N. Sebe

DIME: Scaling Facial Representation Learning via Differential Masked Autoencoding

Hao Yu, Haoyu Chen, Hui Wei +3

Scaling up data and model capacity has driven substantial progress in visual representation learning. However, conventional pretext tasks exhibit diminishing returns on fine-graine…

Localize Any Object in X-Ray Security Scans without Human Annotation

Yaqi Cai, Mingxuan Liu, Lorenzo Vaquero +5

Universal object localization in X-ray security inspection is critical for automated threat detection in safety-critical venues. However, unlike everyday RGB images that dominate w…

Constant-Curvature Sliced Gromov-Wasserstein for Heterogeneous Cross-Curvature Alignment

Shanglin Li, Wenjing Lu, Muyang Li +2

Recent advances in representation learning have highlighted the utility of constant-curvature models, such as hyperbolic and spherical spaces, for modeling complex data. Mixed-curv…

LieBN: Batch Normalization over Lie Groups

Ziheng Chen, Yue Song, Rui Wang +2

Manifold-valued measurements are prevalent in various machine learning tasks. Recent advances have extended Deep Neural Networks (DNNs) to operate on manifolds. These extensions ha…

cs.AI2026

Harnessing Textual Refusal Directions for Multimodal Safety

Moreno D'Incà, Nicu Sebe, Massimiliano Mancini

Safety in Multimodal Large Language Models (MLLMs) depends on unsafe multimodal data for post-training alignment or activation steering. However, such data is hard to collect, must…

Riemannian Networks over Full-Rank Correlation Matrices

Ziheng Chen, Xiaojun Wu, Bernhard Schölkopf +1

Representations on the Symmetric Positive Definite (SPD) manifold have garnered significant attention across different applications. In contrast, the manifold of full-rank correlat…

Hallucination Early Detection in Diffusion Models

Federico Betti, Lorenzo Baraldi, Rita Cucchiara +1

Text-to-Image generation has seen significant advancements in output realism with the advent of diffusion models. However, diffusion models encounter difficulties when tasked with…

The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results

Xingyu Qiu, Yuqian Fu, Jiawei Geng +70

Cross-domain few-shot object detection (CD-FSOD) remains a challenging problem for existing object detectors and few-shot learning approaches, particularly when generalizing across…

Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language Models

Songlong Xing, Weijie Wang, Zhengyu Zhao +3

Despite their impressive zero-shot abilities, vision-language models such as CLIP have been shown to be susceptible to adversarial attacks. To enhance its adversarial robustness, r…

The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery

Haiyang Zheng, Nan Pu, Yaqi Cai +4

Generalized Category Discovery (GCD) leverages labeled data to categorize unlabeled samples from known or unknown classes. Most previous methods jointly optimize supervised and uns…

Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosis

Chen Feng, Zhuo Zhi, Zhao Huang +5

Statistically consistent methods based on the noise transition matrix ( $T$ ) offer a theoretically grounded solution to Learning with Noisy Labels (LNL), with guarantees of converge…

Open-Vocabulary Domain Generalization in Urban-Scene Segmentation

Dong Zhao, Qi Zang, Nan Pu +3

Domain Generalization in Semantic Segmentation (DG-SS) aims to enable segmentation models to perform robustly in unseen environments. However, conventional DG-SS methods are restri…

Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation

Chonghua Lv, Dong Zhao, Shuang Wang +4

Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while negle…

Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving

Jiangxin Sun, Feng Xue, Teng Long +4

With advances in imitation learning (IL) and large-scale driving datasets, end-to-end autonomous driving (E2E-AD) has made great progress recently. Currently, IL-based methods have…

Hyperbolic Busemann Neural Networks

Ziheng Chen, Bernhard Schölkopf, Nicu Sebe

Hyperbolic spaces provide a natural geometry for representing hierarchical and tree-structured data due to their exponential volume growth. To leverage these benefits, neural netwo…

Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation

Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu +2

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO…

A Unified Masked Jigsaw Puzzle Framework for Vision and Language Models

Weixin Ye, Wei Wang, Yahui Liu +5

In federated learning, Transformer, as a popular architecture, faces critical challenges in defending against gradient attacks and improving model performance in both Computer Visi…

In defense of the two-stage framework for open-set domain adaptive semantic segmentation

Wenqi Ren, Weijie Wang, Meng Zheng +4

Open-Set Domain Adaptation for Semantic Segmentation (OSDA-SS) presents a significant challenge, as it requires both domain adaptation for known classes and the distinction of unkn…

POCI-Diff: 3D-Layout Guided Diffusion for Controllable Synthetic Surveillance Data Generation

Andrea Rigo, Luca Stornaiuolo, Weijie Wang +3

Training robust visual surveillance models requires large-scale datasets with precise spatial annotations, yet collecting real surveillance data is costly, privacy-sensitive, and o…

Open-World Deepfake Attribution via Confidence-Aware Asymmetric Learning

Haiyang Zheng, Nan Pu, Wenjing Li +3

The proliferation of synthetic facial imagery has intensified the need for robust Open-World DeepFake Attribution (OW-DFA), which aims to attribute both known and unknown forgeries…

Wasserstein-Aligned Hyperbolic Multi-View Clustering

Rui Wang, Yuting Jiang, Xiaoqing Luo +3

Multi-view clustering (MVC) aims to uncover the latent structure of multi-view data by learning view-common and view-specific information. Although recent studies have explored hyp…

Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding

Yue Li, Qi Ma, Runyi Yang +8

While 3DGS has emerged as a high-fidelity scene representation, encoding rich, general-purpose features directly from its primitives remains under-explored. We address this gap by…

Loomis Painter: Learning Painting Processes by Reversing Image-to-Video Generation

Markus Pobitzer, Chang Liu, Chenyi Zhuang +3

Step-by-step painting tutorials are used for learning artistic techniques, but existing video resources lack interactivity and personalization. While recent generative models have…