arXiv subjects

Zhiyang Li

Publications and source records attributed to Zhiyang Li.

17 recordsLinked to original sources

arXiv2026

Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment

Vision-Language-Action (VLA) models are promising for generalist robot control, but on-robot deployment is bottlenecked by real-time inference under tight cost and energy budgets. Most prior evaluations rely on desktop-grade GPUs, obscuring the trade-offs and opportunities offered by heterogeneous edge accelerators (GPUs/XPUs/NPUs). We present a systematic analysis for low-cost VLA deployment via model-hardware co-characterization. First, we build a cross-accelerator leaderboard and evaluate model-hardware pairs under CET (Cost, Energy, Time), showing that right-sized edge devices can be more cost-/energy-efficient than flagship GPUs while meeting control-rate constraints. Second, using in-depth profiling, we uncover a consistent two-phase inference pattern: a compute-bound VLM backbone followed by a memory-bound Action Expert, which induces phase-dependent underutilization and hardware inefficiency. Finally, guided by these insights, we propose DP-Cache and V-AEFusion to reduce diffusion redundancy and enable asynchronous pipeline parallelism, achieving up to 2.9x speedup on GPUs and 6x on edge NPUs with only marginal success degradation. The example leaderboard website is available at: https://vla-leaderboard-01.vercel.app/.

cs.RO↗

arXiv2026

RoboHarness: A Memory-Augmented Policy Harness for Vision-Language-Action Model Robustness via In-Context Adaptation

Despite the promise of Vision-Language-Action (VLA) models as generalist robotic controllers, their robustness against perceptual noise and environmental variations in out-of-distribution (OOD) tasks remains fundamentally limited by the absence of long-term memory, causal failure attribution, and dynamic intervention capability. To address this, we propose RoboHarness, a memory-augmented policy harness that upgrades frozen VLA policies for robust in-context adaptation without parameter fine-tuning. Specifically, RoboHarness operates through an online pipeline of contrastive Dual-Memory Retrieval-Augmented Generation (RAG), an attribution-driven vision-language orchestrator implemented with a multimodal large language model, and extensible Model Context Protocol (MCP) interventions, while an offline Memory Consolidation module continuously distills the execution traces into reliable priors. Experimental evaluations across three backbone models ($\pi_0$, $\pi_{0.5}$, and SmolVLA) on LIBERO-PRO and our proposed LIBERO-RoboHarness benchmarks demonstrate that RoboHarness achieves an average absolute success rate gain of 56.6%. This includes a significant absolute improvement of 89.1% in long-horizon task chaining. The project page and source code are available at https://github.com/LZY-1021/RoboHarness.

cs.RO↗

arXiv2026

KG-ViP: Bridging Knowledge Grounding and Visual Perception in Multi-modal LLMs for Visual Question Answering

Multi-modal Large Language Models (MLLMs) for Visual Question Answering (VQA) often suffer from dual limitations: knowledge hallucination and insufficient fine-grained visual perception. Crucially, we identify that commonsense graphs and scene graphs provide precisely complementary solutions to these respective deficiencies by providing rich external knowledge and capturing fine-grained visual details. However, prior works typically treat them in isolation, overlooking their synergistic potential. To bridge this gap, we propose KG-ViP, a unified framework that empowers MLLMs by fusing scene graphs and commonsense graphs. The core of the KG-ViP framework is a novel retrieval-and-fusion pipeline that utilizes the query as a semantic bridge to progressively integrate both graphs, synthesizing a unified structured context that facilitates reliable multi-modal reasoning. Extensive experiments on FVQA 2.0+ and MVQA benchmarks demonstrate that KG-ViP significantly outperforms existing VQA methods.

