BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Zheng Yang

Zheng Yang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer Visioneess.SPProgramming LanguagesArtificial IntelligenceDistributed, Parallel, and Cluster ComputingHuman-Computer InteractionInformation TheoryMachine Learningmath.ITNetworking and Internet Architecturephysics.optics

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
12works
0followers
11topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

12 published item(s)

preprint2026arXiv

HCInfer: An Efficient Inference System via Error Compensation for Resource-Constrained Devices

LLMs often struggle with memory-constrained deployment on consumer-grade hardware due to their massive parameter sizes. While existing solutions such as model compression and offloading improve deployment feasibility, they often suffer from substantial accuracy degradation or severe throughput bottlenecks. Recent error compensation methods recover accuracy through auxiliary LoRA-style branches, and we observe that these branches are inherently amenable to offloading: they require substantial parameter storage but access only a small subset of compensation parameters during each inference step. Motivated by this opportunity, we propose HCInfer, a heterogeneous inference system that offloads residual compensation to the CPU while executing the compressed backbone on the GPU, and further introduces an asynchronous compensation pipeline and sensitivity-aware dynamic rank allocation to hide compensation overhead and maximize accuracy recovery. Experimental results show that HCInfer achieves a maximum accuracy improvement of 5.2% on downstream tasks compared to compression model and sustaining a maximum speedup of 10.4x compared to full-precision model.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

CLRNet: Cross Layer Refinement Network for Lane Detection

Lane is critical in the vision navigation system of the intelligent vehicle. Naturally, lane is a traffic sign with high-level semantics, whereas it owns the specific local pattern which needs detailed low-level features to localize accurately. Using different feature levels is of great importance for accurate lane detection, but it is still under-explored. In this work, we present Cross Layer Refinement Network (CLRNet) aiming at fully utilizing both high-level and low-level features in lane detection. In particular, it first detects lanes with high-level semantic features then performs refinement based on low-level features. In this way, we can exploit more contextual information to detect lanes while leveraging local detailed lane features to improve localization accuracy. We present ROIGather to gather global context, which further enhances the feature representation of lanes. In addition to our novel network design, we introduce Line IoU loss which regresses the lane line as a whole unit to improve the localization accuracy. Experiments demonstrate that the proposed method greatly outperforms the state-of-the-art lane detection approaches.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection

Monocular 3D detection has drawn much attention from the community due to its low cost and setup simplicity. It takes an RGB image as input and predicts 3D boxes in the 3D space. The most challenging sub-task lies in the instance depth estimation. Previous works usually use a direct estimation method. However, in this paper we point out that the instance depth on the RGB image is non-intuitive. It is coupled by visual depth clues and instance attribute clues, making it hard to be directly learned in the network. Therefore, we propose to reformulate the instance depth to the combination of the instance visual surface depth (visual depth) and the instance attribute depth (attribute depth). The visual depth is related to objects' appearances and positions on the image. By contrast, the attribute depth relies on objects' inherent attributes, which are invariant to the object affine transformation on the image. Correspondingly, we decouple the 3D location uncertainty into visual depth uncertainty and attribute depth uncertainty. By combining different types of depths and associated uncertainties, we can obtain the final instance depth. Furthermore, data augmentation in monocular 3D detection is usually limited due to the physical nature, hindering the boost of performance. Based on the proposed instance depth disentanglement strategy, we can alleviate this problem. Evaluated on KITTI, our method achieves new state-of-the-art results, and extensive ablation studies validate the effectiveness of each component in our method. The codes are released at https://github.com/SPengLiang/DID-M3D.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Dual Power Spectrum Manifold and Toeplitz HPD Manifold: Enhancement and Analysis for Matrix CFAR Detection

Recently, an innovative matrix CFAR detection scheme based on information geometry, also referred to as the geometric detector, has been developed speedily and exhibits distinct advantages in several practical applications. These advantages benefit from the geometry of the Toeplitz Hermitian positive definite (HPD) manifold $\mathcal{M}_{\mathcal{T}H_{++}}$, but the sophisticated geometry also results in some challenges for geometric detectors, such as the implementation of the enhanced detector to improve the SCR (signal-to-clutter ratio) and the analysis of the detection performance. To meet these challenges, this paper develops the dual power spectrum manifold $\mathcal{M}_{\text{P}}$ as the dual space of $\mathcal{M}_{\mathcal{T}H_{++}}$. For each affine invariant geometric measure on $\mathcal{M}_{\mathcal{T}H_{++}}$, we show that there exists an equivalent function named induced potential function on $\mathcal{M}_{\text{P}}$. By the induced potential function, the measurements of the dissimilarity between two matrices can be implemented on $\mathcal{M}_{\text{P}}$, and the geometric detectors can be reformulated as the form related to the power spectrum. The induced potential function leads to two contributions: 1) The enhancement of the geometric detector, which is formulated as an optimization problem concerning $\mathcal{M}_{\mathcal{T}H_{++}}$, is transformed to an equivalent and simpler optimization on $\mathcal{M}_{\text{P}}$. In the presented example of the enhancement, the closed-form solution, instead of the gradient descent method, is provided through the equivalent optimization. 2) The detection performance is analyzed based on $\mathcal{M}_{\text{P}}$, and the advantageous characteristics, which benefit the detection performance, can be deduced by analyzing the corresponding power spectrum to the maximal point of the induced potential function.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Hands-on Wireless Sensing with Wi-Fi: A Tutorial

