arXiv subjects

Lipeng Wan

Publications and source records attributed to Lipeng Wan.

At least 19 recordsLinked to original sources

arXiv2026

Valley-locked Optical Spin Merons in Valley Photonic Crystal Waveguides

Optical skyrmionic textures, including N\'eel-type skyrmions and merons, have attracted significant attention across diverse physical systems for their promising applications in ultra-precise metrology, optical information processing, and quantum technologies. However, the lack of an effective approach for their on-chip directional transport and manipulation impedes their applications in photonic integrated devices. Here, we numerically demonstrate a photonic platform that utilizes topologically protected valley edge state to achieve robust on-chip directional transport of optical spin merons. These merons originate from spin-orbit coupling within the evanescent field at the valley photonic crystal surface and exist as eigenstates of the topologically protected edge state, ensuring their robust propagation even in the interface with defects. Leveraging the valley degree of freedom of topological edge states, we further achieve valley-locked spin merons, enabling flexible control over the polarity of spin merons. By endowing spin merons with topological protection in momentum space, our work provides an approach for robust on-chip transport and manipulation of spin merons, thereby paving the way for expanding their application in photonic systems.

physics.optics↗

arXiv2026

Progressive Refinement Regulation for Accelerating Diffusion Language Model Decoding

Diffusion language models generate text through iterative denoising under a uniform refinement rule applied to all tokens. However, tokens stabilize at different rates in practice, leading to substantial redundant refinement and motivating refinement control over the denoising process. Existing approaches typically assess refinement necessity from instantaneous, step-level signals under a fixed decoding process. In contrast, whether a token has converged is defined by how its prediction changes along its future refinement trajectory. Moreover, changing the refinement rule reshapes future refinement trajectories, which in turn determine how refinement rules should be formulated, making refinement control inherently dynamic. We propose \emph{Progressive Refinement Regulation} (PRR), a progressive, trajectory-grounded refinement control framework that derives a token-level notion of empirical convergence progress from full decoding rollouts. Based on this signal, PRR learns a lightweight token-wise controller to regulate refinement via temperature-based distribution shaping under a progressive self-evolving training scheme. Experiments show that PRR substantially accelerates diffusion language model decoding while preserving generation quality.

cs.AI↗

arXiv2026

GeoBlock: Inferring Block Granularity from Dependency Geometry in Diffusion Language Models

Block diffusion enables efficient parallel refinement in diffusion language models, but its decoding behavior depends critically on block size. Existing block-sizing strategies rely on fixed rules or heuristic signals and do not account for the dependency geometry that determines which tokens can be safely refined together. This motivates a geometry view of diffusion decoding: \emph{regions with strong causal ordering require sequential updates, whereas semantically cohesive regions admit parallel refinement.} We introduce GeoBlock, a geometry-aware block inference framework that determines block granularity directly from attention-derived dependency geometry. Instead of relying on predefined schedules or local confidence heuristics, GeoBlock analyzes cross-token dependency patterns to identify geometrically stable refinement regions and dynamically determines appropriate block boundaries during decoding. By adapting block granularity to the dependency geometry, GeoBlock preserves the parallel efficiency of block diffusion while enforcing dependency-consistent refinement that exhibits autoregressive reliability. GeoBlock requires no additional training and integrates seamlessly into existing block diffusion architectures. Extensive experiments across multiple benchmarks show that GeoBlock reliably identifies geometry-consistent block boundaries and improves the accuracy of block diffusion with only a small additional computational budget.

cs.CL↗

arXiv2026

Task-Aware Exploration via a Predictive Bisimulation Metric

Accelerating exploration in visual reinforcement learning under sparse rewards remains challenging due to the substantial task-irrelevant variations. Despite advances in intrinsic exploration, many methods either assume access to low-dimensional states or lack task-aware exploration strategies, thereby rendering them fragile in visual domains. To bridge this gap, we present TEB, a Task-aware Exploration approach that tightly couples task-relevant representations with exploration through a predictive Bisimulation metric. Specifically, TEB leverages the metric not only to learn behaviorally grounded task representations but also to measure behaviorally intrinsic novelty over the learned latent space. To realize this, we first theoretically mitigate the representation collapse of degenerate bisimulation metrics under sparse rewards by internally introducing a simple but effective predicted reward differential. Building on this robust metric, we design potential-based exploration bonuses, which measure the relative novelty of adjacent observations over the latent space. Extensive experiments on MetaWorld and Maze2D show that TEB achieves superior exploration ability and outperforms recent baselines.

