The paper examines how large language models (LLMs) can assist in creating regulatory compliance artifacts for EU sustainability and privacy laws, specifically Digital Product Passports (DPPs) under the Ecodesign for Sustainable Products Regulation and Data Protection Impact Assessments (DPIAs) under the General Data Protection Regulation. It investigates the effects of data extraction instructions and regulatory ambiguity on the quality and consistency of LLM-generated artifacts, benchmarking various models against manually crafted ground‑truth schemas. Findings indicate that looser guidelines, like those for DPIAs, demand more extensive prompts to achieve consistency, whereas stricter formatting rules for DPPs yield consistent outputs but may introduce hallucinations.
By Adriana Watson, Marco B\"ucheler, Grant Richards
arXiv:2608.21066v1 Announce Type: new
Abstract: Deploying autonomous systems in safety-critical domains demands guaranteed robustness against physically plausible geometric perturbations rather than...
By Gregoire Theau, Melanie Ducoffe
arXiv:2608.20969v1 Announce Type: new
Abstract: Multimodal clinical AI is limited by weakly aligned inputs and the absence of domain-specific interpretable representations, particularly when learning...
By Chen Dong, He Zonglin, Cheung Kenneth M. C
arXiv:2608.20929v1 Announce Type: new
Abstract: AI-generated image manipulation localization identifies edited pixels, but its OOD performance lags behind image-level detection partly because pixel s...
By Haozhen Yan, Siyuan Shan, Zijian Yu, Youqi Wang, Yan Hong, Jun Lan, Jianfu Zhang
arXiv:2608.20890v1 Announce Type: new
Abstract: Vision-Language-Action (VLA) models have emerged as a powerful paradigm for end-to-end autonomous driving by jointly integrating perception, reasoning,...
By Jingtao Sun, Xiaohai He, Yike Zhang, Dong Huang, Yaonan Wang, Ajmal Mian, Mike Zheng Shou
arXiv:2608.20554v1 Announce Type: cross
Abstract: The critical failure modes in deployed large language models (LLMs) are cross-dimensional: a model can score 99.3 in safety alignment while refusing...
By Fatih Deniz, Yazan Boshmaf, Dorde Popovic, Issa Khalil
arXiv:2608.20366v1 Announce Type: cross
Abstract: Molecular docking requires reasoning jointly about ligand pose and protein flexibility. Most diffusion-based docking models predict torsional updates...
By Maksim Zhdanov, Pavel Strashnov, Vladislav Kurenkov
arXiv:2608.20362v1 Announce Type: cross
Abstract: Reinforcement learning with verifiable rewards (RLVR) is a standard recipe for training large language models on mathematical reasoning, where an ans...
By Chenyu Zhou, Qiliang Jiang, Xu Zhou
The paper introduces a multi‑criteria framework for evaluating sociotechnical interventions, moving beyond sole effectiveness to include political feasibility, user acceptance, cost, and implementation effort. Using misinformation as a case study, the authors surveyed 39 researchers on 40 interventions across these five criteria, revealing that the most effective solutions are not always the most acceptable or feasible. The study offers a decision framework to help practitioners balance these trade‑offs in designing interventions.
By Catherine King, Lynnette Hui Xian Ng, Kathleen M. Carley
The paper introduces CRATE, a two‑stage vision‑language model framework that evaluates mobile agents by reasoning about each step’s consequences and aggregating this evidence to assess task completion. It also presents CRATE‑S, an extension that evaluates operational safety. Experiments show CRATE and CRATE‑S outperform existing benchmarks, achieving high F1‑scores on AndroidWorld and MobileRisk datasets.
By Pengshuai Yang, Zijing Gao, Xue Yu, Benhui Zhuang, Bo Yuan, Junlan Feng
arXiv:2608.21009v1 Announce Type: new
Abstract: Ensuring that Extended Reality (XR) environments are age-appropriate is an important regulatory and safety challenge. However, current age assurance op...
By Riccardo Bovo, George Loukas, Josh P. Davis
The paper surveys multimodal speculative decoding, examining whether diffusion-based block‑parallel generative drafting—successful in text‑only LLMs—can be applied to Vision‑Language, Video‑Language, Audio, and Vision‑Language‑Action models. It introduces a taxonomy separating drafter‑side parallelism from other design choices, and presents an empirical comparison across benchmarks such as OCR, VQA, visual reasoning, and image captioning. The study highlights current limitations, outlines open challenges, and suggests future research directions for multimodal speculative decoding.
