FEAT is a foundation model designed for extremely large structured data that replaces quadratic self‑attention with a linear‑complexity dual‑axis encoding architecture. It combines an adaptive‑fusion bidirectional state‑space model with convolutional gated linear attention to achieve permutation‑invariant representation learning in O(N) time. Experiments on 12 real‑world database benchmarks show that FEAT outperforms existing structured data foundation models on zero‑shot tasks and can be up to 50× faster in inference latency.
By Zhenghang Song, Tang Qian, Lu Chen, Yushuai Li, Zhengke Hu, Bingbing Fang, Yumeng Song, Junbo Zhao, Sheng Zhang, Tianyi Li
The paper introduces CELM, a data‑free framework for federated learning that estimates class‑wise contribution by maximizing logits. It constructs a cross‑client evidence matrix to quantify each client’s competence and coverage for each class, then uses this matrix to compute weighted aggregation that upweights clients offering strong evidence for underrepresented classes. The method maintains stability through simplex constraints and momentum smoothing, and it is compatible with standard FL pipelines, showing improved robustness to class imbalance and heterogeneity on vision benchmarks.
By Asim Ukaye, Nurbek Tastan, Mubarak Abdu-Aguye, Karthik Nandakumar
arXiv:2504. 07133v2 Announce Type: replace-cross Abstract: We revisit the problem of estimating $k$ linear regressors with self-selection bias in $d$ dimensions with the maximum selection criterion, as introduced by Cherapanamjeri, Daskalakis, Ilyas, and Zampetakis [CDIZ23, STOC'23].
By Alkis Kalavasis, Anay Mehrotra, Felix Zhou
The paper introduces a bias‑correction method for synthetic oversampling in imbalanced learning. It estimates the loss discrepancy caused by the data generator using a held‑out majority subset and transfers this correction to the minority class under a uniform bias‑transfer assumption. The authors provide finite‑sample bounds for bias transfer and excess balanced risk, identify when SMOTE introduces significant bias, and demonstrate the method’s applicability to multi‑task learning and propensity‑score estimation, with empirical results showing greatest benefit when synthetic distortion is large.
By Pengfei Lyu, Zhengchi Ma, Linjun Zhang, Anru R. Zhang
The paper presents an automated pipeline that uses unmanned aircraft systems (UAS) multispectral imagery and a Vision Transformer to detect wheat streak mosaic virus (WSMV) at the plant level. While the model achieved 89% accuracy on over 6,500 test patches using treatment-based labels, ELISA-based ground truth revealed significant label noise, indicating that the high accuracy was largely due to label bias rather than true disease detection. When evaluated against more reliable row‑level symptom severity and plant‑level ELISA labels, both deep learning and classical machine learning models showed limited generalization and weak separability between infected and mock‑inoculated plants, underscoring the importance of biologically grounded labels and realistic data conditions for UAS‑based disease detection.
By Dewi Endah Kharismawati, Sandeep Dhakal, Courtney E. McCusker, Jennifer R. Wilson, Erik W. Ohlson, Sami Khanal
PhysPlan is a training‑free guidance framework that enhances video diffusion models by incorporating physical awareness through agentic physics simulation. It uses a vision‑language model to generate a Chain‑of‑Visual‑Thought representation of kinematic trajectories and 3D depth, which then drives an object‑centric test‑time optimization that isolates kinematic changes and locks the passive environment. The framework also employs Kinetic Intensity Profiling to adapt hyperparameters to varying physical deformations, and demonstrates superior performance on PhyGenBench and Physics‑IQ benchmarks compared to existing VDM baselines.
By Minh-Loi Nguyen, Xuan-Vu Le, Thanh-Toan Do, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le
VertexCBF is a framework that learns neural control barrier functions (CBFs) by approximating the stationary Hamilton–Jacobi value function with a neural network trained through physics‑informed and sparsely supervised learning. It exploits control‑affine dynamics and a convex polytope control set to generate supervision points via GPU‑parallel vertex‑restricted tree search, ensuring the learned CBF never exceeds the specified constraint function. The method was evaluated on 15 systems, outperforming baselines by recovering larger safe sets, and demonstrated on a mobile robot that safely avoids pedestrians using a neural CBF trained with this approach.
