Tootfinder

AnyUp: Universal Feature Upsampling
Thomas Wimmer, Prune Truong, Marie-Julie Rakotosaona, Michael Oechsle, Federico Tombari, Bernt Schiele, Jan Eric Lenssen
https://arxiv.org/abs/2510.12764

AnyUp: Universal Feature Upsampling
We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need to be re-trained for every feature extractor and thus do not generalize to different feature types at inference time. In this work, we propose an inference-time feature-agnostic upsampling architecture to alleviate this limitation and improve upsampling quality. In our experiment…

Spectral Feature Extraction for Robust Network Intrusion Detection Using MFCCs
HyeYoung Lee, Muhammad Nadeem, Pavel Tsoi
https://arxiv.org/abs/2507.10622 h…

Spectral Feature Extraction for Robust Network Intrusion Detection Using MFCCs
The rapid expansion of Internet of Things (IoT) networks has led to a surge in security vulnerabilities, emphasizing the critical need for robust anomaly detection and classification techniques. In this work, we propose a novel approach for identifying anomalies in IoT network traffic by leveraging the Mel-frequency cepstral coefficients (MFCC) and ResNet-18, a deep learning model known for its effectiveness in feature extraction and image-based tasks. Learnable MFCCs enable adaptive spectral f…

Learning-To-Measure: In-context Active Feature Acquisition
Yuta Kobayashi, Zilin Jing, Jiayu Yao, Hongseok Namkoong, Shalmali Joshi
https://arxiv.org/abs/2510.12624 https://

Learning-To-Measure: In-context Active Feature Acquisition
Active feature acquisition (AFA) is a sequential decision-making problem where the goal is to improve model performance for test instances by adaptively selecting which features to acquire. In practice, AFA methods often learn from retrospective data with systematic missingness in the features and limited task-specific labels. Most prior work addresses acquisition for a single predetermined task, limiting scalability. To address this limitation, we formalize the meta-AFA problem, where the goal…

Microsoft begins testing a Windows 11 feature for sharing the entire desktop with Copilot Vision; it requires first entering a special mode in the Copilot app (Zac Bowden/Windows Central)
https://www.

Microsoft begins testing sharing your desktop with Copilot on Windows 11 — allows AI to view and chat about what's on your screen
First announced earlier this year, sharing your desktop with Copilot on Windows 11 is now in testing with insiders across all preview channels.

DarTwin made precise by SysMLv2 -- An Experiment
{\O}ystein Haugen, Stefan Klikovits, Martin Arthur Andersen, Jonathan Beaulieu, Francis Bordeleau, Joachim Denil, Joost Mertens
https://arxiv.org/abs/2510.12478

DarTwin made precise by SysMLv2 -- An Experiment
The new SysMLv2 adds mechanisms for the built-in specification of domain-specific concepts and language extensions. This feature promises to facilitate the creation of Domain-Specific Languages (DSLs) and interfacing with existing system descriptions and technical designs. In this paper, we review these features and evaluate SysMLv2's capabilities using concrete use cases. We develop DarTwin DSL, a DSL that formalizes the existing DarTwin notation for Digital Twin (DT) evolution, through SysMLv…

3S-Attack: Spatial, Spectral and Semantic Invisible Backdoor Attack Against DNN Models
Jianyao Yin, Luca Arnaboldi, Honglong Chen, Pascal Berrang
https://arxiv.org/abs/2507.10733 …

3S-Attack: Spatial, Spectral and Semantic Invisible Backdoor Attack Against DNN Models
Backdoor attacks involve either poisoning the training data or directly modifying the model in order to implant a hidden behavior, that causes the model to misclassify inputs when a specific trigger is present. During inference, the model maintains high accuracy on benign samples but misclassifies poisoned samples into an attacker-specified target class. Existing research on backdoor attacks has explored developing triggers in the spatial, spectral (frequency), and semantic (feature) domains, a…

A Multimodal Neural Network for Recognizing Subjective Self-Disclosure Towards Social Robots
Henry Powell, Guy Laban, Emily S. Cross
https://arxiv.org/abs/2508.10828 https://

A Multimodal Neural Network for Recognizing Subjective Self-Disclosure Towards Social Robots
Subjective self-disclosure is an important feature of human social interaction. While much has been done in the social and behavioural literature to characterise the features and consequences of subjective self-disclosure, little work has been done thus far to develop computational systems that are able to accurately model it. Even less work has been done that attempts to model specifically how human interactants self-disclose with robotic partners. It is becoming more pressing as we require so…

An Information-Theoretic Framework for Credit Risk Modeling: Unifying Industry Practice with Statistical Theory for Fair and Interpretable Scorecards
Agus Sudjianto, Denis Burakov
https://arxiv.org/abs/2509.09855

An Information-Theoretic Framework for Credit Risk Modeling: Unifying Industry Practice with Statistical Theory for Fair and Interpretable Scorecards
Credit risk modeling relies extensively on Weight of Evidence (WoE) and Information Value (IV) for feature engineering, and Population Stability Index (PSI) for drift monitoring, yet their theoretical foundations remain disconnected. We establish a unified information-theoretic framework revealing these industry-standard metrics as instances of classical information divergences. Specifically, we prove that IV exactly equals PSI (Jeffreys divergence) computed between good and bad credit outcomes…

Approximate Graph Propagation Revisited: Dynamic Parameterized Queries, Tighter Bounds and Dynamic Updates
Zhuowei Zhao, Zhuo Zhang, Hanzhi Wang, Junhao Gan, Zhifeng Bao, Jianzhong Qi
https://arxiv.org/abs/2509.10036

Approximate Graph Propagation Revisited: Dynamic Parameterized Queries, Tighter Bounds and Dynamic Updates
We revisit Approximate Graph Propagation (AGP), a unified framework which captures various graph propagation tasks, such as PageRank, feature propagation in Graph Neural Networks (GNNs), and graph-based Retrieval-Augmented Generation (RAG). Our work focuses on the settings of dynamic graphs and dynamic parameterized queries, where the underlying graphs evolve over time (updated by edge insertions or deletions) and the input query parameters are specified on the fly to fit application needs. Our…

Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking
Zirui Zheng, Takashi Isobe, Tong Shen, Xu Jia, Jianbin Zhao, Xiaomin Li, Mengmeng Ge, Baolu Li, Qinghe Wang, Dong Li, Dong Zhou, Yunzhi Zhuge, Huchuan Lu, Emad Barsoum
https://arxiv.org/abs/2509.12046

Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking
While autoregressive (AR) models have demonstrated remarkable success in image generation, extending them to layout-conditioned generation remains challenging due to the sparse nature of layout conditions and the risk of feature entanglement. We present Structured Masking for AR-based Layout-to-Image (SMARLI), a novel framework for layoutto-image generation that effectively integrates spatial layout constraints into AR-based image generation. To equip AR model with layout control, a specially d…