The paper addresses the challenge of calibrating membership inference attacks in a one‑round setting where only a single trained model is available. It proposes using neighboring data points of the target to approximate the calibration that reference models normally provide, and demonstrates that querying these neighbors—especially against early training checkpoints—enhances the membership signal. Experiments on three image classification datasets and training setups show that this neighbor‑based approach yields strong attack performance without extra training cost.
By Francesco Rita, Jie Zhang, Florian Tram\`er
arXiv:2609.32352v2 Announce Type: replace-cross
Abstract: Vision-language models (VLMs) have shown increasing potential for medical image understanding, yet their capabilities in ophthalmic imaging r...
By Gujie Shao, Zixun Xie, Xuechun Xing, Ruixiang Wang, Ziyun Lan, Yanlin Qi, Gangyi Zhang, Yuxin Yang, Dawei Li, Haiming Tang
GA-EIRFS is a detector‑agnostic sampling strategy that augments frequency‑based repeat‑factor sampling with a fixed geometry score derived from point count, surface‑normal entropy, and surface coverage. It only alters frame‑sampling probabilities, leaving the underlying detector and inference pipeline unchanged. Experiments on nuScenes show consistent improvements in mean average precision and the nuScenes detection score across multiple seeds and backbones, with notable gains for rare classes such as bicycles.
By Taufiq Ahmed, Constantino \'Alvarez Casado, Daniel Herrera Castro, Sasan Sharifipour, Abhishek Kumar, Miguel Bordallo L\'opez
arXiv:2609.38180v1 Announce Type: new
Abstract: Existing 3D part decomposition methods do not necessarily partition the original shape into non-overlapping parts that collectively cover the entire sh...
By Hao-Tang Tsui, Yu-Rou Tuan, Xiaoxuan Ma, Nicolas Ugrinovic, Takaaki Shiratori, Kris Kitani
EviViT is a lightweight attachment for pretrained vision transformers that learns where to focus detail in high‑resolution images. It uses human visual‑search traces to supervise a question‑conditioned evidence density, guiding regional re‑reading and efficient visual token allocation. The method connects regional features to the global scene via a sparse, coordinate‑aware bridge, improving fine‑grained accuracy across nine host models while using fewer tokens than global‑only processing.
By Yaoxin Niu, Zhangquan Chen, Yang Zhang, Xiang An, Zhumei Wang, Chih-Ting Liao, Hongkun Cao, Ruqi Huang
arXiv:2609.36532v1 Announce Type: cross
Abstract: In multiclass probabilistic prediction, Utility Calibration (UC), which focuses auditing on specified utilities, has recently received attention as a...
By Futoshi Futami, Jerry Huang, Ichiro Takeuchi
The paper introduces Robust Weighted Profile-Loss Change Point Detection (RWCP), a method for locating authorship transitions in mixed human‑LLM documents using detector scores with varying reliability. RWCP combines capped reliability weights, Huber profile gains, and a narrowest‑over‑threshold search to express the population gap as a merge cost, enabling recovery of change points without a closed‑form nonlinear center. Experiments on five benchmark families show that core RWCP reduces WindowDiff by 17.6% compared to weighted change‑point detection, and an extended variant RWCP‑R further improves performance, especially for isolated changes.
By Wan Tian, Zhongyi Li, Yawen Li, Rui Zhang, Yijie Peng, Fuzhen Zhuang
Co-PiLOT is a latent optimization framework that maps candidate physical structures through a generative encoder-decoder, using the decoder as a learned validity prior and performing physics-informed black-box optimization in latent space. It is applied to the inverse design of magnesium alloy microstructure/texture, employing a vision transformer encoder paired with latent diffusion, diffusion transformer, and rectified-flow transformer decoders trained on an 80,000-sample EBSD dataset to produce a minimal bottleneck representation. The MERIDIAN optimizer, driven by a deep-kernel Gaussian process and failure-aware feasibility prediction, achieves the best target-driven objective score within 160 simulations, reducing relative target error by 3–22% compared to seven baseline methods.
By Mahish K. Guru, Mayank Nagar, Ayush vyas, Jan Bohlen, Roland Aydin, Noomane Ben Khalifa
PCaPaint is a prostate cancer inpainting method that uses latent diffusion models (LDMs) and introduces a conditioning strategy where the condition image is filled with Gaussian noise to mitigate shortcut learning. It also proposes a new training objective that focuses on errors within the lesion region and a multi‑sequence latent design that separately compresses T2w and DWI&ADC scans to preserve their distinct frequency characteristics. Experiments show that the synthetic data generated by PCaPaint improves downstream tasks such as prostate lesion segmentation, patient‑level classification, and lesion‑level detection, outperforming recent state‑of‑the‑art LDM‑based tumor inpainting methods in both performance and image quality.
