arXiv subjects

Duo Wang

Publications and source records attributed to Duo Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Wasserstein Distributionally Robust Adaptive Covariance Steering

We present a methodology for predictable and safe covariance steering control of uncertain nonlinear stochastic processes. The systems under consideration are subject to general uncertainties, which include unbounded random disturbances (aleatoric uncertainties) and incomplete model knowledge (state-dependent epistemic uncertainties). These general uncertainties lead to temporally evolving state distributions that are entirely unknown, can have arbitrary shapes, and may diverge unquantifiably from expected behaviors, leading to unpredictable and unsafe behaviors. Our method relies on an $\mathcal{L}_1$-adaptive control architecture that ensures robust control of uncertain stochastic processes while providing Wasserstein metric certificates in the space of probability measures. We show how these distributional certificates can be incorporated into the high-level covariance control steering to guarantee safe control. Unlike existing distributionally robust planning and control methodologies, our approach avoids difficult-to-verify requirements like the availability of finite samples from the true underlying distribution or an a priori knowledge of time-varying ambiguity sets to which the state distributions are assumed to belong.

eess.SY↗

arXiv2025

Unveiling Insulating Ferro and Ferrimagnetism in Double-Double Perovskite Oxides

The emergence of ferro- and ferrimagnetic behavior in insulating materials is uncommon, largely due to Hund's rules. Utilizing symmetry analysis, first-principles methods, and classical Monte Carlo simulations, \textcolor{black}{we report technologically important insulating ferro and ferrimagnetic double-double perovskite oxides. Our study predicts LaA$^{\prime}$MnNiO$_6$ (A$^{\prime}$ = V, Cr, Mn, Co, and Ni) as promising candidates for spintronic and optical applications exhibiting band gaps between 1.3 eV and 1.9 eV. We explain the mechanisms driving band gap openings and magnetic exchange interactions in these ferro and ferrimagnetic compounds. Monte Carlo simulations, together with state-of-the-art orbital-decomposed exchange parameter analysis, reveal intriguing variations in magnetic transition temperatures (up to 242 K) and the corresponding exchange mechanisms in all LaA$^{\prime}$MnNiO$_6$ compounds.} In addition, we assess the thermodynamic and dynamic stability of these compounds to comment on the feasibility of these systems.

cond-mat.mtrl-sci↗

arXiv2025

TLV-HGNN: Thinking Like a Vertex for Memory-efficient HGNN Inference

Heterogeneous graph neural networks (HGNNs) excel at processing heterogeneous graph data and are widely applied in critical domains. In HGNN inference, the neighbor aggregation stage is the primary performance determinant, yet it suffers from two major sources of memory inefficiency. First, the commonly adopted per-semantic execution paradigm stores intermediate aggregation results for each semantic prior to semantic fusion, causing substantial memory expansion. Second, the aggregation process incurs extensive redundant memory accesses, including repeated loading of target vertex features across semantics and repeated accesses to shared neighbors due to cross-semantic neighborhood overlap. These inefficiencies severely limit scalability and reduce HGNN inference performance. In this work, we first propose a semantics-complete execution paradigm from a vertex perspective that eliminates per-semantic intermediate storage and redundant target vertex accesses. Building on this paradigm, we design TVL-HGNN, a reconfigurable hardware accelerator optimized for efficient aggregation. In addition, we introduce a vertex grouping technique based on cross-semantic neighborhood overlap, with hardware implementation, to reduce redundant accesses to shared neighbors. Experimental results demonstrate that TVL-HGNN achieves average speedups of 7.85x and 1.41x over the NVIDIA A100 GPU and the state-of-the-art HGNN accelerator HiHGNN, respectively, while reducing energy consumption by 98.79% and 32.61%.