By Bojan Deraji\'c, Sebastian Bernhard, Wolfgang H\"onig
arXiv:2609.12397v1 Announce Type: new
Abstract: Multi-modal image generation, particularly subject-driven customization, has garnered growing attention in recent years. Despite the rapid advancement...
By Danning Zhang, Yijing Lin, Shuhan Zhuang, Mengqi Huang, Shaojin Wu, Shancheng Fang, Zhendong Mao
arXiv:2609.10313v1 Announce Type: cross
Abstract: Shapley values are widely used for post-hoc feature attribution, but most estimators return point quantities and do not quantify uncertainty, and pop...
By Agostino Gnasso
The paper presents a unified framework for regularization-based robust reinforcement learning by deriving upper bounds on the performance gap between nominal and worst-case policies. These bounds are expressed as a regularization objective plus a KL-divergence penalty, explaining why KL penalties enhance robustness. The authors reformulate robust training as a constrained optimization problem, updating the Lagrange multiplier jointly with the policy to automatically tune regularization, and validate the approach with extensive adversarial evaluations on continuous control tasks.
By Amine Andam, Jamal Bentahar, Mustapha Hedabou
The paper investigates the environmental impact of running large language models (LLMs) on mobile devices. It evaluates 18 different LLM configurations on two smartphones and a server, measuring energy per token, latency, accuracy, and battery-cycle consumption. Findings reveal that on-device inference is about three times less energy‑efficient than batched server inference, that energy consumption varies non‑monotonically with quantization bit‑width, and that most models are not on the Pareto front of accuracy and energy efficiency. The study concludes that local AI is not inherently more sustainable than cloud inference, with the majority of environmental impact stemming from device embodied carbon.
By \'Edouard Gu\'egain, Tristan Coignion
The paper presents a curriculum‑based adversarial heterogeneous agent reinforcement learning (HARL‑AC) approach for autonomous quad‑copter landing on a ship deck in maritime settings. Using Heterogeneous‑Agent Proximal Policy Optimization (HAPPO) in NVIDIA Isaac Lab, the authors train a cooperative control policy that outperforms domain‑randomized baselines, achieving up to 97.5% success on in‑distribution sea states and higher median success and lower crash rates on out‑of‑distribution sea states. The adversarially trained policy also exhibits more cautious behavior, slightly increasing timeouts but improving safety in severe, unseen conditions.
By Allan Minh-Tam Nguyen, Sree Showrya Kotala, Stefan Banioi-Crijman, Kurt Driessens, Rico M\"ockel
The paper introduces a new criticality metric specifically designed for vulnerable road users (VRUs) and a scenario‑independent prediction framework that applies to all traffic participants. The VRU‑centric metric improves pedestrian criticality classification by up to 50 %, while the prediction framework surpasses state‑of‑the‑art metrics by 275 %, achieving an F1‑score of 0.96 on the DeepAccident dataset. These advances enable more accurate, scenario‑agnostic safety assessments for autonomous driving systems.
By J\"org Gamerdinger, Victor Schwarzenberger, Philipp Schmid, Sven Teufel, Oliver Bringmann
Robion is a new serving and management system designed to run Vision‑Language‑Action (VLA) models on multi‑GPU edge servers for robot factories. It splits the VLM and ADiT stages within a single GPU, shares streams across multiple models, and prioritizes requests by remaining SLO time, enabling high robot load while meeting strict latency requirements. In experiments, Robion achieves 6.7× higher robot load than vLLM‑Omni and 1.5× higher than a monolithic pipeline, and can serve 64 robots on a 4‑GPU server with 98% SLO attainment.