By Levente Lippenszky, Hongxu Yang, Marcell D\"om\"ot\"or, Krisztian Koos, L\'aszl\'o Rusk\'o
arXiv:2607.12896v3 Announce Type: replace
Abstract: Medical image segmentation foundation models are expected to generalize across diverse clinical scenarios, yet existing universal methods remain fr...
By Yunzhou Li, Jiesi Hu, Yanwu Yang, Hanyang Peng, Chenfei Ye, Jianfeng Cao, Yixuan Yuan, Ting Ma
arXiv:2609.37243v1 Announce Type: cross
Abstract: Cross-modal knowledge distillation transfers knowledge from a teacher modality to a student modality. Existing feature-level alignment methods typica...
By Dae Ung Jo, Jongin Lim, YoungJoon Yoo, Daeho Um
arXiv:2609.37855v1 Announce Type: cross
Abstract: Hand anthropometry supports protective-glove design, but existing measurement methods often require trained operators, specialized hardware, or manua...
By Fan Zhou, Shuairan Chen, Mengying Zhang, Yulin Wu, Sadegh Jafari, Sixing Yu, Rui Li, Ali Jannesari, Guowen Song
arXiv:2609.38010v1 Announce Type: cross
Abstract: Modern computer vision models achieve high accuracy when trained on large-scale annotated datasets. In critical domains such as construction safety m...
By Mohamed Benkedadra, Aissa Saoudi, Maxime Gloesener, Sidi Ahmed Mahmoudi, Matei Mancas
arXiv:2506.11261v2 Announce Type: replace-cross
Abstract: Vision-language-action (VLA) models have shown promising progress in robotic manipulation. However, directly mapping visual observations and...
By Shizhe Chen, Ricardo Garcia, Paul Pacaud, Cordelia Schmid
arXiv:2609.32013v2 Announce Type: replace-cross
Abstract: We present TriO, a multi-modal unsupervised world model that predicts 4D occupancy, obstacle segmentation, flow and LiDAR. In contrast to pri...
By Quinlan Sykora, Sourav Biswas, Christopher Diehl, Andrew Cunningham, Thomas Gilles, Raquel Urtasun
arXiv:2609.37387v1 Announce Type: cross
Abstract: Enlarged perivascular spaces (PVS) visible in brain magnetic resonance imaging (MRI) are increasingly thought to be linked to poor brain health. PVS...
By Jesse Phitidis, William N. Whiteley, Joanna M. Wardlaw, Miguel O. Bernabeu, Yajun Cheng, Xiaodi Liu, Junfang Zhang, Una Clancy, Stephen Makin, Roberto Duarte Coello, Susana Mu\~noz Maniega, Mark E. Bastin, Simon R. Cox, Maria del C. Vald\'es Hern\'andez
arXiv:2609.37551v1 Announce Type: cross
Abstract: Emerging optical-network applications increasingly use received data for inference and control rather than exact source reproduction, creating an opp...
By Hussein Jammal, Andrea Bianco, Cristina Rottondi
arXiv:2609.37272v1 Announce Type: new
Abstract: Non-injective mappings in neural networks map distinct inputs to the same representation, thereby implicitly inducing equivalence relations in the inpu...
By Bizu Feng, Zhimu Yang, Shuming Wang, Yuan Cheng, Shaode Yu, Xiaojun Qian, Zixin Hu
arXiv:2609.36136v1 Announce Type: new
Abstract: Compact OCR-specific vision-language models achieve strong document parsing performance, but often rely on costly supervision and focus primarily on vi...
By Xin Chen, Anan Du, Feng Feng, Pei Fu, Jian Luan, Longwei Xu, Shaojie Zhang, Hang Li, Heng Qu, Cheng Tan
arXiv:2609.36217v1 Announce Type: new
Abstract: A deeper understanding of brain function requires a precise, structured characterization of behavior.Yet, extracting behavioral representations from vi...
By Xinming Dai, Qihang Jin, Tianshu Tan, Baiyuan Chen, Hanrui Lyu, Lenny Aharon, Kyle Daruwalla, Xun Helen Hou, Matthew R. Whiteway, Liam Paninski, Yizi Zhang