17 papers
The First EgoCross Challenge at EgoVis 2026: Cross-Domain Egocentric Video Question Answering
Yuqian Fu, Tianwen Qian, Yanjun Li +30
EgoCross is a cross-domain egocentric video question answering benchmark designed to evaluate whether multimodal large language models can generalize beyond common daily-life scena…
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…
DataComp-VLM: Improved Open Datasets for Vision-Language Models
Matteo Farina, Vishaal Udandarao, Thao Nguyen +34
Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curat…
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…
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
Selim Kuzucu, Alessio Tonioni, Vasile Lup +3
Large Vision-Language Models (LVLMs) map visual inputs into dense token sequences, imposing a quadratic computational bottleneck for inference. Elastic visual-token compression add…
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…