activity
20212026
collaborators
Showing cs.CVShow all

21 papers · 1 filter

cs.CV2026

Editing Everything Everywhere All at Once

Fabio Quattrini, Carmine Zaccagnino, Enis Simsar +4

Editing multiple elements of an image in a single forward pass is a practical alternative to multi-turn image manipulation, offering improved efficiency and potentially better harm…

cs.CV2026

FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision--Language Generation

Eric Tillmann Bill, Enis Simsar, Alessio Tonioni +1

Modern text-to-image diffusion models encode rich visual priors, but expose them only through one-way text-conditioned generation. Existing unified vision--language models derived…

cs.CV2026

Shifting the Breaking Point of Flow Matching for Multi-Instance Editing

Carmine Zaccagnino, Fabio Quattrini, Enis Simsar +4

Flow matching models have recently emerged as an efficient alternative to diffusion, especially for text-guided image generation and editing, offering faster inference through cont…

cs.CV2025

FOCUS: Optimal Control for Multi-Entity World Modeling in Text-to-Image Generation

Eric Tillmann Bill, Enis Simsar, Thomas Hofmann

Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-entity scenes, often exhibiting attribute leakage, identity entanglement, and subject omissions. W…

cs.CV2025

RefAM: Attention Magnets for Zero-Shot Referral Segmentation

Anna Kukleva, Enis Simsar, Alessio Tonioni +4

Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models, often at the cost of additional…

cs.CV2025

JEDI: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models

Eric Tillmann Bill, Enis Simsar, Thomas Hofmann

We introduce JEDI, a test-time adaptation method that enhances subject separation and compositional alignment in diffusion models without requiring retraining or external supervisi…