cs.CV↗

arXiv2025

Hardware-Impaired Over-the-Air Computation with Fluid Antenna Array

This paper investigates a fluid antenna (FA) array-enhanced over-the-air computation (AirComp) system in the presence of hardware impairments (HWIs), exploiting the new degrees of freedom offered by reconfigurable antenna positioning. To minimize the mean squared error (MSE) of the aggregated signal, we jointly optimize transmit power control, receive beamforming, and the antenna position vector (APV), subject to practical constraints such as HWI-induced distortion noise, FA movement energy consumption, and total power budgets. The resulting optimization problem is non-convex and highly coupled. To address it efficiently, we adopt a block coordinate descent (BCD) framework, decomposing it into three manageable subproblems. For each subproblem, closed-form solutions or efficient numerical algorithms are derived. Simulation results demonstrate that the proposed joint transceiver and APV design significantly reduces the MSE compared to conventional fixed-position antenna (FPA) arrays and exhibits enhanced robustness against hardware impairments. The effectiveness and convergence of the proposed algorithm are further validated under various system configurations.

eess.SP↗

arXiv2025

Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric

With the rapid advancement of 3D visualization, 3D Gaussian Splatting (3DGS) has emerged as a leading technique for real-time, high-fidelity rendering. While prior research has emphasized algorithmic performance and visual fidelity, the perceptual quality of 3DGS-rendered content, especially under varying reconstruction conditions, remains largely underexplored. In practice, factors such as viewpoint sparsity, limited training iterations, point downsampling, noise, and color distortions can significantly degrade visual quality, yet their perceptual impact has not been systematically studied. To bridge this gap, we present 3DGS-QA, the first subjective quality assessment dataset for 3DGS. It comprises 225 degraded reconstructions across 15 object types, enabling a controlled investigation of common distortion factors. Based on this dataset, we introduce a no-reference quality prediction model that directly operates on native 3D Gaussian primitives, without requiring rendered images or ground-truth references. Our model extracts spatial and photometric cues from the Gaussian representation to estimate perceived quality in a structure-aware manner. We further benchmark existing quality assessment methods, spanning both traditional and learning-based approaches. Experimental results show that our method consistently achieves superior performance, highlighting its robustness and effectiveness for 3DGS content evaluation. The dataset and code are made publicly available at https://github.com/diaoyn/3DGSQA to facilitate future research in 3DGS quality assessment.

cs.CV↗

arXiv2025

Security Analysis of Thumbnail-Preserving Image Encryption and a New Framework

As a primary encryption primitive balancing the privacy and searchability of cloud storage images, thumbnail preserving encryption (TPE) enables users to quickly identify the privacy personal image on the cloud and request this image from the owner through a secure channel. In this paper, we have found that two different plaintext images may produce the same thumbnail. It results in the failure of search strategy because the collision of thumbnail occurs. To address this serious security issues, we conduct an in-depth analysis on the collision probabilities of thumbnails, and then propose a new TPE framework, called multi-factor thumbnail preserving encryption (MFTPE). It starts from the collision probability of two blocks, extend to the probabilities of two images and ultimately to N images. Then, we in detail describe three specific MFTPE constructions preserving different combinations of factors, i.e., the sum and the geometric mean, the sum and the range, and the sum and the weighted mean. The theoretical and experimental results demonstrate that the proposed MFTPE reduces the probability of thumbnails, exhibits strong robustness, and also effectively resists face detection and noise attacks.

cs.CR↗

arXiv2025

RIS-Aided Monitoring With Cooperative Jamming: Design and Performance Analysis

We investigate a reconfigurable intelligent surface (RIS) aided wireless surveillance system. In this system, a monitor not only receives signal from suspicious transmitter via a RIS-enhanced legitimate surveillance (LS) link but also simultaneously takes control of multiple jammers to degrade the quality of received suspicious signal. Under this setup, to enhance monitoring performance requires improvements of both the received signal quality at the monitor and the cooperative jamming (CJ). Considering that the surveillance system is aided by one RIS, whose phase shift optimization involves both channel state information (CSI) of the LS and CJ links, we utilize partial CSI to alleviate the CSI acquisition burden in our design. We propose two RIS-aided monitoring schemes with optimal jammer selection (OJS), and derive their closed-form expressions of surveillance success probability (SSP), respectively. Furthermore, we consider RIS-aided monitoring schemes with random jammer selection as corresponding benchmarks. Thereafter, we analyze special cases where the jammers are using power control to avoid being found, making it appears like passive monitoring. Also, the effect of RIS is highlighted by considering asymptotically large number of RIS elements. Numerical results verify that the proposed OJS strategy further enhances the RIS-aided monitoring performance compared with non-jammer-selection RISLR and RISCR schemes, where the superiority comes at the cost of CSI knowledge and becomes marginal in the region of high jamming power. In addition, the RISLO shows surveillance performance advantage overRISCOwhen the suspicious power is low or when the number of RIS elements is large.