cs.AR↗

arXiv2025

Accelerating GNN Training through Locality-aware Dropout and Merge

Graph Neural Networks (GNNs) have demonstrated significant success in graph learning and are widely adopted across various critical domains. However, the irregular connectivity between vertices leads to inefficient neighbor aggregation, resulting in substantial irregular and coarse-grained DRAM accesses. This lack of data locality presents significant challenges for execution platforms, ultimately degrading performance. While previous accelerator designs have leveraged on-chip memory and data access scheduling strategies to address this issue, they still inevitably access features at irregular addresses from DRAM. In this work, we propose LiGNN, a hardware-based solution that improves data locality by applying dropout and merge techniques during neighbor aggregation to accelerate GNN training. Unlike conventional algorithm-level dropout methods that primarily aim to improve accuracy while overlooking hardware costs, LiGNN introduces a locality-aware feature dropout mechanism. This approach selectively drops node features with data locality awareness, effectively reducing irregular DRAM accesses without compromising model accuracy. Moreover, by leveraging detailed knowledge of memory layout and organization-including critical alignment constraints-LiGNN strategically merges memory accesses during neighbor aggregation at the DRAM row level, guided by GNN-level semantics. This optimization significantly improves data locality with minimal additional cost. Under the commonly adopted 0.5 dropout rate, LiGNN outperforms state-of-the-art methods, delivering a 1.48~3.02x speedup, reducing DRAM accesses by 34%~55%, and lowering DRAM row activations by 59%~82%, all while maintaining model accuracy.

cs.AR↗

arXiv2025

Large Processor Chip Model

Computer System Architecture serves as a crucial bridge between software applications and the underlying hardware, encompassing components like compilers, CPUs, coprocessors, and RTL designs. Its development, from early mainframes to modern domain-specific architectures, has been driven by rising computational demands and advancements in semiconductor technology. However, traditional paradigms in computer system architecture design are confronting significant challenges, including a reliance on manual expertise, fragmented optimization across software and hardware layers, and high costs associated with exploring expansive design spaces. While automated methods leveraging optimization algorithms and machine learning have improved efficiency, they remain constrained by a single-stage focus, limited data availability, and a lack of comprehensive human domain knowledge. The emergence of large language models offers transformative opportunities for the design of computer system architecture. By leveraging the capabilities of LLMs in areas such as code generation, data analysis, and performance modeling, the traditional manual design process can be transitioned to a machine-based automated design approach. To harness this potential, we present the Large Processor Chip Model (LPCM), an LLM-driven framework aimed at achieving end-to-end automated computer architecture design. The LPCM is structured into three levels: Human-Centric; Agent-Orchestrated; and Model-Governed. This paper utilizes 3D Gaussian Splatting as a representative workload and employs the concept of software-hardware collaborative design to examine the implementation of the LPCM at Level 1, demonstrating the effectiveness of the proposed approach. Furthermore, this paper provides an in-depth discussion on the pathway to implementing Level 2 and Level 3 of the LPCM, along with an analysis of the existing challenges.

cs.AR↗

arXiv2025

VA-CDH: A Variance-Aware Method to Optimize Latency for Caching with Delayed Hits

Caches are fundamental to latency-sensitive systems like Content Delivery Networks (CDNs) and Mobile Edge Computing (MEC). However, the delayed hit phenomenon where multiple requests for an object occur during its fetch from the remote server after a miss significantly inflates user-perceived latency. While recent algorithms acknowledge delayed hits by estimating the resulting aggregate delay, they predominantly focus on its mean value. We identify and demonstrate that such approaches are insufficient, as the real aggregate delay frequently exhibits substantial variance in the true production system, leading to suboptimal latency performance when ignored. Thus, we propose VA-CDH, a variance-aware method to optimize latency for caching with delayed hits. It employs a novel ranking function that explicitly incorporates both the empirically estimated mean and standard deviation of aggregate delay, allowing caching decisions to account for its variation. We derive the analytical distribution of aggregate delay under Poisson arrivals as a theoretical contribution, offering more statistical insight beyond the mean value. Through the simulations conducted on synthetic and real-world datasets, we show that VA-CDH reduces the total latency by 1%-6% approximately compared to state-of-the-art algorithms.

cs.NI↗

arXiv2025

Discovery of an ultrastable antiferromagnetic two-dimensional CrF3 phase with anisotropic quasi-one-dimensional mechanical, electronic, and thermal properties