By Yantao Li, Huanlin Gao, Fang Zhao, Chao Tan, Qiang Hui, Shuting Liu, Fuyuan Shi, Ting Lu, Shaoan Zhao, Xueqiang Guo, Xinpei Su, Jianbing Zhang, Xinyu Dai, Kai Wang, Shiguo Lian
arXiv:2608.20980v1 Announce Type: new
Abstract: Graph neural networks (GNNs) are routinely employed for short-range forecasting on multivariate time series with a spatial graph structure. Despite the...
By Kenneth Martin, Simon Heilig, Asja Fischer, Michel F. C. Haddad, Adam M. Sykulski, Moshe Eliasof
The paper introduces Fuzzy-MoE, a fuzzy logic‑based Mixture‑of‑Experts model that jointly identifies latent temporal states and routes forecasts to appropriate experts in non‑stationary multivariate time series. By combining local convolutional dynamics with global segmented statistics, the dual‑view fuzzy router uses learnable Gaussian membership functions to compute expert activation strengths, enabling explicit IF‑THEN rule‑based expert selection. Experiments on several public benchmarks show that Fuzzy‑MoE outperforms mainstream forecasting methods while providing interpretable routing diagnostics.
By Lan Guo, Jie Xiao, Zhao Su, Jun Shen, Haoran Li, Weixia Ma, Qingguo Zhou, Binbin Yong
ReFrame is a training‑free framework that enhances safety alignment for multimodal large language models at test time. It uses two lightweight agents: one generates risk and utility evidence, and the other rewrites prompts and routes images to create a safe proxy before invoking the deployed MLLM. Experiments show that ReFrame improves jailbreak defense, safety awareness, and reduces over‑sensitivity while maintaining multimodal utility.
By Wenzheng Jiang, Xuankun Rong, Yuanzhao Zhai, Dawei Feng, Huaimin Wang
The article reviews how multimodal large language models (MLLMs) are expanding radiology AI beyond image‑specific tasks to multimodal reasoning, yet volumetric radiology poses a representational challenge because clinical interpretation needs full 3‑D spatial context and quantitative data. It surveys over 200 studies, categorizing advances in volumetric representation, multimodal understanding, and agentic orchestration, and introduces a Claim‑Design‑Validation framework to align technical, workflow, and clinical claims. The review emphasizes that native volumetric modeling and agentic capabilities must match spatial, quantitative, contextual, and workflow demands, and that clinical credibility hinges on faithful 3‑D representation, traceable behavior, proper validation, and defined human oversight.
By Zanting Ye, Shengyuan Liu, Xin Liu, Chenhui Wang, Zhisong Wang, Jiashuai Liu, Zipei Wang, Cheng Wang, Wentao Pan, Mengjie Fang, Di Dong, Mohammad Salmanpour, Arman Rahmim, Yu Gu, Yong Xia, Hongming Shan, Yixuan Yuan, Yefeng Zheng, Lijun Lu
arXiv:2604.13687v2 Announce Type: replace-cross
Abstract: Glitches frequently contaminate data in gravitational-wave detectors, complicating the observation and analysis of astrophysical signals. Thi...
By Tiago Fernandes, Francesco Di Renzo, Antonio Onofre, Alejandro Torres-Forn\'e, Jos\'e A. Font
MIL-BERT is a neural network algorithm that classifies large texts by selecting relevant excerpts, inspired by multiple instance learning. It scales to samples with nearly 1 million tokens and has been evaluated on seven datasets, achieving state‑of‑the‑art results on three long‑text tasks such as political bias detection, trigger warning identification, and author demographic inference. The model also generalizes from weakly‑labeled text bags to accurately classify smaller instances.
By John Cadigan, Dayne Freitag, Eric Yeh
The paper introduces ICOMT, a framework for interpretable clustering using optimal multi-way decision trees. It proposes a new discretization technique based on one-dimensional K‑means, formulates a binary linear optimization problem to ensure tree optimality, and demonstrates superior clustering accuracy and shallow tree structures on four public datasets.
By Hayato Suzuki, Shunnosuke Ikeda, Naoki Nishimura, Yuichi Takano
Object-centric world models forecast future videos by evolving a set of entity slots, but the variables receiving dynamics supervision are often unconstrained visual features. We introduce \method{},...