arXiv subjects

Peilun Li

Publications and source records attributed to Peilun Li.

10 recordsLinked to original sources

arXiv2026

Identify Then Project: Contrastive Learning of Latent Dynamics from Partial Observations with Port-Hamiltonian Structure

Identifying latent state representations and dynamics is essential when direct modeling in observation space is infeasible, particularly under partial and high-dimensional observations. In such settings, representation learning and physics-aware modeling are inherently coupled. We study this problem for latent port-Hamiltonian systems, a structured class encompassing both conservative and dissipative dynamics. We propose a two-stage identify-then-project framework. First, a contrastive teacher learns continuous-time latent dynamics from partial observations. Then, a student projects the identified teacher representation and dynamics onto a port-Hamiltonian submanifold via a learned affine chart, yielding a physically consistent realization. As a conceptual counterfactual, we also consider a single-stage variant that jointly learns latent identification and port-Hamiltonian structure, but find it to be less reliable, motivating the proposed two-stage teacher-student framework. We show theoretically that affine projection is the natural bridge between the affine gauge of contrastive latent identification and the port-Hamiltonian systems. Empirically, we demonstrate that the proposed two-stage approach preserves the teacher's dynamics while enforcing physical structure, and performs more reliably than the single-stage alternative, particularly in dissipative regimes and high-dimensional visual settings.

cs.LG↗

arXiv2026

PHDME: Physics-Informed Diffusion Models without Explicit Governing Equations

Diffusion models provide expressive priors for forecasting trajectories of dynamical systems, but are typically unreliable in the sparse data regime. Physics-informed machine learning (PIML) improves reliability in such settings; however, most methods require \emph{explicit governing equations} during training, which are often only partially known due to complex and nonlinear dynamics. We introduce \textbf{PHDME}, a port-Hamiltonian diffusion framework designed for \emph{sparse observations} and \emph{incomplete physics}. PHDME leverages port-Hamiltonian structural prior but does not require full knowledge of the closed-form governing equations. Our approach first trains a Gaussian process distributed Port-Hamiltonian system (GP-dPHS) on limited observations to capture an energy-based representation of the dynamics. The GP-dPHS is then used to generate a physically consistent artificial dataset for diffusion training, and to inform the diffusion model with a structured physics residual loss. After training, the diffusion model acts as an amortized sampler and forecaster for fast trajectory generation. Finally, we apply split conformal calibration to provide uncertainty statements for the generated predictions. Experiments on PDE benchmarks and a real-world spring system show improved accuracy and physical consistency under data scarcity.

cs.LG↗

arXiv2025

Solving Unit Commitment Problems with Graph Neural Network based Initial Commitment Prediction and Large Neighborhood Search

Unit commitment problem (UCP) is a critical component of power market decision-making. However, its computational complexity necessitates effi-cient solution methods. In this work we propose a framework to accelerate the solving process of the UCP, and the data collecting process for two dis-tinct graph neural network (GNN) policy. We at first train a Neural Initial Commitment Prediction policy to obtain an initial commitment for UCP. Sec-ond, a heuristic process is introduced to restore the feasibility of the initial commitment. Third, get the neighborhood based on the initial prediction then neighborhood search to improve the commitment. At last, we train a Neural neighborhood Prediction policy to predict the neighborhood of the incum-bent commitment at each iteration, continuously optimizing the commitment until the stopping condition is met. This approach produces high-quality ini-tial commitments that can be iteratively refined to meet higher accuracy re-quirements. The experimental results show that the GNN policies trained on the 80-unit system outperform commercial solvers on a 1080-unit system, and LNS performs better than commercial solver on more complex instanc-es.

math.OC↗

arXiv2025

Plug-and-Play Physics-informed Learning using Uncertainty Quantified Port-Hamiltonian Models

The ability to predict trajectories of surrounding agents and obstacles is a crucial component in many robotic applications. Data-driven approaches are commonly adopted for state prediction in scenarios where the underlying dynamics are unknown. However, the performance, reliability, and uncertainty of data-driven predictors become compromised when encountering out-of-distribution observations relative to the training data. In this paper, we introduce a Plug-and-Play Physics-Informed Machine Learning (PnP-PIML) framework to address this challenge. Our method employs conformal prediction to identify outlier dynamics and, in that case, switches from a nominal predictor to a physics-consistent model, namely distributed Port-Hamiltonian systems (dPHS). We leverage Gaussian processes to model the energy function of the dPHS, enabling not only the learning of system dynamics but also the quantification of predictive uncertainty through its Bayesian nature. In this way, the proposed framework produces reliable physics-informed predictions even for the out-of-distribution scenarios.

cs.RO↗

arXiv2024

IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems

As large language model (LLM) agents increasingly integrate into our infrastructure, their robust coordination and message synchronization become vital. The Byzantine Generals Problem (BGP) is a critical model for constructing resilient multi-agent systems (MAS) under adversarial attacks. It describes a scenario where malicious agents with unknown identities exist in the system-situations that, in our context, could result from LLM agents' hallucinations or external attacks. In BGP, the objective of the entire system is to reach a consensus on the action to be taken. Traditional BGP requires global consensus among all agents; however, in practical scenarios, global consensus is not always necessary and can even be inefficient. Therefore, there is a pressing need to explore a refined version of BGP that aligns with the local coordination patterns observed in MAS. We refer to this refined version as Imperfect BGP (IBGP) in our research, aiming to address this discrepancy. To tackle this issue, we propose a framework that leverages consensus protocols within general MAS settings, providing provable resilience against communication attacks and adaptability to changing environments, as validated by empirical results. Additionally, we present a case study in a sensor network environment to illustrate the practical application of our protocol.

