arXiv subjects

Borui Xu

Publications and source records attributed to Borui Xu.

6 recordsLinked to original sources

arXiv2026

VLALagBench: Understanding When and Why VLA Inference Latency Matters

Vision-language-action (VLA) models offer a promising path toward general-purpose robot manipulation. While inference latency can affect task success in a constantly evolving physical world, the relationship between latency and task success rate remains poorly understood. In this paper, we introduce VLALagBench, a comprehensive benchmark for studying VLA inference latency sensitivity across task types, object speeds, execution modes (synchronous and asynchronous), and VLA policies. Using VLALagBench, we find that even a modest inference latency of 100 ms can nearly halve task success on moving targets, with sensitivity varying substantially across tasks and policies. These differences reflect task-specific requirements for precision and continuous motion. By overlapping inference with action execution, asynchronous execution can recover some of the lost success at the cost of more frequent inference requests. Building on these findings, we develop an empirical model that predicts task success from limited calibration data, achieving root-mean-square prediction errors of only 5.7-7.8% across various VLA policies. Given an inference system's latency and per-robot throughput, these predictions guide the selection of system-specific VLA algorithm configurations to maximize task success. We believe VLALagBench and these findings provide a solid foundation for future robotics algorithm-system co-design.

cs.RO↗

arXiv2026

VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware

Vision-language-action (VLA) models increasingly run on edge devices aboard robots, where inference latency constrains closed-loop robot control. However, it remains unclear how to design VLA models, their inference software and edge hardware so that robots can run VLA inference in real time. Most VLA models report only task success, while prior studies cover limited action-generation strategies, divide inference into at most three stages, and lack comparisons of inference optimizations on the same models. Therefore, we introduce VLA-HWBench, a benchmark that measures 18 open VLA models on NVIDIA Jetson AGX Thor and AMD Ryzen AI Max+ PRO 395, with a seven-stage inference breakdown. Our study reveals three insights. First, action-generation strategy matters more than model size. It dominates 14 of 19 Jetson configurations, latency varies by $82\times$ on Jetson and $157\times$ on AMD, and parameter count explains at most 15% of latency variance. Models that generate long action chunks in a few flow-matching steps keep up with control, whereas token-by-token decoding does not. Second, kernel fusion with 4-bit weights helps most, running $π_{0.5}$ and GR00T N1.7 2.6-2.9$\times$ faster than PyTorch with torch.compile, but it exists for only these two models and only on the Jetson. Optimization also moves the time to the stages it shortens least, as CPU preprocessing grows from 12% to 39% of the GR00T N1.7 call. Third, after optimization, memory bandwidth limits only the stages that process few tokens on the Jetson, such as the denoising steps, whereas software limits all other stages, from unfused kernels to serial preprocessing on the host CPU. Overall, low-latency edge VLAs should use few action-generation iterations, inference software should extend kernel fusion and low-bit weights to more models and platforms, and edge hardware needs high memory bandwidth and a fast host CPU.

cs.RO↗

arXiv2026

VLA-Retain: Benchmarking Cross-Dimension Effects of Vision Tuning in VLAs

Vision-language-action (VLA) models transfer knowledge from large-scale pretraining into robot control, but their manipulation performance remains sensitive to changes in observation conditions, which recent work addresses by fine-tuning the visual module on target-domain data. However, it remains unclear how such adaptation affects robustness beyond the target condition, as existing robustness benchmarks only evaluate models without fine-tuning and adaptation studies only report the target gain. Measuring this cross-dimension effect requires separating target gains from off-target changes, isolating adaptation effects from architectural differences, ruling out generic forgetting, and comparing tuning choices. Therefore, we introduce VLA-Retain, a benchmark that compares five open VLA models, tuned on Camera-view or Sensor-noise data, with their own base checkpoints on LIBERO-Plus dataset spanning seven perturbation dimensions. Our study reveals four findings. First, targeted vision tuning is not local, and its target gain does not predict retention. Mean off-target gain is negative in 8 of 10 model--domain configurations. Under Camera-view tuning, X-VLA gains $69.4$ percentage points on the target but loses $4.6$ points on average elsewhere, whereas OpenVLA-OFT gains $39.3$ and $1.4$ points, respectively. Second, these regressions are not explained only by performance loss on the same tasks without perturbations. Third, broader training coverage raises overall gain over target-specific training but does not eliminate dimension-level regressions. Fourth, tuning strategies are model-dependent, as DELTA-style feature preservation raises X-VLA's mean off-target gain to $+1.2$ points but lowers OpenVLA-OFT's to $-23.1$. Overall, these findings show that target-domain success alone is insufficient and highlight cross-dimensional retention as a key criterion for targeted VLA adaptation.

