arXiv subjects

Xinyi Shi

Publications and source records attributed to Xinyi Shi.

5 recordsLinked to original sources

arXiv2026

A Straight Line Is Not a Camera Pose: Auditing Short-Clip Pose Benchmarks

The absolute trajectory error (ATE) is the standard measure of camera-motion accuracy, from SLAM to feed-forward 3D reconstruction. On the common Sintel protocol, a constant-velocity straight line using no images has a lower mean ATE than 10 of 11 recent models re-run with official code. Two properties of ATE's alignment explain this. First, it maps any constant-velocity prediction onto the best-fitting line through the true path, so the line scores the path's regression residual. A residual signal-to-noise ratio (SNR) criterion predicts when moving a prediction towards its constant-velocity fit lowers ATE. It gives the outcome for 95% of 1056 model-clip pairs, 98% of 792 held-out pairs and 97% of 1034 ScanNet pairs, and it separates Sintel (median SNR 0.86) from TUM, ScanNet and full-length Bonn and Wild-SLAM (2.7 to 27), where straightening raises every model's mean ATE. Second, position-only alignment ignores where cameras look: rotating a trajectory by 30 degrees against its orientations leaves ATE unchanged, yet worsens the reprojection of static points for every model on Sintel, TUM and ScanNet in the main setting, and the line, second by mean ATE on Sintel, places them worst by geometric mean: a lower ATE need not mean better geometry. Fitting the alignment's rotation to the predicted orientations gives pose-anchored ATE, a one-function change in ATE's units costing 0.17 ms per clip (ATE: 0.11 ms). It ranks every image-free reference below every model on Sintel, tracks the reprojection error under rotation and straightening, where ATE does not (Spearman 0.61 vs. 0.32), largely preserves the models' order, and ties 10-frame translational relative pose error (RPE) and the discernible trajectory error (DTE) on our rotation and reference tests. Code, predictions and results will be released.

cs.CV↗

arXiv2026

Beyond atol and rtol: Sound Test Oracles for Low-Precision GPU Kernels

Low-precision GPU kernels are commonly tested against a reference using hand-picked absolute and relative tolerances. Legitimate numerical error varies with the input, format and precision plan, so a fixed tolerance trades false alarms for missed faults. We present numoracle, which derives per-element acceptance regions from precision-annotated reference programs. Its calculus tracks shared rounding errors, provenance-ordered products, block-scaled quantizers and calibrated math-library errors. A rounding-interval check detects faulty stores that symmetric bounds can admit. Soundness is conditional on explicit rounding, hardware, domain and implementation assumptions; a fixed-input mode removes the zero-mean rounding assumption. We evaluate 13 Triton operators from Liger-Kernel, Unsloth and vLLM on two GPU generations. The main campaigns produce no false alarm on 33,960 correct-kernel and behavior-preserving-variant runs per GPU. Under input shift, the GPU campaigns record no false alarm while tuned tolerances flag up to 30% of correct runs; final-version reference checks identify inputs without complete finite-range certificates. On the RTX PRO 6000, numoracle kills 116 of 124 effective mutants, versus 59-83 for four fixed baselines. Among 400 tuned tolerance configurations, requiring at most 1% false alarms in every evaluated Liger input group permits at most 31 of 53 main-mutant kills, versus numoracle's 50. Historical replays expose accuracy faults in eight change pairs without rejecting their matched corrected controls; a ninth change concerns rounding parity.

cs.MS↗

arXiv2025

Automated Penetration Testing with LLM Agents and Classical Planning

While penetration testing plays a vital role in cybersecurity, achieving fully automated, hands-off-the-keyboard execution remains a significant research challenge. In this paper, we introduce the "Planner-Executor-Perceptor (PEP)" design paradigm and use it to systematically review existing work and identify the key challenges in this area. We also evaluate existing penetration testing systems, with a particular focus on the use of Large Language Model (LLM) agents for this task. The results show that the out-of-the-box Claude Code and Sonnet 4.5 exhibit superior penetration capabilities observed to date, substantially outperforming all prior systems. However, a detailed analysis of their testing processes reveals specific strengths and limitations; notably, LLM agents struggle with maintaining coherent long-horizon plans, performing complex reasoning, and effectively utilizing specialized tools. These limitations significantly constrain its overall capability, efficiency, and stability. To address these limitations, we propose CHECKMATE, a framework that integrates enhanced classical planning with LLM agents, providing an external, structured "brain" that mitigates the inherent weaknesses of LLM agents. Our evaluation shows that CHECKMATE outperforms the state-of-the-art system (Claude Code) in penetration capability, improving benchmark success rates by over 20%. In addition, it delivers substantially greater stability, cutting both time and monetary costs by more than 50%.

cs.CR↗

arXiv2025

GraphFaaS: Serverless GNN Inference for Burst-Resilient, Real-Time Intrusion Detection

Provenance-based intrusion detection is an increasingly popular application of graphical machine learning in cybersecurity, where system activities are modeled as provenance graphs to capture causality and correlations among potentially malicious actions. Graph Neural Networks (GNNs) have demonstrated strong performance in this setting. However, traditional statically-provisioned GNN inference architectures fall short in meeting two crucial demands of intrusion detection: (1) maintaining consistently low detection latency, and (2) handling highly irregular and bursty workloads. To holistically address these challenges, we present GraphFaaS, a serverless architecture tailored for GNN-based intrusion detection. GraphFaaS leverages the elasticity and agility of serverless computing to dynamically scale the GNN inference pipeline. We parallelize and adapt GNN workflows to a serverless environment, ensuring that the system can respond in real time to fluctuating workloads. By decoupling compute resources from static provisioning, GraphFaaS delivers stable inference latency, which is critical for dependable intrusion detection and timely incident response in cybersecurity operations. Preliminary evaluation shows GraphFaaS reduces average detection latency by 85% and coefficient of variation (CV) by 64% compared to the baseline.

cs.CR↗

arXiv2025

Comparative Performance of Finetuned ImageNet Pre-trained Models for Electronic Component Classification

Electronic component classification and detection are crucial in manufacturing industries, significantly reducing labor costs and promoting technological and industrial development. Pre-trained models, especially those trained on ImageNet, are highly effective in image classification, allowing researchers to achieve excellent results even with limited data. This paper compares the performance of twelve ImageNet pre-trained models in classifying electronic components. Our findings show that all models tested delivered respectable accuracies. MobileNet-V2 recorded the highest at 99.95%, while EfficientNet-B0 had the lowest at 92.26%. These results underscore the substantial benefits of using ImageNet pre-trained models in image classification tasks and confirm the practical applicability of these methods in the electronics manufacturing sector.

cs.CV↗