cs.AI↗

arXiv2025

Toward Automated and Trustworthy Scientific Analysis and Visualization with LLM-Generated Code

As modern science becomes increasingly data-intensive, the ability to analyze and visualize large-scale, complex datasets is critical to accelerating discovery. However, many domain scientists lack the programming expertise required to develop custom data analysis workflows, creating barriers to timely and effective insight. Large language models (LLMs) offer a promising solution by generating executable code from natural language descriptions. In this paper, we investigate the trustworthiness of open-source LLMs in autonomously producing Python scripts for scientific data analysis and visualization. We construct a benchmark suite of domain-inspired prompts that reflect real-world research tasks and systematically evaluate the executability and correctness of the generated code. Our findings show that, without human intervention, the reliability of LLM-generated code is limited, with frequent failures caused by ambiguous prompts and the models' insufficient understanding of domain-specific contexts. To address these challenges, we design and assess three complementary strategies: data-aware prompt disambiguation, retrieval-augmented prompt enhancement, and iterative error repair. While these methods significantly improve execution success rates and output quality, further refinement is needed. This work highlights both the promise and current limitations of LLM-driven automation in scientific workflows and introduces actionable techniques and a reusable benchmark for building more inclusive, accessible, and trustworthy AI-assisted research tools.

cs.SE↗

arXiv2025

JANUS: Resilient and Adaptive Data Transmission for Enabling Timely and Efficient Cross-Facility Scientific Workflows

In modern science, the growing complexity of large-scale scientific projects has led to an increasing reliance on cross-facility scientific workflows, where resources and expertise from multiple institutions and geographic locations are leveraged to accelerate scientific discovery. These workflows often require transmitting huge amounts of scientific data through wide-area networks. Although high-speed networks like ESnet and transfer services such as Globus have improved data mobility, several challenges remain. The sheer volume of data can overwhelm network bandwidth, widely used transport protocols such as TCP suffer from inefficiencies due to retransmissions triggered by packet loss, and existing fault-tolerance mechanisms like erasure coding introduce substantial overhead. In this paper, we propose JANUS, a resilient and adaptable data transmission approach designed for cross-facility scientific workflows. Unlike traditional TCP-based methods, JANUSleverages UDP, integrates erasure coding for fault tolerance, and combines it with error-bounded lossy compression to reduce overhead. This novel design allows users to balance data transmission time and accuracy, optimizing transfer performance based on specific scientific requirements. Additionally, JANUS dynamically adjusts erasure coding parameters in response to real-time network conditions, ensuring efficient data transfers even in fluctuating environments. We develop optimization models for determining ideal configurations and implement adaptive data transfer protocols to enhance reliability. Through extensive simulations and real-network experiments, we demonstrate that JANUS significantly improves transfer efficiency while maintaining data fidelity.

cs.DC↗

arXiv2025

Playing Non-Embedded Card-Based Games with Reinforcement Learning

Significant progress has been made in AI for games, including board games, MOBA, and RTS games. However, complex agents are typically developed in an embedded manner, directly accessing game state information, unlike human players who rely on noisy visual data, leading to unfair competition. Developing complex non-embedded agents remains challenging, especially in card-based RTS games with complex features and large state spaces. We propose a non-embedded offline reinforcement learning training strategy using visual inputs to achieve real-time autonomous gameplay in the RTS game Clash Royale. Due to the lack of a object detection dataset for this game, we designed an efficient generative object detection dataset for training. We extract features using state-of-the-art object detection and optical character recognition models. Our method enables real-time image acquisition, perception feature fusion, decision-making, and control on mobile devices, successfully defeating built-in AI opponents. All code is open-sourced at https://github.com/wty-yy/katacr.

cs.LG↗

arXiv2025

MInCo: Mitigating Information Conflicts in Distracted Visual Model-based Reinforcement Learning