We report the discovery of an ultra-stable antiferromagnetic two-dimensional (2D) CrF3 phase that is energetically more favorable than the traditionally assumed hexagonal structure. Using first-principles calculations and evolutionary structure searches, we identify a new low-energy rectangular configuration of CrF3 with remarkable anisotropic properties. Mechanically, this phase exhibits zero in-plane Poisson's ratio, a rare negative out-of-plane Poisson's ratio, and quasi-one-dimensional (quasi-1D) behavior characterized by minimal coupling between orthogonal directions. Electronically, CrF3 shows quasi-1D transport with two independent conduction bands near the Fermi level, tunable via uniaxial strain. The calculated bandgap is 3.05 eV, which can be modulated under strain, enabling control over its electronic properties. The material also displays out-of-plane antiferromagnetic ordering with a magnetic anisotropy energy of 0.098 meV per Cr atom and an estimated Neel temperature of 20 K. Additionally, we investigate the thermal conductivity of monolayer rectangular CrF3 (r-CrF3), revealing significant anisotropy in heat transport. The thermal conductivity along the y-axis is approximately 60.5 W/mK at 300 K, much higher than along the x-axis at 13.2 W/mK. The thermal anisotropic factor is 4.58, surpassing that of other 2D materials like black phosphorene, WTe2, and arsenene, highlighting r-CrF3's potential for advanced directional heat management. Consequently, the rectangular CrF3 phase is a promising candidate for applications in spintronics, strain-engineered nanoelectronics, mechanical metamaterials, and thermal management technologies.

cond-mat.mtrl-sci↗

arXiv2025

Emergence of topological superconductivity in the presence of chiral magnetism in 2D CrInTe$_3$

We propose a general framework for designing a two-dimensional (2D) topological superconductor (TSC) using a magnet-superconductor hybrid system. This setup involves a monolayer of CrInTe$_3$, which hosts noncoplanar magnetic textures, in proximity to a 2D $s$-wave superconducting layer. Serving as an alternative to $p$-wave superconductors, this configuration induces a topological superconducting phase and is a promising platform for realizing the 2D Kitaev model, which supports Majorana zero-energy modes through emergent $p$-wave symmetry superconducting pairing. Notably, the magnetic moments break time-reversal symmetry while the superconducting state preserves particle-hole symmetry, placing our system in the Altland-Zirnbauer class $D$ and ensuring robust Majorana excitations. We first perform density functional theory-based simulations to study a monolayer of CrInTe$_3$, from which essential magnetic characteristic parameters, such as Heisenberg exchange interaction and Dzyaloshinskii-Moriya interaction (DMI), are calculated using the state-of-the-art Liechtenstein-Katsnelson-Antropov-Gubanov (LKAG) approach. With a substantial DMI coupling exhibited in CrInTe$_3$, large-scale Monte Carlo simulations reveal the stabilization of a noncoplanar spiral magnetic state as ground state. In this magnetic phase, we observe a transition from corner modes in the zero-energy local density of states (LDOS) to edge modes as the chemical potential ($μ$) varies. Furthermore, under a finite magnetic field, the system enters a mixed magnetic state, characterized by isolated skyrmions and spiral domain walls, which lead to unique low-energy localization of electronic wave functions, rendering the system an insulator. Finally, we discuss potential experimental realizations of TSC in this magnet-superconductor interfacial system, using real-space probes such as scanning tunneling microscopy (STM).

cond-mat.supr-con↗

arXiv2024

LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings

Zero-shot graph machine learning, especially with graph neural networks (GNNs), has garnered significant interest due to the challenge of scarce labeled data. While methods like self-supervised learning and graph prompt learning have been extensively explored, they often rely on fine-tuning with task-specific labels, limiting their effectiveness in zero-shot scenarios. Inspired by the zero-shot capabilities of instruction-fine-tuned large language models (LLMs), we introduce a novel framework named Token Embedding-Aligned Graph Language Model (TEA-GLM) that leverages LLMs as cross-dataset and cross-task zero-shot learners for graph machine learning. Concretely, we pretrain a GNN, aligning its representations with token embeddings of an LLM. We then train a linear projector that transforms the GNN's representations into a fixed number of graph token embeddings without tuning the LLM. A unified instruction is designed for various graph tasks at different levels, such as node classification (node-level) and link prediction (edge-level). These design choices collectively enhance our method's effectiveness in zero-shot learning, setting it apart from existing methods. Experiments show that our graph token embeddings help the LLM predictor achieve state-of-the-art performance on unseen datasets and tasks compared to other methods using LLMs as predictors.