By Dionysios Adamopoulos, Nattapol Chanpaisit, Basel Fakhri, Christina Giannoula
The article presents the first demonstration of an agentic TCAD calibration workflow for a fabricated bottom‑gate In–W–O transistor. Starting from measured transfer curves, the workflow uses measurement–TCAD residuals and local sensitivity tests to guide parameter corrections or additional physical models, accepting only updates that improve device metrics. For a 2%‑W reference device, five agent‑suggested updates reduced the multi‑metric device objective by 14.3× and achieved low errors in threshold voltage and on‑current across varying bias and geometry, showing model transferability and process sensitivity.
By Gyujun Jeong, Junmo Lee, Sungwon Cho, Woohyun Hwang, Kwangyou Seo, Suhwan Lim, Wanki Kim, Daewon Ha, Rishi Ranade, Kihang Youn, Ram Cherukuri, Yiyi Wang, Asif Khan, Shimeng Yu
The paper introduces ExCYDER, an explainable AI framework for anomaly detection in Distributed Energy Resource (DER) networks. It combines LightGBM with SHAP to self-verify alerts, ensuring that each detection aligns with feature‑attribution evidence. Experiments on a realistic DNP3 dataset show over 98% detection accuracy, 44.6% rule‑SHAP consistency, 14.5 ms SHAP latency per alert, and minimal confidence deviation, while distinguishing coherent from inconsistent alerts without sacrificing accuracy.
By Damilola Popoola, Souradeep Bhattacharya, Manimaran Govindarasu
The paper introduces Pairwise Likelihood MIA (PL‑MIA), a unified membership inference attack that combines a Gaussian likelihood‑ratio statistic with population calibration and the Cauchy combination test. PL‑MIA generates p‑values from pairwise comparisons between a query point and reference points, then aggregates these continuous signals using the Cauchy test to preserve evidence strength. Experiments show that PL‑MIA surpasses strong baselines, boosting true positive rates by over 25% in low‑false‑positive settings, thereby validating the theoretical advantages of the proposed statistical framework.
By Shengjie Niu, Zebin Yun, Yeheng Ge, Jian Huang
The paper introduces Spatial‑FAD, a few‑shot medical anomaly detection framework that fuses Vision‑Language Model (CLIP) semantics with spatial priors from Vision Foundation Models (DINO). A VFM‑enhanced adapter injects structural affinity into CLIP features, while a sliding‑window aggregation produces high‑resolution embeddings for finer lesion localization. Prototype‑enhanced support memory further improves efficiency and performance, yielding significant gains on Liver CT, Retinal OCT, and Brain MRI datasets, notably an 11.4% Dice improvement in 4‑shot scenarios.
By Juzheng Miao, Yuchen Yuan, Cheng Chen, Pheng-Ann Heng
Prism‑SQA is a neural framework that interprets surface electromyography (sEMG) quality assessment by separating each signal into a clean component and five contaminant-specific components using a U‑Net with bidirectional LSTM. Each contaminant is verified against canonical physiological signatures, allowing clinicians to see how specific noises affect quality. The resulting quality indices can be customized for different clinical contexts without retraining, and Prism‑SQA matches or surpasses current black‑box methods on both continuous and binary quality tasks.
By Kuan-Chen Wang, Kai-Chun Liu, Ping-Cheng Yeh, Sheng-Yu Peng, Yu Tsao
The paper presents a cross‑modal learning framework that predicts three‑dimensional dislocation density fields directly from X‑ray diffraction data. By pairing simulated dislocation density fields with virtual diffraction patterns and embedding them into a shared 2‑D latent space via contrastive learning, the authors achieve strong alignment between structural and diffraction representations. Experiments show that model performance improves rapidly with dataset size, reaching near‑saturation with about 500 representative observations out of 10,000, and the predicted structures capture the dominant spatial features of the underlying microstructures.
By Benjamin Udofia, Nicolas Bertin, Markus Stricker