Existing visual model-based reinforcement learning (MBRL) algorithms with observation reconstruction often suffer from information conflicts, making it difficult to learn compact representations and hence result in less robust policies, especially in the presence of task-irrelevant visual distractions. In this paper, we first reveal that the information conflicts in current visual MBRL algorithms stem from visual representation learning and latent dynamics modeling with an information-theoretic perspective. Based on this finding, we present a new algorithm to resolve information conflicts for visual MBRL, named MInCo, which mitigates information conflicts by leveraging negative-free contrastive learning, aiding in learning invariant representation and robust policies despite noisy observations. To prevent the dominance of visual representation learning, we introduce time-varying reweighting to bias the learning towards dynamics modeling as training proceeds. We evaluate our method on several robotic control tasks with dynamic background distractions. Our experiments demonstrate that MInCo learns invariant representations against background noise and consistently outperforms current state-of-the-art visual MBRL methods. Code is available at https://github.com/ShiguangSun/minco.

cs.LG↗

arXiv2025

HPDR: High-Performance Portable Scientific Data Reduction Framework

The rapid growth of scientific data is surpassing advancements in computing, creating challenges in storage, transfer, and analysis, particularly at the exascale. While data reduction techniques such as lossless and lossy compression help mitigate these issues, their computational overhead introduces new bottlenecks. GPU-accelerated approaches improve performance but face challenges in portability, memory transfer, and scalability on multi-GPU systems. To address these, we propose HPDR, a high-performance, portable data reduction framework. HPDR supports diverse processor architectures, reducing memory transfer overhead to 2.3% and achieving up to 3.5x faster throughput than existing solutions. It attains 96% of the theoretical speedup in multi-GPU settings. Evaluations on the Frontier supercomputer demonstrate 103 TB/s throughput and up to 4x acceleration in parallel I/O performance at scale. HPDR offers a scalable, efficient solution for managing massive data volumes in exascale computing environments.

cs.DC↗

arXiv2024

Spin-orbit interactions of the twisted random light

The twist phase of random light represents a nontrivial two-point phase, endowing the field with orbital angular momentum. Although the mutual transition of the spin and orbit angular momenta of coherent light has been revealed, the relationship between spin-orbital angular momentum interaction (SOI) and the twist phase has remained unexplored. This is because of the stochastic nature of random light, making it challenging to explore the properties of angular momenta that rely on well-defined spatial and polarization structures. This study addresses this gap from the view of the asymmetry coherent-mode decomposition for twisted random light to gain insight into the intricate interplay between the twist phase and the SOI within a tight focusing system. Our findings reveal that spin and orbit angular momentum transitions occur in the tightly focused twisted random light beam, yielding the transverse spin density controlled by the twist phase. This effect becomes more pronounced when the spin of random light and the chirality of the twist phase are the same. Our work may find significant applications in optical sensing, metrology, and quantum optics.

physics.optics↗

arXiv2024

Enhancing Decision Transformer with Diffusion-Based Trajectory Branch Generation

Decision Transformer (DT) can learn effective policy from offline datasets by converting the offline reinforcement learning (RL) into a supervised sequence modeling task, where the trajectory elements are generated auto-regressively conditioned on the return-to-go (RTG).However, the sequence modeling learning approach tends to learn policies that converge on the sub-optimal trajectories within the dataset, for lack of bridging data to move to better trajectories, even if the condition is set to the highest RTG.To address this issue, we introduce Diffusion-Based Trajectory Branch Generation (BG), which expands the trajectories of the dataset with branches generated by a diffusion model.The trajectory branch is generated based on the segment of the trajectory within the dataset, and leads to trajectories with higher returns.We concatenate the generated branch with the trajectory segment as an expansion of the trajectory.After expanding, DT has more opportunities to learn policies to move to better trajectories, preventing it from converging to the sub-optimal trajectories.Empirically, after processing with BG, DT outperforms state-of-the-art sequence modeling methods on D4RL benchmark, demonstrating the effectiveness of adding branches to the dataset without further modifications.