cs.MA↗

arXiv2024

Physics-Constrained Learning for PDE Systems with Uncertainty Quantified Port-Hamiltonian Models

Modeling the dynamics of flexible objects has become an emerging topic in the community as these objects become more present in many applications, e.g., soft robotics. Due to the properties of flexible materials, the movements of soft objects are often highly nonlinear and, thus, complex to predict. Data-driven approaches seem promising for modeling those complex dynamics but often neglect basic physical principles, which consequently makes them untrustworthy and limits generalization. To address this problem, we propose a physics-constrained learning method that combines powerful learning tools and reliable physical models. Our method leverages the data collected from observations by sending them into a Gaussian process that is physically constrained by a distributed Port-Hamiltonian model. Based on the Bayesian nature of the Gaussian process, we not only learn the dynamics of the system, but also enable uncertainty quantification. Furthermore, the proposed approach preserves the compositional nature of Port-Hamiltonian systems.

cs.LG↗

arXiv2023

Parallel and Asynchronous Smart Contract Execution

Today's blockchains suffer from low throughput and high latency, which impedes their widespread adoption of more complex applications like smart contracts. In this paper, we propose a novel paradigm for smart contract execution. It distinguishes between consensus nodes and execution nodes: different groups of execution nodes can execute transactions in parallel; meanwhile, consensus nodes can asynchronously order transactions and process execution results. Moreover, it requires no coordination among execution nodes and can effectively prevent livelocks. We show two ways of applying this paradigm to blockchains. First, we show how we can make Ethereum support parallel and asynchronous contract execution \emph{without hard-forks}. Then, we propose a new public, permissionless blockchain. Our benchmark shows that, with a fast consensus layer, it can provide a high throughput even for complex transactions like Cryptokitties gene mixing. It can also protect simple transactions from being starved by complex transactions.

cs.CR↗

arXiv2018

Scaling Nakamoto Consensus to Thousands of Transactions per Second

This paper presents Conflux, a fast, scalable and decentralized blockchain system that optimistically process concurrent blocks without discarding any as forks. The Conflux consensus protocol represents relationships between blocks as a direct acyclic graph and achieves consensus on a total order of the blocks. Conflux then, from the block order, deterministically derives a transaction total order as the blockchain ledger. We evaluated Conflux on Amazon EC2 clusters with up to 20k full nodes. Conflux achieves a transaction throughput of 5.76GB/h while confirming transactions in 4.5-7.4 minutes. The throughput is equivalent to 6400 transactions per second for typical Bitcoin transactions. Our results also indicate that when running Conflux, the consensus protocol is no longer the throughput bottleneck. The bottleneck is instead at the processing capability of individual nodes.

cs.DC↗

arXiv2018

Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption

Recent advances in vision tasks (e.g., segmentation) highly depend on the availability of large-scale real-world image annotations obtained by cumbersome human labors. Moreover, the perception performance often drops significantly for new scenarios, due to the poor generalization capability of models trained on limited and biased annotations. In this work, we resort to transfer knowledge from automatically rendered scene annotations in virtual-world to facilitate real-world visual tasks. Although virtual-world annotations can be ideally diverse and unlimited, the discrepant data distributions between virtual and real-world make it challenging for knowledge transferring. We thus propose a novel Semantic-aware Grad-GAN (SG-GAN) to perform virtual-to-real domain adaption with the ability of retaining vital semantic information. Beyond the simple holistic color/texture transformation achieved by prior works, SG-GAN successfully personalizes the appearance adaption for each semantic region in order to preserve their key characteristic for better recognition. It presents two main contributions to traditional GANs: 1) a soft gradient-sensitive objective for keeping semantic boundaries; 2) a semantic-aware discriminator for validating the fidelity of personalized adaptions with respect to each semantic region. Qualitative and quantitative experiments demonstrate the superiority of our SG-GAN in scene adaption over state-of-the-art GANs. Further evaluations on semantic segmentation on Cityscapes show using adapted virtual images by SG-GAN dramatically improves segmentation performance than original virtual data. We release our code at https://github.com/Peilun-Li/SG-GAN.

cs.CV↗

arXiv2018

Gosig: Scalable Byzantine Consensus on Adversarial Wide Area Network for Blockchains

Existing Byzantine fault tolerance (BFT) protocols face significant challenges in the consortium blockchain scenario. On the one hand, we can make little assumptions about the reliability and security of the underlying Internet. On the other hand, the applications on consortium blockchains demand a system as scalable as the Bit-coin but providing much higher performance, as well as provable safety. We present a new BFT protocol, Gosig, that combines crypto-based secret leader selection and multi-round voting in the protocol layer with implementation layer optimizations such as gossip-based message propagation. In particular, Gosig guarantees safety even in a network fully controlled by adversaries, while providing provable liveness with easy-to-achieve network connectivity assumption. On a wide area testbed consisting of 140 Amazon EC2 servers spanning 14 cities on five continents, we show that Gosig can achieve over 4,000 transactions per second with less than 1 minute transaction confirmation time.

cs.DC↗