cs.CV↗

arXiv2026

Metasurface-based Terahertz Three-dimensional Holography Enabled by Physics-Informed Neural Network

Artificial intelligence has revolutionized optical device design, overcoming the efficiency bottlenecks of traditional methods. For holographic metasurfaces, conventional iterative algorithms suffer from time-consuming iterations and convergence stagnation, especially as the complexity of 3D target fields increases. While recent deep-learning-based algorithms have improved the trade-off between speed and image quality, most existing models remain constrained by predefined physical scenarios (e.g., fixed distances), limiting their adaptability in dynamic practical applications. To address these challenges, we propose a physics-informed neural network (PINN) based on local polynomial fitting and multi-plane wave propagation (LM-PINN) for the rapid design of terahertz 3D holographic metasurfaces. By leveraging a self-supervised training strategy, LM-PINN eliminates the need for labeled datasets, enabling direct end-to-end mapping from target holographic patterns to the metasurface structures. Both simulated and experimental results demonstrate that LM-PINN-designed metasurfaces offer higher imaging quality than traditional iterative algorithms. Crucially, by incorporating a distance encoding process, a single trained LM-PINN generalizes effectively across diverse physical configurations, including varying diffraction distances and distinct 2D or 3D targets, eliminating the necessity for retraining. Furthermore, the inference process of LM-PINN typically takes less than 1 second, providing a multifold speed advantage over traditional algorithms. Consequently, this strategy offers a robust and universal framework that paves the way for high-quality, real-time, and large-scale 3D holographic technologies.

physics.optics↗

arXiv2025

Deep-learning-enabled inverse design of large-scale metasurfaces with full-wave accuracy

Recent advances in meta-optics have enabled diverse functionalities in compact optical devices; however, conventional forward design approaches become inadequate as device complexity and scale grow. Inverse design offers a powerful alternative but often requires massive computational resources and neglects mutual coupling effects. Here, we propose and experimentally validate a deep-learning-enabled framework for rapid inverse design of large-scale, aperiodic metasurfaces with full-wave accuracy.The framework integrates an inverse design network responsible that maps target near-field responses to metasurface geometries in a non-iterative and scalable manner. A lightweight forward prediction network, integrated as a full-wave solver surrogate within the framework, enables efficient end-to-end training of the inverse design network while capturing mutual coupling effects by considering both local and neighboring geometries.The framework's effectiveness is experimentally verified through a multi-foci metalens and a holographic metasurface. This framework enables the inverse design from micrometer to centimeter scales (> 20kλ), with near-field responses discrepancies less than 3% compared to full-wave solvers at subwavelength (< λ/10) resolution.Moreover, it is generalizable to metasurfaces of arbitrary size and operates efficiently without high-performance resources, overcoming the computational bottlenecks of previous inverse design methods.

physics.optics↗

arXiv2025

Evaluating Small Language Models for News Summarization: Implications and Factors Influencing Performance

The increasing demand for efficient summarization tools in resource-constrained environments highlights the need for effective solutions. While large language models (LLMs) deliver superior summarization quality, their high computational resource requirements limit practical use applications. In contrast, small language models (SLMs) present a more accessible alternative, capable of real-time summarization on edge devices. However, their summarization capabilities and comparative performance against LLMs remain underexplored. This paper addresses this gap by presenting a comprehensive evaluation of 19 SLMs for news summarization across 2,000 news samples, focusing on relevance, coherence, factual consistency, and summary length. Our findings reveal significant variations in SLM performance, with top-performing models such as Phi3-Mini and Llama3.2-3B-Ins achieving results comparable to those of 70B LLMs while generating more concise summaries. Notably, SLMs are better suited for simple prompts, as overly complex prompts may lead to a decline in summary quality. Additionally, our analysis indicates that instruction tuning does not consistently enhance the news summarization capabilities of SLMs. This research not only contributes to the understanding of SLMs but also provides practical insights for researchers seeking efficient summarization solutions that balance performance and resource use.

cs.CL↗