arXiv subjects

Nan Xiao

Publications and source records attributed to Nan Xiao.

10 recordsLinked to original sources

arXiv2026

arg-VU: Affordance Reasoning with Physics-Aware 3D Geometry for Visual Understanding in Robotic Surgery

Affordance reasoning provides a principled link between perception and action, yet remains underexplored in surgical robotics, where tissues are highly deformable, compliant, and dynamically coupled with tool motion. We present arg-VU, a physics-aware affordance reasoning framework that integrates temporally consistent geometry tracking with constraint-induced mechanical modeling for surgical visual understanding. Surgical scenes are reconstructed using 3D Gaussian Splatting (3DGS) and converted into a temporally tracked surface representation. Extended Position-Based Dynamics (XPBD) embeds local deformation constraints and produces representative geometry points (RGPs) whose constraint sensitivities define anisotropic stiffness metrics capturing the local constraint-manifold geometry. Robotic tool poses in SE(3) are incorporated to compute rigidly induced displacements at RGPs, from which we derive two complementary measures: a physics-aware compliance energy that evaluates mechanical feasibility with respect to local deformation constraints, and a positional agreement score that captures motion alignment (as kinematic motion baseline). Experiments on surgical video datasets show that arg-VU yields more stable, physically consistent, and interpretable affordance predictions than kinematic baselines. These results demonstrate that physics-aware geometric representations enable reliable affordance reasoning for deformable surgical environments and support embodied robotic interaction.

cs.CV↗

arXiv2025

CIS-BA: Continuous Interaction Space Based Backdoor Attack for Object Detection in the Real-World

Object detection models deployed in real-world applications such as autonomous driving face serious threats from backdoor attacks. Despite their practical effectiveness,existing methods are inherently limited in both capability and robustness due to their dependence on single-trigger-single-object mappings and fragile pixel-level cues. We propose CIS-BA, a novel backdoor attack paradigm that redefines trigger design by shifting from static object features to continuous inter-object interaction patterns that describe how objects co-occur and interact in a scene. By modeling these patterns as a continuous interaction space, CIS-BA introduces space triggers that, for the first time, enable a multi-trigger-multi-object attack mechanism while achieving robustness through invariant geometric relations. To implement this paradigm, we design CIS-Frame, which constructs space triggers via interaction analysis, formalizes them as class-geometry constraints for sample poisoning, and embeds the backdoor during detector training. CIS-Frame supports both single-object attacks (object misclassification and disappearance) and multi-object simultaneous attacks, enabling complex and coordinated effects across diverse interaction states. Experiments on MS-COCO and real-world videos show that CIS-BA achieves over 97% attack success under complex environments and maintains over 95% effectiveness under dynamic multi-trigger conditions, while evading three state-of-the-art defenses. In summary, CIS-BA extends the landscape of backdoor attacks in interaction-intensive scenarios and provides new insights into the security of object detection systems.

cs.CV↗

arXiv2025

External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation

Ads recommendation is a prominent service of online advertising systems and has been actively studied. Recent studies indicate that scaling-up and advanced design of the recommendation model can bring significant performance improvement. However, with a larger model scale, such prior studies have a significantly increasing gap from industry as they often neglect two fundamental challenges in industrial-scale applications. First, training and inference budgets are restricted for the model to be served, exceeding which may incur latency and impair user experience. Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system. We propose the External Large Foundation Model (ExFM) framework to address the overlooked challenges. Specifically, we develop external distillation and a data augmentation system (DAS) to control the computational cost of training/inference while maintaining high performance. We design the teacher in a way like a foundation model (FM) that can serve multiple students as vertical models (VMs) to amortize its building cost. We propose Auxiliary Head and Student Adapter to mitigate the data distribution gap between FM and VMs caused by the streaming data issue. Comprehensive experiments on internal industrial-scale applications and public datasets demonstrate significant performance gain by ExFM.

cs.IR↗

arXiv2025

ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI

Simulation has enabled unprecedented compute-scalable approaches to robot learning. However, many existing simulation frameworks typically support a narrow range of scenes/tasks and lack features critical for scaling generalizable robotics and sim2real. We introduce and open source ManiSkill3, the fastest state-visual GPU parallelized robotics simulator with contact-rich physics targeting generalizable manipulation. ManiSkill3 supports GPU parallelization of many aspects including simulation+rendering, heterogeneous simulation, pointclouds/voxels visual input, and more. Simulation with rendering on ManiSkill3 can run 10-1000x faster with 2-3x less GPU memory usage than other platforms, achieving up to 30,000+ FPS in benchmarked environments due to minimal python/pytorch overhead in the system, simulation on the GPU, and the use of the SAPIEN parallel rendering system. Tasks that used to take hours to train can now take minutes. We further provide the most comprehensive range of GPU parallelized environments/tasks spanning 12 distinct domains including but not limited to mobile manipulation for tasks such as drawing, humanoids, and dextrous manipulation in realistic scenes designed by artists or real-world digital twins. In addition, millions of demonstration frames are provided from motion planning, RL, and teleoperation. ManiSkill3 also provides a comprehensive set of baselines that span popular RL and learning-from-demonstrations algorithms.

cs.RO↗

arXiv2024

A Reinforcement Learning-Based Automatic Video Editing Method Using Pre-trained Vision-Language Model