cs.LG↗

arXiv2024

Observation of Moir\'e Plasmonic Skyrmion Clusters

Skyrmions are topological defects belonging to nontrivial homotopy classes in particle theory. Their remarkably stable topology has recently been observed in electromagnetic waves. For the evanescent fields near a surface, this has been realized so far only for elementary optical skyrmions, with a fixed skyrmion number. Here we report, both in theory and experiment, the concept of moir\'e plasmonic skyrmion clusters, where multi-skyrmions are nested to form a large optical skyrmion cluster. By leveraging twistronics engineering of plasmonic nanostructures, we demonstrate both crystallized and quasi-crystallized optical skyrmion lattices, revealing an unprecedented degree of topological control. In a misaligned composite nanostructure, the rapid inverting of optical skyrmion number is achieved, which is explained by a lattice model. This topological change of moir\'eplasmonic skyrmion clusters can serve as a precise beacon of the relative alignment deviation between composite nanostructures.

physics.optics↗

arXiv2024

Grounded Answers for Multi-agent Decision-making Problem through Generative World Model

Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent decision-making problems because they miss the trial-and-error experience and reasoning as humans. To address this limitation, we explore a paradigm that integrates a language-guided simulator into the multi-agent reinforcement learning pipeline to enhance the generated answer. The simulator is a world model that separately learns dynamics and reward, where the dynamics model comprises an image tokenizer as well as a causal transformer to generate interaction transitions autoregressively, and the reward model is a bidirectional transformer learned by maximizing the likelihood of trajectories in the expert demonstrations under language guidance. Given an image of the current state and the task description, we use the world model to train the joint policy and produce the image sequence as the answer by running the converged policy on the dynamics model. The empirical results demonstrate that this framework can improve the answers for multi-agent decision-making problems by showing superior performance on the training and unseen tasks of the StarCraft Multi-Agent Challenge benchmark. In particular, it can generate consistent interaction sequences and explainable reward functions at interaction states, opening the path for training generative models of the future.

cs.AI↗

arXiv2024

Edge detection imaging by quasi-bound states in the continuum

Optical metasurfaces have revolutionized analog computing and image processing at sub-wavelength scales with faster speed and lower power consumption. They typically involve spatial differentiation with engineered angular dispersion. Quasi-bound states in the continuum (quasi-BICs) have recently emerged as a powerful tool for tailoring properties of optical resonances. While quasi-BICs have been explored in various applications that require high $Q$-factors and enhanced field confinement, their full potential in image processing remains unexplored. Here, we demonstrate edge detection imaging by leveraging a quasi-BIC in an all-dielectric metasurface. This metasurface, composed of four nanodisks per unit cell, supports a polarization-independent quasi-BIC through structural perturbations, allowing simultaneously engineering $Q$-factor and angular dispersion. Importantly, we find that with suitable parameters, this quasi-BIC metasurface can perform isotropic two-dimensional spatial differentiation, which is the core element for realizing edge detection. Following the theoretical design, we fabricate the metasurfaces on the silicon-on-insulator platform and experimentally validate their capability of high-quality, efficient, and uniform edge detection imaging under different incident polarizations. Our results illuminate the mechanisms of edge detection with quasi-BIC metasurfaces and highlight new opportunities for their application in ultra-compact, low-power optical computing devices.

physics.optics↗

arXiv2024

Imagine, Initialize, and Explore: An Effective Exploration Method in Multi-Agent Reinforcement Learning

Effective exploration is crucial to discovering optimal strategies for multi-agent reinforcement learning (MARL) in complex coordination tasks. Existing methods mainly utilize intrinsic rewards to enable committed exploration or use role-based learning for decomposing joint action spaces instead of directly conducting a collective search in the entire action-observation space. However, they often face challenges obtaining specific joint action sequences to reach successful states in long-horizon tasks. To address this limitation, we propose Imagine, Initialize, and Explore (IIE), a novel method that offers a promising solution for efficient multi-agent exploration in complex scenarios. IIE employs a transformer model to imagine how the agents reach a critical state that can influence each other's transition functions. Then, we initialize the environment at this state using a simulator before the exploration phase. We formulate the imagination as a sequence modeling problem, where the states, observations, prompts, actions, and rewards are predicted autoregressively. The prompt consists of timestep-to-go, return-to-go, influence value, and one-shot demonstration, specifying the desired state and trajectory as well as guiding the action generation. By initializing agents at the critical states, IIE significantly increases the likelihood of discovering potentially important under-explored regions. Despite its simplicity, empirical results demonstrate that our method outperforms multi-agent exploration baselines on the StarCraft Multi-Agent Challenge (SMAC) and SMACv2 environments. Particularly, IIE shows improved performance in the sparse-reward SMAC tasks and produces more effective curricula over the initialized states than other generative methods, such as CVAE-GAN and diffusion models.