With the rapid development of wireless communication technology, wireless access points (AP) and internet of things (IoT) devices have been widely deployed in our surroundings. Various types of wireless signals (e.g., Wi-Fi, LoRa, LTE) are filling out our living and working spaces. Previous researches reveal the fact that radio waves are modulated by the spatial structure during the propagation process (e.g., reflection, diffraction, and scattering) and superimposed on the receiver. This observation allows us to reconstruct the surrounding environment based on received wireless signals, called "wireless sensing". Wireless sensing is an emerging technology that enables a wide range of applications, such as gesture recognition for human-computer interaction, vital signs monitoring for health care, and intrusion detection for security management. Compared with other sensing paradigms, such as vision-based and IMU-based sensing, wireless sensing solutions have unique advantages such as high coverage, pervasiveness, low cost, and robustness under adverse light and texture scenarios. Besides, wireless sensing solutions are generally lightweight in terms of both computation overhead and device size. This tutorial takes Wi-Fi sensing as an example. It introduces both the theoretical principles and the code implementation of data collection, signal processing, features extraction, and model design. In addition, this tutorial highlights state-of-the-art deep learning models (e.g., CNN, RNN, and adversarial learning models) and their applications in wireless sensing systems. We hope this tutorial will help people in other research fields to break into wireless sensing research and learn more about its theories, designs, and implementation skills, promoting prosperity in the wireless sensing research field.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Nonreciprocal light propagation induced by a subwavelength spinning cylinder

Nonreciprocal optical devices have broad applications in light manipulations for communications and sensing. Non-magnetic mechanisms of optical nonreciprocity are highly desired for high-frequency on-chip applications. Here, we investigate the nonreciprocal properties of light propagation in a dielectric waveguide induced by a subwavelength spinning cylinder. We find that the chiral modes of the cylinder can give rise to unidirectional coupling with the waveguide via the transverse spin-orbit interaction, leading to different transmissions for guided wave propagating in opposite directions and thus optical isolation. We reveal the dependence of the nonreciprocal properties on various system parameters including mode order, spinning speed, and coupling distance. The results show that higher-order chiral modes and larger spinning speed generally give rise to stronger nonreciprocity, and there exists an optimal cylinder-waveguide coupling distance where the optical isolation reaches the maximum. Our work contributes to the understanding of nonreciprocity in subwavelength moving structures and can find applications in integrated photonic circuits, topological photonics, and novel metasurfaces.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection

Monocular 3D object detection is one of the most challenging tasks in 3D scene understanding. Due to the ill-posed nature of monocular imagery, existing monocular 3D detection methods highly rely on training with the manually annotated 3D box labels on the LiDAR point clouds. This annotation process is very laborious and expensive. To dispense with the reliance on 3D box labels, in this paper we explore the weakly supervised monocular 3D detection. Specifically, we first detect 2D boxes on the image. Then, we adopt the generated 2D boxes to select corresponding RoI LiDAR points as the weak supervision. Eventually, we adopt a network to predict 3D boxes which can tightly align with associated RoI LiDAR points. This network is learned by minimizing our newly-proposed 3D alignment loss between the 3D box estimates and the corresponding RoI LiDAR points. We will illustrate the potential challenges of the above learning problem and resolve these challenges by introducing several effective designs into our method. Codes will be available at https://github.com/SPengLiang/WeakM3D.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Lolisa: Formal syntax and semantics for a subset of the solidity programming language in Mathematical Tool Coq

This article presents the formal syntax and semantics for a large subset of the Solidity programming language developed for the Etheruem blockchain platform based on our resent work about developing a general, extensible, and reusable formal memory (GERM) framework and an extension of Curry-Howard isomorphism, denoted as execution-verification isomorphism (EVI). This subset is denoted as Lolisa, which, to our knowledge, is the first mechanized and validated formal syntax and semantics developed for Solidity. The formal syntax of Lolisa adopts a stronger static type system than Solidity for enhanced type safety. In addition, Lolisa not only includes nearly all the syntax components of Solidity, such as mapping, modifier, contract, and address types, but it also contains general-purpose programming language features, such as multiple return values, pointer arithmetic, struct, and field access. Therefore, the inherent compatibility of Lolisa allows Solidity programs to be directly translated into Lolisa with a line-by-line correspondence without rebuilding or abstracting, and, in addition, the inherent generality of Lolisa allows it to be extended to express other programming languages as well. To this end, we also present a preliminary scheme for extending Lolisa to other languages systematically.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Hybrid Formal Verification System in Coq for Ensuring the Reliability and Security of Ethereum-based Service Smart Contracts

