Peilin Zheng

Zhe Chen, Peilin Zheng, Wenshuo Chen et al.

Creating functional Digital Twins, simulatable 3D replicas of the real world, is a central challenge in computer vision. Current methods like NeRF produce visually rich but functionally incomplete twins. The key barrier is the lack of underlying material properties (e.g., permittivity, conductivity). Acquiring this information for every point in a scene via non-contact, non-invasive sensing is a primary goal, but it demands solving a notoriously ill-posed physical inversion problem. Standard remote signals, like images and radio frequencies (RF), deeply entangle the unknown geometry, ambient field, and target materials. We introduce NEMF, a novel framework for dense, non-invasive physical inversion designed to build functional digital twins. Our key insight is a systematic disentanglement strategy. NEMF leverages high-fidelity geometry from images as a powerful anchor, which first enables the resolution of the ambient field. By constraining both geometry and field using only non-invasive data, the original ill-posed problem transforms into a well-posed, physics-supervised learning task. This transformation unlocks our core inversion module: a decoder. Guided by ambient RF signals and a differentiable layer incorporating physical reflection models, it learns to explicitly output a continuous, spatially-varying field of the scene's underlying material parameters. We validate our framework on high-fidelity synthetic datasets. Experiments show our non-invasive inversion reconstructs these material maps with high accuracy, and the resulting functional twin enables high-fidelity physical simulation. This advance moves beyond passive visual replicas, enabling the creation of truly functional and simulatable models of the physical world.

Bowei Su, Mingxi Ye, Yuhong Na et al.

The Solidity smart contract ecosystem has rapidly grown, leading to multiple compilers targeting different blockchain platforms or improving compilation efficiency. Although many compilers aim to be compatible with the primary Solidity compiler (Solc), significant inconsistencies in compilation and execution remain. These inconsistencies hinder contract migration, mislead developers during debugging, and may introduce exploitable vulnerabilities, causing financial losses. Existing testing techniques mainly focus on bugs within a single compiler or perform differential testing in the same execution environment. However, they are insufficient for detecting cross-compiler inconsistencies, as they lack mechanisms to explore triggering conditions and compare bytecode across environments. We propose ParityFuzz, a cross-compiler differential testing framework for Solidity. It operates in three stages. First, it derives mutation rules, including syntax- and boundary-oriented rules, by analyzing compilers and execution environments. Second, it uses reinforcement learning to select effective mutation rules for test generation. Third, it compiles and executes programs across multiple compilers, then normalizes and compares results to detect inconsistencies. Our evaluation shows ParityFuzz is efficient and effective. It achieves up to 18x higher compilation success rate and 1.8x higher code coverage than state-of-the-art fuzzers. It uncovers 64 previously unknown inconsistencies across six compilers. Notably, 11 issues have been fixed, and our findings received a bounty from the Polkadot community.

Xiucheng Wang, Peilin Zheng, Nan Cheng

In this paper, a signal detection method based on the denoise diffusion model (DM) is proposed, which outperforms the maximum likelihood (ML) estimation method that has long been regarded as the optimal signal detection technique. Theoretically, a novel mathematical theory for intelligent signal detection based on stochastic differential equations (SDEs) is established in this paper, demonstrating the effectiveness of DM in reducing the additive white Gaussian noise in received signals. Moreover, a mathematical relationship between the signal-to-noise ratio (SNR) and the timestep in DM is established, revealing that for any given SNR, a corresponding optimal timestep can be identified. Furthermore, to address potential issues with out-of-distribution inputs in the DM, we employ a mathematical scaling technique that allows the trained DM to handle signal detection across a wide range of SNRs without any fine-tuning. Building on the above theoretical foundation, we propose a DM-based signal detection method, with the diffusion transformer (DiT) serving as the backbone neural network, whose computational complexity of this method is $\mathcal{O}(n^2)$. Simulation results demonstrate that, for BPSK and QAM modulation schemes, the DM-based method achieves a significantly lower symbol error rate (SER) compared to ML estimation, while maintaining a much lower computational complexity.

Weilin Zheng, Zibin Zheng, Hong-Ning Dai et al.

Blockchain-based cryptocurrencies and applications have flourished in blockchain research community. Massive data generated from diverse blockchain systems bring not only huge business values but also technological challenges in data analytics of heterogeneous blockchain data. Different from Bitcoin and Ethereum, EOSIO has richer diversity and a higher volume of blockchain data due to its unique architectural design in resource management, consensus scheme and high throughput. Despite its popularity (e.g., 89,800,000 blocks generated till November 14, 2019 since its launch on June 8, 2018), few studies have been made on data analysis of EOSIO. To fill this gap, we collect and process the up-to-date on-chain data from EOSIO. We name these well-processed EOSIO datasets as XBlock-EOS, which consists of 7 well-processed datasets: 1) Block, Transaction and Action, 2) Internal and External EOS Transfer Action, 3) Contract Information, 4) Contract Invocation, 5) Token Action, 6) Account Creation, 7) Resource Management. It is challenging to process and analyze a high volume of raw EOSIO data and establish the mapping from original raw data to the well-grained datasets since it requires substantial efforts in extracting various types of data as well as sophisticated knowledge on software engineering and data analytics. Meanwhile, we present statistics and exploration on these datasets. Moreover, we also outline the possible research opportunities based on XBlock-EOS.

Peilin Zheng, Zibin Zheng, Hong-ning Dai

Blockchain-based cryptocurrencies have received extensive attention recently. Massive data has been stored on permission-less blockchains. The analysis on massive blockchain data can bring huge business values. However, the lack of well-processed up-to-date blockchain datasets impedes big data analytics of blockchain data. To fill this gap, we collect and process the up-to-date on-chain data from Ethereum, which is one of the most popular permission-less blockchains. We name these well-processed Ethereum datasets as XBlock-ETH, which consists of the data of blockchain transactions, smart contracts, and cryptocurrencies (i.e., tokens). The basic statistics and exploration of these datasets are presented. We also outline the possible research opportunities. The datasets with the raw data and codes have been publicly released online.

Peilin Zheng, Zibin Zheng, Liang Chen

Blockchain and blockchain-based decentralized applications are attracting increasing attentions recently. In public blockchain systems, users usually connect to third-party peers or run a peer to join the P2P blockchain network. However, connecting to unreliable blockchain peers will make users waste resources and even lose millions of dollars of cryptocurrencies. In order to select the reliable blockchain peers, it is urgently needed to evaluate and predict the reliability of them. Faced with this problem, we propose H-BRP, Hybrid Blockchain Reliability Prediction model to extract the blockchain reliability factors then make personalized prediction for each user. Large-scale real-world experiments are conducted on 100 blockchain requesters and 200 blockchain peers. The implement and dataset of 2,000,000 test cases are released. The experimental results show that the proposed model obtains better accuracy than other approaches.