Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection introduces OracleAD, an unsupervised framework that encodes each variable’s past into a causal embedding to jointly predict the present and reconstruct the input window. The embeddings are projected via self‑attention into a shared latent space, capturing dynamic spatial relationships that are aligned to a Stable Latent Structure (SLS) representing normal-state relationships. Anomalies are detected through a dual scoring mechanism based on prediction error and deviation from the SLS, allowing fine‑grained diagnosis and root‑cause identification at the variable level.
By Dongchan Cho, Jiho Han, Keumyeong Kang, Minsang Kim, Honggyu Ryu, Namsoon Jung
arXiv:2601.13235v2 Announce Type: replace-cross
Abstract: Caregivers seeking AI-mediated support express complex needs---information-seeking, emotional validation, and distress cues---that warrant ca...
By Drishti Goel, Jeongah Lee, Qiuyue Joy Zhong, Violeta J. Rodriguez, Daniel S. Brown, Ravi Karkar, Dong Whi Yoo, Koustuv Saha
arXiv:2604.06192v2 Announce Type: replace-cross
Abstract: Recent work uses entropy-based signals at multiple representation levels to study reasoning in large language models, but the field remains l...
By Mar Gonz\`alez I Catal\`a, Haitz S\'aez de Oc\'ariz Borde, George D. Monta\~nez, Pietro Li\`o
arXiv:2604.18936v2 Announce Type: replace
Abstract: Despite the growing application of large language models (LLMs) to theoretical physics, there has been little academic exploration of how domain-sp...
By Nathaniel S. Woodward, Zhiqi Gao, Yurii Kvasiuk, Kendrick M. Smith, Frederic Sala, Moritz M\"unchmeyer
arXiv:2604.22903v2 Announce Type: replace
Abstract: The integration of quantum machine learning with classical deep learning offers promising avenues for medical image analysis by mapping data into h...
By Yasmin Rodrigues Sobrinho, Jo\~ao Renato Ribeiro Manesco, Jo\~ao Paulo Papa
arXiv:2605.11388v2 Announce Type: replace
Abstract: Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambigu...
By Dean Light, Michael Theologitis, Kshitish Ghate, Shuyue Stella Li, Benjamin Newman, Chirag Shah, Aylin Caliskan, Pang Wei Koh, Dan Suciu, Yulia Tsvetkov
The paper introduces MOVAL, a model evaluation tool that estimates performance of deep neural networks on unlabeled test data by calibrating class-wise confidence scores. MOVAL mitigates issues from distributional shifts and class imbalance, enabling estimation of metrics beyond accuracy such as F1-Score and AUC. Experiments on natural and medical image datasets demonstrate state‑of‑the‑art results across classification and segmentation tasks, providing accurate class, instance, and pixel‑level performance estimates for safe deployment.
By Zeju Li, Konstantinos Kamnitsas, Mobarakol Islam, Melanie Roschewitz, Cheng Ouyang, Chen Chen, Ben Glocker
arXiv:2602.16429v2 Announce Type: replace
Abstract: Agentic systems, AI architectures that autonomously execute multi-step workflows to achieve complex goals, are often built using repeated large lan...
By Ido Levy, Segev Shlomov, Avi Yaeli, Nir Mashkif, Asaf Adi, Yinon Goldshtein, Eilam Shapira, Leshem Choshen
arXiv:2610.29784v1 Announce Type: new
Abstract: Most contemporary artificial intelligence (AI) systems are released with frozen parameters and improve through external updates, whereas an ideal syste...
By Zhipeng Chen, Yunsen Liang, Yanxi Chen, Hongkang Zhao, Lingyun Feng, Ruiyang Ren, Guoxin Chen, Jia Deng, Feng Chang, Chuan Hao, Ran Tao, Jian Yang, Ji-Rong Wen, Bryan Dai, Wayne Xin Zhao
arXiv:2610.29896v1 Announce Type: new
Abstract: Existing social bias benchmarks evaluate large language models mostly on fluent, well-formed English, reflecting native speaker usage and leaving non-n...
By Federico Marcuzzi, Martin Christoph, Iryna Gurevych, Alla Rozovskays
arXiv:2610.30067v1 Announce Type: new
Abstract: Vietnamese pre-trained encoders have improved rapidly, but the strongest ones are large, multilingual-vocabulary models or depend on external word segm...
By Quang Anh Kiet Tran, Nam Anh Tran, Manh Hung Trinh, Thanh Danh Le, Khang Nhat Hoang Vo, Huynh Dai Nhan Tran
The paper introduces a unified training framework for underwater image enhancement that addresses the scarcity of paired clean-degraded datasets. It employs a text-guided diffusion model to generate diverse, semantically consistent degraded images and uses a progressive degradation curriculum to balance learning across multiple attributes and difficulty levels. The approach also incorporates a transmission-guided one-step diffusion model to handle varying degradation severity, achieving superior performance on several underwater benchmarks.
By Hongri Tian, Wenxue Li, Tian Ye, Sixiang Chen, Lujia Wang, Xianying Wang, Xinhu Zheng, Gang Hua, Lei Zhu
The paper presents a semi‑supervised framework that uses open‑vocabulary object detectors to generate region proposals and semantic representations, builds an object‑level similarity graph, and propagates probabilistic labels to assign soft, uncertainty‑aware annotations to previously unlabeled objects. Experiments on four detection benchmarks show that high‑quality soft labels can be produced with only a small fraction of manual annotations, and models trained on these semi‑automatically annotated datasets achieve performance comparable to fully manually annotated models. On COCO, the method reaches 40.5% AP, nearly matching the 40.9% AP of a fully annotated model while incurring only 1% of the labeling cost.
By Jonathan Klees, Timo Heller, Matthias Rottmann
Singular-value spectra encode important structure in transformer feed-forward projections, yet their causal role in downstream behavior remains underexplored. We study post-hoc spectral smoothing and...
Designing RNA molecules that bind to target protein structures requires generating both an RNA conformation and its bound complex geometry, without assuming a predefined binding site. Existing approac...
Vision-and-Language Navigation (VLN) requires agents to follow instructions and navigate to target locations. However, current VLN agents often suffer severe performance degradation in unseen environm...
Self-supervised Vision Transformers learn strong image-level representations, but their patch-level representations can be unreliable for dense prediction. We study this mismatch and find that the cla...
Unmanned aerial vehicles (UAVs) have recently emerged as important remote sensing platforms, and UAV navigation has shown great potential in remote sensing applications. However, existing methods do n...
LLMs have shown strong in-context learning (ICL) capability, but extending it to Multimodal LLMs (MLLMs) remains challenging. Prior multimodal ICL methods often rely on ICL-specific datasets for addit...
Frontier language models now score above 90% on popular knowledge benchmarks and are increasingly deployed as agents that carry out multi-hour professional work. Yet no existing benchmark tests whethe...