collaborators

8 papers

cs.CV2026

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…

cs.CV2026

Segmenting, Fast and Slow: Real-Time Open-Vocabulary Video Instance Segmentation with Dual-Path Processing

Luca Barsellotti, Martin Sundermeyer, Mattia Segu +5

Object-centric models inspired by DETR have become the dominant paradigm for open-vocabulary video instance segmentation (OV-VIS). While recent efforts have reduced the computation…

cs.CV2026

FINER: MLLMs Hallucinate under Fine-grained Negative Queries

Rui Xiao, Sanghwan Kim, Yongqin Xian +2

Multimodal large language models (MLLMs) struggle with hallucinations, particularly with fine-grained queries, a challenge underrepresented by existing benchmarks that focus on coa…

cs.CV2025

MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning

Mattia Segu, Marta Tintore Gazulla, Yongqin Xian +2

Scaling up model size and training data has advanced foundation models for instance-level perception, achieving state-of-the-art in-domain and zero-shot performance across object d…

cs.CV2025

UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint

Enis Simsar, Alessio Tonioni, Yongqin Xian +2

We propose an unsupervised instruction-based image editing approach that removes the need for ground-truth edited images during training. Existing methods rely on supervised learni…

cs.CV2025

Active Data Curation Effectively Distills Large-Scale Multimodal Models

Vishaal Udandarao, Nikhil Parthasarathy, Muhammad Ferjad Naeem +6

Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. Prior works have explored ever more complex KD strategies involving diffe…