This paper reports on the development of a formal symbolic process virtual machine (FSPVM) denoted as FSPVM-E for verifying the reliability and security of Ethereum-based services at the source code level of smart contracts, and a Coq proof assistant is employed for both programming the system and for proving its correctness. The current version of FSPVM-E adopts execution-verification isomorphism, which is an application extension of Curry-Howard isomorphism, as its fundamental theoretical framework to combine symbolic execution and higher-order logic theorem proving. The four primary components of FSPVM-E include a general, extensible, and reusable formal memory framework, an extensible and universal formal intermediate programming language denoted as Lolisa, which is a large subset of the Solidity programming language using generalized algebraic datatypes, the corresponding formally verified interpreter of Lolisa, denoted as FEther, and assistant tools and libraries. The self-correctness of all components is certified in Coq. Currently, FSPVM-E supports the ERC20 token standard, and can automatically and symbolically execute Ethereum-based smart contracts, scan their standard vulnerabilities, and verify their reliability and security properties with Hoare-style logic in Coq. To the best of authors' knowledge, the present work represents the first hybrid formal verification system implemented in Coq for Ethereum smart contracts that is applied at the Solidity source code level.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds

3D object detection based on point clouds has become more and more popular. Some methods propose localizing 3D objects directly from raw point clouds to avoid information loss. However, these methods come with complex structures and significant computational overhead, limiting its broader application in real-time scenarios. Some methods choose to transform the point cloud data into compact tensors first and leverage off-the-shelf 2D detectors to propose 3D objects, which is much faster and achieves state-of-the-art results. However, because of the inconsistency between 2D and 3D data, we argue that the performance of compact tensor-based 3D detectors is restricted if we use 2D detectors without corresponding modification. Specifically, the distribution of point clouds is uneven, with most points gather on the boundary of objects, while detectors for 2D data always extract features evenly. Motivated by this observation, we propose DENse Feature Indicator (DENFI), a universal module that helps 3D detectors focus on the densest region of the point clouds in a boundary-aware manner. Moreover, DENFI is lightweight and guarantees real-time speed when applied to 3D object detectors. Experiments on KITTI dataset show that DENFI improves the performance of the baseline single-stage detector remarkably, which achieves new state-of-the-art performance among previous 3D detectors, including both two-stage and multi-sensor fusion methods, in terms of mAP with a 34FPS detection speed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

PAS: Prediction-based Adaptive Sleeping for Environment Monitoring in Sensor Networks

Energy efficiency has proven to be an important factor dominating the working period of WSN surveillance systems. Intensive studies have been done to provide energy efficient power management mechanisms. In this paper, we present PAS, a Prediction-based Adaptive Sleeping mechanism for environment monitoring sensor networks to conserve energy. PAS focuses on the diffusion stimulus (DS) scenario, which is very common and important in the application of environment monitoring. Different with most of previous works, PAS explores the features of DS spreading process to obtain higher energy efficiency. In PAS, sensors determine their sleeping schedules based on the observed emergency of DS spreading. While sensors near the DS boundary stay awake to accurately capture the possible stimulus arrival, the far away sensors turn into sleeping mode to conserve energy. Simulation experiment shows that PAS largely reduces the energy cost without decreasing system performance

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Reconfigurable Intelligent Surfaces Assisted Communications with Discrete Phase Shifts: How Many Quantization Levels are Required to Achieve Full Diversity?

Due to hardware limitations, the phase shifts of the reflecting elements of reconfigurable intelligent surfaces (RISs) need to be quantized into discrete values. This letter aims to unveil the minimum required number of phase quantization levels $L$ in order to achieve the full diversity order in RIS-assisted wireless communication systems. With the aid of an upper bound of the outage probability, we first prove that the full diversity order is achievable provided that $L$ is not less than three. If $L=2$, on the other hand, we prove that the achievable diversity order cannot exceed $(N+1)/2$, where $N$ is the number of reflecting elements. This is obtained with the aid of a lower bound of the outage probability. Therefore, we prove that the minimum required value of $L$ to achieve the full diversity order is $L=3$. Simulation results verify the theoretical analysis and the impact of phase quantization levels on RIS-assisted communication systems.

0 citations0 reviewsNo code linkedOpen access