Prefilling Attack
arXiv (Cornell University)·2025Open Access
LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning
arXiv (Cornell University)·2025Open Access
Multimodal Emotion Recognition in Conversation via Possible Speaker’s Audio and Visual Sequence Selection
2025· 3 cited
Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval
ArXiv.org·2025Open Access
Semantically Conditioned Prompts for Visual Recognition Under Missing Modality Scenarios
2025· 1 cited
Perceive. Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries
2025
page 1 of 10Next →

Frequent Co-authors

Rita Cucchiara(44), Marcella Cornia(35), Costantino Grana(10), Giuseppe Serra(9), Matteo Stefanini(7), Federico Bolelli(7), Silvia Cascianelli(6), Sara Sarto(6), Federico Landi(5), Manuele Barraco(5), Massimiliano Corsini(5), Federico Cocchi(3), Nicholas Moratelli(3), Giuseppe Fiameni(2), Francesco Paci(2), Luca Benini(2), Samuele Poppi(2), Davide Caffagni(2), Stefano Pini(2), Michele Cancilla(2)