eess.SY↗

arXiv2024

LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration

GraphRAG integrates (knowledge) graphs with large language models (LLMs) to improve reasoning accuracy and contextual relevance. Despite its promising applications and strong relevance to multiple research communities, such as databases and natural language processing, GraphRAG currently lacks modular workflow analysis, systematic solution frameworks, and insightful empirical studies. To bridge these gaps, we propose LEGO-GraphRAG, a modular framework that enables: 1) fine-grained decomposition of the GraphRAG workflow, 2) systematic classification of existing techniques and implemented GraphRAG instances, and 3) creation of new GraphRAG instances. Our framework facilitates comprehensive empirical studies of GraphRAG on large-scale real-world graphs and diverse query sets, revealing insights into balancing reasoning quality, runtime efficiency, and token or GPU cost, that are essential for building advanced GraphRAG systems.

cs.AI↗

arXiv2024

Parf: Adaptive Parameter Refining for Abstract Interpretation

The core challenge in applying abstract interpretation lies in the configuration of abstraction and analysis strategies encoded by a large number of external parameters of static analysis tools. To attain low false-positive rates (i.e., accuracy) while preserving analysis efficiency, tuning the parameters heavily relies on expert knowledge and is thus difficult to automate. In this paper, we present a fully automated framework called Parf to adaptively tune the external parameters of abstract interpretation-based static analyzers. Parf models various types of parameters as random variables subject to probability distributions over latticed parameter spaces. It incrementally refines the probability distributions based on accumulated intermediate results generated by repeatedly sampling and analyzing, thereby ultimately yielding a set of highly accurate parameter settings within a given time budget. We have implemented Parf on top of Frama-C/Eva - an off-the-shelf open-source static analyzer for C programs - and compared it against the expert refinement strategy and Frama-C/Eva's official configurations over the Frama-C OSCS benchmark. Experimental results indicate that Parf achieves the lowest number of false positives on 34/37 (91.9%) program repositories with exclusively best results on 12/37 (32.4%) cases. In particular, Parf exhibits promising performance for analyzing complex, large-scale real-world programs.

cs.LO↗

arXiv2024

Joint Fronthaul Load Balancing and Computation Resource Allocation in Cell-Free User-Centric Massive MIMO Networks

We consider scalable cell-free massive multiple-input multiple-output networks under an open radio access network paradigm comprising user equipments (UEs), radio units (RUs), and decentralized processing units (DUs). UEs are served by dynamically allocated user-centric clusters of RUs. The corresponding cluster processors (implementing the physical layer for each user) are hosted by the DUs as software-defined virtual network functions. Unlike the current literature, mainly focused on the characterization of the user rates under unrestricted fronthaul communication and computation, in this work we explicitly take into account the fronthaul topology, the limited fronthaul communication capacity, and computation constraints at the DUs. In particular, we systematically address the new problem of joint fronthaul load balancing and allocation of the computation resource. As a consequence of our new optimization framework, we present representative numerical results highlighting the existence of an optimal number of quantization bits in the analog-to-digital conversion at the RUs.

