The paper introduces a contact tracing algorithm that incorporates differential privacy to protect users’ risk scores from adversarial inference. By releasing each risk score with an epsilon of 1, the algorithm achieves a two- to ten-fold reduction in infection rates across two leading COVID‑19 agent‑based simulators. This work claims to be the first to provide differential privacy guarantees for risk score disclosure in COVID‑19 contact tracing.
By Rob Romijnders, Christos Louizos, Yuki M. Asano, Max Welling
GraphProfiler is an auditable LLM-based profiler that infers sensitive attributes such as age, income, and occupation from user-generated content by aggregating indirect cues across many posts. It represents each user's post history as a source-linked personal knowledge graph, allowing predictions to be traced back to specific posts, concepts, and relationships. The system achieves an 86.7% success rate on the SynthPAI benchmark and 84.6% on PANDORA, citing supporting evidence for over 98% of predictions and demonstrating that cited posts significantly contribute to attack success.
By Ahmed Sohair Khan, Estrid He, Chenglong Ma, Monica Wachowicz, Elham Naghizade
DRS‑VPT is a feed‑forward transformer that performs image‑to‑scan registration by predicting the scan pose, point maps, and a coarse‑to‑fine feature pyramid for direct reprojective alignment. It unifies tasks like camera‑LiDAR calibration and indoor camera‑to‑map relocalization, achieving state‑of‑the‑art results in autonomous driving and competitive performance indoors without map‑specific training. The model also learns complex scan‑to‑image projection behaviors, such as occlusion of back‑facing points.
By Lanke Frank Tarimo Fu, Maurice Fallon
VideoTok4D introduces a 4D‑aware video tokenizer that transforms videos into compact tokens representing a dynamic 3D world. It employs spatiotemporal disentanglement to separate static and dynamic content, a track‑aware dynamic attention mechanism for motion consistency across views, and a diffusion prior (Co4DGen) for efficient 4D scene generation. Experiments show state‑of‑the‑art results with up to four orders of magnitude less storage than dense 4D representations, and shorter diffusion sequences for faster generation.
By Xinyi Chen, Hanxin Zhu, Xijun Wang, Xingrui Wang, Sen Liang, Xin Li, Zhibo Chen
The paper introduces Adversarial Importance Sampling (Advis), a technique that leverages importance sampling over standard training trajectories to estimate and optimize worst‑case returns without extra environment interactions or auxiliary networks, thereby capturing long‑term robustness. It also presents advrl, a modular PyTorch library that consolidates existing robustness methods and adversarial attacks into single‑file implementations for easier prototyping and reproducible evaluation. Finally, the authors highlight that optimal adversarial hyperparameters do not transfer across agents, prompting evaluation against a broader set of attackers (6–14× more configurations) and demonstrate the effectiveness of their approach on continuous control tasks.
By Amine Andam, Jamal Bentahar, Mustapha Hedabou
MAxBench is a geometry‑agnostic benchmark for evaluating how well language models recover multinomial concept representations. The study compares ten localization methods across five geometry types, six concepts, and four models, finding that affine subspaces generally steer more reliably and recall more instances than rank‑one or linear subspaces. The results also show that manifold steering can match the best methods when applicable, and that no method consistently outperforms prompting for these complex concepts.
By Divya Appapogu, Freya Behrens, Yonatan Belinkov, Aaron Mueller
The paper introduces AIM, a privacy‑aware memory framework that lets multi‑agent, multi‑user large language models manage both private and shared memory. AIM classifies data as private (user‑specific) or public (shared) and enforces index‑level access controls to protect sensitive information while enabling shared knowledge to improve coordination. The authors also present MUMBench, a new dataset for evaluating memory operations in multi‑user settings, and report high accuracy metrics for AIM on this benchmark.
By Zachary Johnson, Nigel Boachie Kumankumah, Somya Chatterjee, Tejas Sathyamurthi, Min Chen, Xinyi Alice Li, Xiao Wang, Emily Morgan Gelchie, Jessica Lin, Sadid A. Hasan, Sulaiman Vesal
Guided Adversarial Robust Transfer (GART) learning is a new transfer learning method that relaxes the requirement for source data to closely resemble the target population. By optimizing an adversarial loss over a mixture of source distributions, GART achieves faster convergence and improved prediction performance when target data are scarce. Experiments on simulated data and on multi‑institutional biobank‑linked electronic health records for high‑density lipoprotein cholesterol demonstrate higher robustness and accuracy compared to existing transfer learning approaches.
By Xin Xiong, Zijian Guo, Tianxi Cai
The paper presents a human‑annotated dataset of 100 Quran recitation recordings, identifying 348 scored units and 162 localized events across ten combined labels. An evaluator that scores both labels and word positions achieves a label‑aware F1 of 0.525 and a localization F1 of 0.826, with adapted production cleaner/alignment components yielding similar scores. A pilot experiment with eight 20‑minute runs across three coders and eight models shows wide variance in F1 (0.143–0.892) and highlights that most gold events are detected, leaving only span extent and label conventions as the remaining challenges.
By Mohamad Al Mdfaa, Nursultan Askarbekuly, Ahmed Helaly, Ubai Sandouk, Manuel Mazzara
The paper introduces Diffusion-Conditioned Representation Alignment (DCRA), a training framework that uses the forward diffusion process as a structured corruption scheduler for time‑series representation learning. DCRA aligns representations across noise levels with a feature‑level consistency objective, preserving class‑discriminative structure and enabling smooth, semantically coherent trajectories in latent space. Experiments on the CHB‑MIT EEG dataset demonstrate that DCRA improves seizure detection performance under various noise conditions, achieving higher sensitivity at low false‑positive rates and producing more balanced, structured representations than baseline methods.