In this era of videos, automatic video editing techniques attract more and more attention from industry and academia since they can reduce workloads and lower the requirements for human editors. Existing automatic editing systems are mainly scene- or event-specific, e.g., soccer game broadcasting, yet the automatic systems for general editing, e.g., movie or vlog editing which covers various scenes and events, were rarely studied before, and converting the event-driven editing method to a general scene is nontrivial. In this paper, we propose a two-stage scheme for general editing. Firstly, unlike previous works that extract scene-specific features, we leverage the pre-trained Vision-Language Model (VLM) to extract the editing-relevant representations as editing context. Moreover, to close the gap between the professional-looking videos and the automatic productions generated with simple guidelines, we propose a Reinforcement Learning (RL)-based editing framework to formulate the editing problem and train the virtual editor to make better sequential editing decisions. Finally, we evaluate the proposed method on a more general editing task with a real movie dataset. Experimental results demonstrate the effectiveness and benefits of the proposed context representation and the learning ability of our RL-based editing framework.

cs.CV↗

arXiv2024

APT-MMF: An advanced persistent threat actor attribution method based on multimodal and multilevel feature fusion

Threat actor attribution is a crucial defense strategy for combating advanced persistent threats (APTs). Cyber threat intelligence (CTI), which involves analyzing multisource heterogeneous data from APTs, plays an important role in APT actor attribution. The current attribution methods extract features from different CTI perspectives and employ machine learning models to classify CTI reports according to their threat actors. However, these methods usually extract only one kind of feature and ignore heterogeneous information, especially the attributes and relations of indicators of compromise (IOCs), which form the core of CTI. To address these problems, we propose an APT actor attribution method based on multimodal and multilevel feature fusion (APT-MMF). First, we leverage a heterogeneous attributed graph to characterize APT reports and their IOC information. Then, we extract and fuse multimodal features, including attribute type features, natural language text features and topological relationship features, to construct comprehensive node representations. Furthermore, we design multilevel heterogeneous graph attention networks to learn the deep hidden features of APT report nodes; these networks integrate IOC type-level, metapath-based neighbor node-level, and metapath semantic-level attention. Utilizing multisource threat intelligence, we construct a heterogeneous attributed graph dataset for verification purposes. The experimental results show that our method not only outperforms the existing methods but also demonstrates its good interpretability for attribution analysis tasks.

cs.CR↗

arXiv2020

The Rockerverse: Packages and Applications for Containerization with R

The Rocker Project provides widely used Docker images for R across different application scenarios. This article surveys downstream projects that build upon the Rocker Project images and presents the current state of R packages for managing Docker images and controlling containers. These use cases cover diverse topics such as package development, reproducible research, collaborative work, cloud-based data processing, and production deployment of services. The variety of applications demonstrates the power of the Rocker Project specifically and containerisation in general. Across the diverse ways to use containers, we identified common themes: reproducible environments, scalability and efficiency, and portability across clouds. We conclude that the current growth and diversification of use cases is likely to continue its positive impact, but see the need for consolidating the Rockerverse ecosystem of packages, developing common practices for applications, and exploring alternative containerisation software.

cs.SE↗

arXiv2019

Physics driven reduced order model for real time blood flow simulations

Predictive modeling of blood flow and pressure have numerous applications ranging from non-invasive assessment of functional significance of disease to planning invasive procedures. While several such predictive modeling techniques have been proposed, their use in the clinic has been limited due in part to the significant time required to perform virtual interventions and compute the resultant changes in hemodynamic conditions. We propose a fast hemodynamic assessment method based on first constructing an exploration space of geometries, tailored to each patient, and subsequently building a physics driven reduced order model in this space. We demonstrate that this method can predict fractional flow reserve derived from coronary computed tomography angiography in response to changes to a patient-specific lumen geometry in real time while achieving high accuracy when compared to computational fluid dynamics simulations. We validated this method on over 1300 patients that received a coronary CT scan and demonstrated a correlation coefficient of 0.98 with an error of 0.005 +- 0.015 (95% confidence interval: (-0.020, 0.031)) as compared to three-dimensional blood flow calculations.

math.NA↗

arXiv2015

Mean Square Capacity of Power Constrained Fading Channels with Causal Encoders and Decoders

This paper is concerned with the mean square stabilization problem of discrete-time LTI systems over a power constrained fading channel. Different from existing research works, the channel considered in this paper suffers from both fading and additive noises. We allow any form of causal channel encoders/decoders, unlike linear encoders/decoders commonly studied in the literature. Sufficient conditions and necessary conditions for the mean square stabilizability are given in terms of channel parameters such as transmission power and fading and additive noise statistics in relation to the unstable eigenvalues of the open-loop system matrix. The corresponding mean square capacity of the power constrained fading channel under causal encoders/decoders is given. It is proved that this mean square capacity is smaller than the corresponding Shannon channel capacity. In the end, numerical examples are presented, which demonstrate that the causal encoders/decoders render less restrictive stabilizability conditions than those under linear encoders/decoders studied in the existing works.

math.OC↗

arXiv2012

Road Pricing for Spreading Peak Travel: Modeling and Design

A case study of the Singapore road network provides empirical evidence that road pricing can significantly affect commuter trip timing behaviors. In this paper, we propose a model of trip timing decisions that reasonably matches the observed commuters' behaviors. Our model explicitly captures the difference in individuals' sensitivity to price, travel time and early or late arrival at destination. New pricing schemes are suggested to better spread peak travel and reduce traffic congestion. Simulation results based on the proposed model are provided in comparison with the real data for the Singapore case study.

cs.GT↗