cs.LG↗

arXiv2024

MGARD: A multigrid framework for high-performance, error-controlled data compression and refactoring

We describe MGARD, a software providing MultiGrid Adaptive Reduction for floating-point scientific data on structured and unstructured grids. With exceptional data compression capability and precise error control, MGARD addresses a wide range of requirements, including storage reduction, high-performance I/O, and in-situ data analysis. It features a unified application programming interface (API) that seamlessly operates across diverse computing architectures. MGARD has been optimized with highly-tuned GPU kernels and efficient memory and device management mechanisms, ensuring scalable and rapid operations.

cs.CV↗

arXiv2024

Spatiotemporally adaptive compression for scientific dataset with feature preservation -- a case study on simulation data with extreme climate events analysis

Scientific discoveries are increasingly constrained by limited storage space and I/O capacities. For time-series simulations and experiments, their data often need to be decimated over timesteps to accommodate storage and I/O limitations. In this paper, we propose a technique that addresses storage costs while improving post-analysis accuracy through spatiotemporal adaptive, error-controlled lossy compression. We investigate the trade-off between data precision and temporal output rates, revealing that reducing data precision and increasing timestep frequency lead to more accurate analysis outcomes. Additionally, we integrate spatiotemporal feature detection with data compression and demonstrate that performing adaptive error-bounded compression in higher dimensional space enables greater compression ratios, leveraging the error propagation theory of a transformation-based compressor. To evaluate our approach, we conduct experiments using the well-known E3SM climate simulation code and apply our method to compress variables used for cyclone tracking. Our results show a significant reduction in storage size while enhancing the quality of cyclone tracking analysis, both quantitatively and qualitatively, in comparison to the prevalent timestep decimation approach. Compared to three state-of-the-art lossy compressors lacking feature preservation capabilities, our adaptive compression framework improves perfectly matched cases in TC tracking by 26.4-51.3% at medium compression ratios and by 77.3-571.1% at large compression ratios, with a merely 5-11% computational overhead.

cs.CV↗

arXiv2023

High-performance Data Management for Whole Slide Image Analysis in Digital Pathology

When dealing with giga-pixel digital pathology in whole-slide imaging, a notable proportion of data records holds relevance during each analysis operation. For instance, when deploying an image analysis algorithm on whole-slide images (WSI), the computational bottleneck often lies in the input-output (I/O) system. This is particularly notable as patch-level processing introduces a considerable I/O load onto the computer system. However, this data management process could be further paralleled, given the typical independence of patch-level image processes across different patches. This paper details our endeavors in tackling this data access challenge by implementing the Adaptable IO System version 2 (ADIOS2). Our focus has been constructing and releasing a digital pathology-centric pipeline using ADIOS2, which facilitates streamlined data management across WSIs. Additionally, we've developed strategies aimed at curtailing data retrieval times. The performance evaluation encompasses two key scenarios: (1) a pure CPU-based image analysis scenario ("CPU scenario"), and (2) a GPU-based deep learning framework scenario ("GPU scenario"). Our findings reveal noteworthy outcomes. Under the CPU scenario, ADIOS2 showcases an impressive two-fold speed-up compared to the brute-force approach. In the GPU scenario, its performance stands on par with the cutting-edge GPU I/O acceleration framework, NVIDIA Magnum IO GPU Direct Storage (GDS). From what we know, this appears to be among the initial instances, if any, of utilizing ADIOS2 within the field of digital pathology. The source code has been made publicly available at https://github.com/hrlblab/adios.

eess.IV↗