By Wenrui Xu, Anas Enanaa, Keshab K. Parhi
The paper introduces a certification framework for assessing concept unlearning in text-to-image diffusion models, offering high‑confidence guarantees with bounded error on residual concept leakage. Unlike prior methods that rely solely on attack success rates from automated prompt searches, this approach combines statistical certification with worst‑case analysis along concept‑relevant embedding directions to derive explicit upper bounds on leakage probability. Evaluations across NSFW content, artistic styles, and celebrity identities reveal that certified leakage bounds exceed standard attack success rates by 16.2%, highlighting significant residual risks overlooked by existing protocols.
By Mansi, Luca Marzari, Francesco Leofante
The paper introduces GACA, a critic‑free reinforcement learning estimator that adapts credit assignment granularity based on a step‑level uncertainty proxy. GACA assigns higher weight to fine‑grained signals for steps with above‑average negative log‑likelihood, while relying on episode‑level signals for less uncertain steps, improving task success on ALFWorld and WebShop for 1.5B and 7B language models. The authors provide a risk decomposition, a conditional bound on action‑value variation, and an error‑projection analysis to justify the method’s effectiveness.
By Taoran Liang, Yang Liu, Shang Luo, Yingguang Yang, Rongrong Zhang, Yingzong Min, Yulin Huang, Jianshen Zhang, Yongzhi Qi, Kefu Xu, Congjing Ran, Bin Chong
Doc2FRC introduces Fixed-Range Chunking (FRC), a dynamic programming method that partitions documents into chunks of a predefined length interval, ensuring consistent length distributions during training and inference. This approach reduces train-test length mismatch, mitigates n-gram repetition, and improves translation quality for 7B LLMs compared to direct Doc2Doc fine-tuning. Experiments on IWSLT2017 and a new 10-language test set, GlobVDoc, demonstrate that FRC outperforms existing document-level machine translation methods and enhances out-of-distribution translation performance.
By Xiaotian Wang, Youyuan Lin, Zhan Shen, Hitomi Yanaka
PACIFIC is a framework that aligns large language model responses with user preferences by leveraging stable Big‑Five personality traits as a latent signal. The authors built a 1,200‑pair dataset covering diverse domains and trait directions, and found that trait‑aligned contexts enable LLMs to achieve near‑ceiling accuracy (up to 99%) in personalized QA. They also introduced a persona‑aware contrastive retriever (PiRAG) that improves label‑free accuracy from 30% to 43% over standard semantic retrieval, highlighting retrieval as the main bottleneck.
By Tianyu Zhao, Siqi Li, Yasser Shoukry, Salma Elmalaki
The paper investigates the impact of label noise on sign language recognition, comparing robust loss functions—symmetric cross entropy (SCE) and generalized cross entropy (GCE)—to standard cross entropy (CE) in both isolated (ISLR) and continuous (CSLR) settings. Experiments on ASL Citizen with injected symmetric noise show that SCE and GCE outperform CE across multiple backbones, though GCE’s optimal hyperparameter does not transfer well. In CSLR experiments on PHOENIX-2014, robust losses offer limited gains, with performance largely influenced by auxiliary weight settings rather than the loss choice.
By Akihisa Shitara, Yoichi Ochiai
The paper introduces a method for progressively extending the dynamic range of an image by learning to increase it by a single exposure value first, then applying the network recurrently to achieve full HDR reconstruction. The approach is agnostic to input dynamic range, targets a bounded output domain, and utilizes RAW images with adversarial losses to produce realistic results. Memory Replay during backpropagation allows training over multiple inference stages, reducing reconstruction errors and enabling robust recovery of bright highlights in long‑tailed HDR scenes.
By Sebastian Dille, Keru Fu, S. Mahdi H. Miangoleh, Ya\u{g}{\i}z Aksoy
The paper introduces a two‑step debiased estimation method for PDE‑constrained inverse problems where the PDE solution is approximated by Physics‑Informed Neural Networks (PINNs). By combining neural‑network‑based nonparametric estimation with an influence‑function bias correction, the authors achieve a √{n}-consistent, asymptotically normal estimator without undersmoothing the neural network. The approach is extended to Bayesian inference, yielding a posterior that contracts at the √{n}-rate with asymptotic covariance matching the frequentist estimator, and the analysis also provides near‑minimax rates for estimating nonparametric regression functions and their derivatives in Sobolev spaces.
By Yves Atchade, Debarghya Mukherjee
The paper introduces a threat model for malicious intent injection in AI‑native 6G networks and examines four injection strategies: stealth‑mode, random distribution, increasing frequency, and decreasing frequency. It proposes a dual‑path detection framework combining a CNN with TF‑IDF features for supervised detection and an AutoEncoder trained on benign data for one‑class detection. Evaluation shows the framework achieves higher accuracy (0.97) and F1‑score (0.98) than the state‑of‑the‑art baseline.
By Nilesh Chakraborty, Petar Djukic, Burak Kantarci
PEARL is a framework for human‑centric cyber‑physical systems that uses a dual‑path Early‑Exit Deep Q‑Network to control the trade‑off between privacy and utility. By training per‑branch binary labels—Utility Confidence Labels (UCL) and Privacy Confidence Labels (PCL)—based on mutual information between private states and observable actions, PEARL selects the shallowest exit that satisfies both privacy and utility constraints, avoiding noise injection. The system includes an MI‑based feedback loop to detect behavioral drift and trigger retraining, and experiments on a smart‑home HVAC system and a VR smart classroom show a 25.67% reduction in adversarial state‑inference accuracy with only a 10‑16% utility cost.
By Mojtaba Taherisadr, Salma Elmalaki
arXiv:2606.23189v2 Announce Type: replace-cross
Abstract: Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-appl...
By Anmol Goel, Iryna Gurevych