arXiv:2607. 02569v1 Announce Type: cross Abstract: This paper presents a safety-centered empirical evaluation of uncertainty-aware last-layer adaptation for referable diabetic retinopathy screening using RETFound, a self-supervised vision-transformer retinal foundation model used here as a frozen feature encoder, and the public APTOS 2019 and DDR diabetic retinopathy fundus image datasets.
By Karim Mardhani
arXiv:2601. 11960v3 Announce Type: replace-cross Abstract: Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference responses.
By Jingchu Wang, Bingbing Xu, Yige Yuan, Dan Zhang, Bin Xie, Xiaoqian Sun, Huawei Shen
arXiv:2509. 22851v4 Announce Type: replace-cross Abstract: Margin-based optimization is fundamental to improving generalization and robustness in classification tasks.
By Yaswanth Chittepu, Prasann Singhal, Greg Durrett, Scott Niekum
arXiv:2512. 22240v5 Announce Type: replace-cross Abstract: Machine learning models are primarily judged by predictive performance, especially in applied genomics, where explanations are read as biological findings.
By Chama Bensmail
arXiv:2607. 05251v1 Announce Type: cross Abstract: Neural network verification and data privacy are inherently in tension: verification demands full access to model parameters and input data, yet both are increasingly restricted by privacy regulations and intellectual property constraints.
By Nianyun Song, Xiaokun Luan, Yu Guo, Rongfang Bie, Meng Sun, Xiyue Zhang
arXiv:2607. 02611v1 Announce Type: cross Abstract: Work-related Musculoskeletal Disorders (WMSDs) require continuous ergonomic assessments.
By Xuhan Zhang, Zhuangzhuang Dai, Luis J. Mans, Victor Chang
arXiv:2607. 04780v1 Announce Type: cross Abstract: Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particle system are biased approximations of an ideal Feynman--Kac flow.
By Stanislas Strasman (SU, LPSM), Gabriel Victorino Cardoso (LPSM), Sylvain Le Corff (LPSM), Vincent Lemaire (LPSM), Antonio Ocello
arXiv:2607. 05364v1 Announce Type: cross Abstract: Modern autoregressive ASR systems can emit timestamps as decoded tokens, enabling timestamped transcription without frame-level aligners or inference-time post-processing.
By Cheng-Kang Chou, Ming-To Chuang, Ke-Han Lu, Chan-Jan Hsu, Hung-yi Lee
arXiv:2602. 17284v2 Announce Type: replace Abstract: We consider the privacy amplification properties of a sampling scheme in which a user's data isused in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps.
By Vitaly Feldman, Moshe Shenfeld
arXiv:2508. 04928v5 Announce Type: replace-cross Abstract: We propose a method to extend foundational monocular depth estimators (FMDEs), trained on perspective images, to fisheye images.
By Rit Gangopadhyay, Jung-Hee Kim, Xien Chen, Patrick Rim, Hyoungseob Park, Alex Wong
arXiv:2506. 15199v4 Announce Type: replace Abstract: While there are many applications of ML to scientific problems that look promising, visuals can be deceiving.
By Alejandro Francisco Queiruga, Theo Gutman-Solo, Shuai Jiang
arXiv:2211. 15590v2 Announce Type: replace Abstract: Analyzing the behavior of complex interdependent networks requires complete information about the network topology and the interdependent links across networks.
By MirSaleh Bahavarnia, Hiba Baroud, Yu Wang, Jin-Zhu Yu
arXiv:2607. 05098v1 Announce Type: new Abstract: When sensitive attributes are continuous and high-dimensional $-$ demographic score vectors, posteriors over attributes, age or income profiles $-$ enforcing full statistical independence is often too restrictive, and existing relaxations rely on indirect dependence penalties or adversarial schemes that do not directly target the fairness-accuracy trade-off.
By Ieva Petrulionyte, Julien Mairal, Michael Arbel
arXiv:2606. 12471v2 Announce Type: replace-cross Abstract: Klindt, LeCun, and Balestriero (arXiv:2605.
By Seth Dobrin, {\L}ukasz Chmiel
arXiv:2607. 05281v1 Announce Type: cross Abstract: Present-day quantum computing is cloud-based, where a user submits a circuit to a service provider's proprietary backend hardware.
By Ben Priestley, Mina Doosti
arXiv:2607. 04119v1 Announce Type: cross Abstract: Reconstructing Computer-Aided Design (CAD) modeling sequences from images is crucial for preserving design intent and supporting parametric editing.
By Zhaopeng Feng, Chen Zhi, Xuhong Zhang, Zhengwen Feng, Xinkui Zhao
arXiv:2510. 25599v2 Announce Type: replace Abstract: Regression tasks, notably in safety-critical domains, require reliable uncertainty quantification, yet the literature remains largely classification-focused.
By Christopher B\"ulte, Yusuf Sale, Gitta Kutyniok, Eyke H\"ullermeier
arXiv:2506. 05716v2 Announce Type: replace-cross Abstract: Deep Q-Networks (DQN) can suffer from overestimation bias because bootstrapped targets use a maximisation operation over noisy value estimates.
By Adrian Ly, Richard Dazeley, Peter Vamplew, Francisco Cruz, Sunil Aryal
arXiv:2607. 03025v1 Announce Type: new Abstract: The use of Large Language Models (LLMs) across diverse areas of human activity-ranging from everyday tasks to safety-critical applications-aims to enhance decision-making effectiveness with minimal human feedback.
By Andreas Kouridakis, Dimitrios Patiniotis Spyropoulos, George Vouros
arXiv:2607. 03075v1 Announce Type: new Abstract: Safety-critical applications require classifiers that are both robust and reliable.
By Nicolas Sournac, Ahmed Baha Ben Jmaa, Bertrand Braeckeveldt