11 papers
Kinematics-Centric Continuous Sign Language Retrieval with Gloss-Guided Boundary-Aware Alignment
Chang Liu, Ke Han, Davide Talon +2
Sign language-text alignment remains a fundamental challenge for text-driven sign language understanding. Existing methods predominantly rely on appearance-heavy RGB representation…
Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning
Lorenzo Orsingher, Thomas De Min, Massimiliano Mancini +2
Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations. To evaluate unlearning effectiveness in multimodal lar…
Personalizing MLLMs via Reinforced Multimodal Reference Game
Deepayan Das, Davide Talon, Yiming Wang +2
Personalizing Multimodal Large Language Models (MLLMs) aims to recognize users' unique concepts from visual data and provide personalized responses. Although prior work has shown t…
Thinking Past the Answer: Evaluating Harmful Overthinking in Large Reasoning Models
Simone Caldarella, Davide Talon, Rahaf Aljundi +2
Large Reasoning Models (LRMs) improve performance by generating explicit intermediate reasoning traces through increased test-time compute, yet the assumption that longer reasoning…
How to Take a Memorable Picture? Empowering Users with Actionable Feedback
Francesco Laiti, Davide Talon, Jacopo Staiano +1
Image memorability, i.e., how likely an image is to be remembered, has traditionally been studied in computer vision either as a passive prediction task, with models regressing a s…
Multi-Level Conditioning by Pairing Localized Text and Sketch for Fashion Image Generation
Ziyue Liu, Davide Talon, Federico Girella +5
Sketches offer designers a concise yet expressive medium for early-stage fashion ideation by specifying structure, silhouette, and spatial relationships, while textual descriptions…
Evaluating Attribute Confusion in Fashion Text-to-Image Generation
Ziyue Liu, Federico Girella, Yiming Wang +1
Despite the rapid advances in Text-to-Image (T2I) generation models, their evaluation remains challenging in domains like fashion, involving complex compositional generation. Recen…
LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing
Federico Girella, Davide Talon, Ziyue Liu +3
Fashion design is a complex creative process that blends visual and textual expressions. Designers convey ideas through sketches, which define spatial structure and design elements…
Seeing the Abstract: Translating the Abstract Language for Vision Language Models
Davide Talon, Federico Girella, Ziyue Liu +2
Natural language goes beyond dryly describing visual content. It contains rich abstract concepts to express feeling, creativity and properties that cannot be directly perceived. Ye…
Training-Free Personalization via Retrieval and Reasoning on Fingerprints
Deepayan Das, Davide Talon, Yiming Wang +2
Vision Language Models (VLMs) have lead to major improvements in multimodal reasoning, yet they still struggle to understand user-specific concepts. Existing personalization method…
One VLM to Keep it Learning: Generation and Balancing for Data-free Continual Visual Question Answering
Deepayan Das, Davide Talon, Massimiliano Mancini +2
Vision-Language Models (VLMs) have shown significant promise in Visual Question Answering (VQA) tasks by leveraging web-scale multimodal datasets. However, these models often strug…