cs.IT↗

arXiv2024

PS$^3$: Precise Patch Presence Test based on Semantic Symbolic Signature

During software development, vulnerabilities have posed a significant threat to users. Patches are the most effective way to combat vulnerabilities. In a large-scale software system, testing the presence of a security patch in every affected binary is crucial to ensure system security. Identifying whether a binary has been patched for a known vulnerability is challenging, as there may only be small differences between patched and vulnerable versions. Existing approaches mainly focus on detecting patches that are compiled in the same compiler options. However, it is common for developers to compile programs with very different compiler options in different situations, which causes inaccuracy for existing methods. In this paper, we propose a new approach named PS3, referring to precise patch presence test based on semantic-level symbolic signature. PS3 exploits symbolic emulation to extract signatures that are stable under different compiler options. Then PS3 can precisely test the presence of the patch by comparing the signatures between the reference and the target at semantic level. To evaluate the effectiveness of our approach, we constructed a dataset consisting of 3,631 (CVE, binary) pairs of 62 recent CVEs in four C/C++ projects. The experimental results show that PS3 achieves scores of 0.82, 0.97, and 0.89 in terms of precision, recall, and F1 score, respectively. PS3 outperforms the state-of-the-art baselines by improving 33% in terms of F1 score and remains stable in different compiler options.

cs.SE↗

arXiv2023

Discovering Galaxy Features via Dataset Distillation

In many applications, Neural Nets (NNs) have classification performance on par or even exceeding human capacity. Moreover, it is likely that NNs leverage underlying features that might differ from those humans perceive to classify. Can we "reverse-engineer" pertinent features to enhance our scientific understanding? Here, we apply this idea to the notoriously difficult task of galaxy classification: NNs have reached high performance for this task, but what does a neural net (NN) "see" when it classifies galaxies? Are there morphological features that the human eye might overlook that could help with the task and provide new insights? Can we visualize tracers of early evolution, or additionally incorporated spectral data? We present a novel way to summarize and visualize galaxy morphology through the lens of neural networks, leveraging Dataset Distillation, a recent deep-learning methodology with the primary objective to distill knowledge from a large dataset and condense it into a compact synthetic dataset, such that a model trained on this synthetic dataset achieves performance comparable to a model trained on the full dataset. We curate a class-balanced, medium-size high-confidence version of the Galaxy Zoo 2 dataset, and proceed with dataset distillation from our accurate NN-classifier to create synthesized prototypical images of galaxy morphological features, demonstrating its effectiveness. Of independent interest, we introduce a self-adaptive version of the state-of-the-art Matching Trajectory algorithm to automate the distillation process, and show enhanced performance on computer vision benchmarks.

cs.CV↗

arXiv2022

MSE-Based Transceiver Designs for RIS-Aided Communications With Hardware Impairments

It is challenging to precisely configure the phase shifts of the reflecting elements at the reconfigurable intelligent surface (RIS) due to inherent hardware impairments (HIs). In this paper, the mean square error (MSE) performance is investigated in an RIS-aided single-user multiple-input multipleoutput (MIMO) communication system with transceiver HIs and RIS phase noise. We aim to jointly optimize the transmit precoder, linear received equalizer, and RIS reflecting matrices to minimize the MSE. To tackle this problem, an iterative algorithm is proposed, wherein the beamforming matrices are alternately optimized. Specifically, for the beamforming optimization subproblem, we derive the closed-form expression of the optimal precoder and equalizer matrices. Then, for the phase shift optimization subproblem, an efficient algorithm based on the majorization-minimization (MM) method is proposed. Simulation results show that the proposed MSE-based RIS-aided transceiver scheme dramatically outperforms the conventional system algorithms that do not consider HIs at both the transceiver and the RIS.

cs.IT↗

arXiv2021

Energy Efficient Reconfigurable Intelligent Surface Enabled Mobile Edge Computing Networks with NOMA

Reconfigurable intelligent surface (RIS) has emerged as a promising technology for achieving high spectrum and energy efficiency in future wireless communication networks. In this paper, we investigate an RIS-aided single-cell multi-user mobile edge computing (MEC) system where an RIS is deployed to support the communication between a base station (BS) equipped with MEC servers and multiple single-antenna users. To utilize the scarce frequency resource efficiently, we assume that users communicate with BS based on a non-orthogonal multiple access (NOMA) protocol. Each user has a computation task which can be computed locally or partially/fully offloaded to the BS. We aim to minimize the sum energy consumption of all users by jointly optimizing the passive phase shifters, the size of transmission data, transmission rate, power control, transmission time and the decoding order. Since the resulting problem is non-convex, we use the block coordinate descent method to alternately optimize two separated subproblems. More specifically, we use the dual method to tackle a subproblem with given phase shift and obtain the closed-form solution; and then we utilize penalty method to solve another subproblem for given power control. Moreover, in order to demonstrate the effectiveness of our proposed algorithm, we propose three benchmark schemes: the time-division multiple access (TDMA)-MEC scheme, the full local computing scheme and the full offloading scheme. We use an alternating 1-D search method and the dual method that can solve the TDMA-based transmission problem well. Numerical results demonstrate that the proposed scheme can increase the energy efficiency and achieve significant performance gains over the three benchmark schemes.

cs.IT↗

arXiv2021

Improvement of Normal Estimation for PointClouds via Simplifying Surface Fitting

With the burst development of neural networks in recent years, the task of normal estimation has once again become a concern. By introducing the neural networks to classic methods based on problem-specific knowledge, the adaptability of the normal estimation algorithm to noise and scale has been greatly improved. However, the compatibility between neural networks and the traditional methods has not been considered. Similar to the principle of Occam's razor, that is, the simpler is better. We observe that a more simplified process of surface fitting can significantly improve the accuracy of the normal estimation. In this paper, two simple-yet-effective strategies are proposed to address the compatibility between the neural networks and surface fitting process to improve normal estimation. Firstly, a dynamic top-k selection strategy is introduced to better focus on the most critical points of a given patch, and the points selected by our learning method tend to fit a surface by way of a simple tangent plane, which can dramatically improve the normal estimation results of patches with sharp corners or complex patterns. Then, we propose a point update strategy before local surface fitting, which smooths the sharp boundary of the patch to simplify the surface fitting process, significantly reducing the fitting distortion and improving the accuracy of the predicted point normal. The experiments analyze the effectiveness of our proposed strategies and demonstrate that our method achieves SOTA results with the advantage of higher estimation accuracy over most existed approaches.

cs.CV↗

arXiv2021

Fast and Accurate Normal Estimation for Point Cloud via Patch Stitching

This paper presents an effective normal estimation method adopting multi-patch stitching for an unstructured point cloud. The majority of learning-based approaches encode a local patch around each point of a whole model and estimate the normals in a point-by-point manner. In contrast, we suggest a more efficient pipeline, in which we introduce a patch-level normal estimation architecture to process a series of overlapping patches. Additionally, a multi-normal selection method based on weights, dubbed as multi-patch stitching, integrates the normals from the overlapping patches. To reduce the adverse effects of sharp corners or noise in a patch, we introduce an adaptive local feature aggregation layer to focus on an anisotropic neighborhood. We then utilize a multi-branch planar experts module to break the mutual influence between underlying piecewise surfaces in a patch. At the stitching stage, we use the learned weights of multi-branch planar experts and distance weights between points to select the best normal from the overlapping parts. Furthermore, we put forward constructing a sparse matrix representation to reduce large-scale retrieval overheads for the loop iterations dramatically. Extensive experiments demonstrate that our method achieves SOTA results with the advantage of lower computational costs and higher robustness to noise over most of the existing approaches.

cs.CV↗

arXiv2020

Reflections in the Sky: Joint Trajectory and Passive Beamforming Design for Secure UAV Networks with Reconfigurable Intelligent Surface

This paper investigates the problem of secure energy efficiency maximization for a reconfigurable intelligent surface (RIS) assisted uplink wireless communication system, where an unmanned aerial vehicle (UAV) equipped with an RIS works as a mobile relay between the base station (BS) and a group of users. We focus on maximizing the secure energy efficiency of the system via jointly optimizing the UAV's trajectory, the RIS's phase shift, users' association and transmit power. To tackle this problem, we divide the original problem into three sub-problems, and propose an efficient iterative algorithm. In particular, the successive convex approximation method (SCA) is applied to solve the nonconvex UAV trajectory, the RIS's phase shift, and transmit power optimization sub-problems. We further provide two schemes to simplify the solution of phase and trajectory sub-problem. Simulation results demonstrate that the proposed algorithm converges fast, and the proposed design can enhance the secure energy efficiency by up to 38\% gains, as compared to the traditional schemes without any RIS.

eess.SP↗