cs.LG↗

arXiv2024

Verification and Validation of a Vision-Based Landing System for Autonomous VTOL Air Taxis

Autonomous air taxis are poised to revolutionize urban mass transportation, however, ensuring their safety and reliability remains an open challenge. Validating autonomy solutions on air taxis in the real world presents complexities, risks, and costs that further convolute this challenge. Verification and Validation (V&V) frameworks play a crucial role in the design and development of highly reliable systems by formally verifying safety properties and validating algorithm behavior across diverse operational scenarios. Advancements in high-fidelity simulators have significantly enhanced their capability to emulate real-world conditions, encouraging their use for validating autonomous air taxi solutions, especially during early development stages. This evolution underscores the growing importance of simulation environments, not only as complementary tools to real-world testing but as essential platforms for evaluating algorithms in a controlled, reproducible, and scalable manner. This work presents a V&V framework for a vision-based landing system for air taxis with vertical take-off and landing (VTOL) capabilities. Specifically, we use Verse, a tool for formal verification, to model and verify the safety of the system by obtaining and analyzing the reachable sets. To conduct this analysis, we utilize a photorealistic simulation environment. The simulation environment, built on Unreal Engine, provides realistic terrain, weather, and sensor characteristics to emulate real-world conditions with high fidelity. To validate the safety analysis results, we conduct extensive scenario-based testing to assess the reachability set and robustness of the landing algorithm in various conditions. This approach showcases the representativeness of high-fidelity simulators, offering an effective means to analyze and refine algorithms before real-world deployment.

cs.RO↗

arXiv2024

Bayesian Data Augmentation and Training for Perception DNN in Autonomous Aerial Vehicles

Learning-based solutions have enabled incredible capabilities for autonomous systems. Autonomous vehicles, both aerial and ground, rely on DNN for various integral tasks, including perception. The efficacy of supervised learning solutions hinges on the quality of the training data. Discrepancies between training data and operating conditions result in faults that can lead to catastrophic incidents. However, collecting vast amounts of context-sensitive data, with broad coverage of possible operating environments, is prohibitively difficult. Synthetic data generation techniques for DNN allow for the easy exploration of diverse scenarios. However, synthetic data generation solutions for aerial vehicles are still lacking. This work presents a data augmentation framework for aerial vehicle's perception training, leveraging photorealistic simulation integrated with high-fidelity vehicle dynamics. Safe landing is a crucial challenge in the development of autonomous air taxis, therefore, landing maneuver is chosen as the focus of this work. With repeated simulations of landing in varying scenarios we assess the landing performance of the VTOL type UAV and gather valuable data. The landing performance is used as the objective function to optimize the DNN through retraining. Given the high computational cost of DNN retraining, we incorporated Bayesian Optimization in our framework that systematically explores the data augmentation parameter space to retrain the best-performing models. The framework allowed us to identify high-performing data augmentation parameters that are consistently effective across different landing scenarios. Utilizing the capabilities of this data augmentation framework, we obtained a robust perception model. The model consistently improved the perception-based landing success rate by at least 20% under different lighting and weather conditions.

cs.RO↗

arXiv2024

Public Transport Network Design for Equality of Accessibility via Message Passing Neural Networks and Reinforcement Learning

Designing Public Transport (PT) networks able to satisfy mobility needs of people is essential to reduce the number of individual vehicles on the road, and thus pollution and congestion. Urban sustainability is thus tightly coupled to an efficient PT. Current approaches on Transport Network Design (TND) generally aim to optimize generalized cost, i.e., a unique number including operator and users' costs. Since we intend quality of PT as the capability of satisfying mobility needs, we focus instead on PT accessibility, i.e., the ease of reaching surrounding points of interest via PT. PT accessibility is generally unequally distributed in urban regions: suburbs generally suffer from poor PT accessibility, which condemns residents therein to be dependent on their private cars. We thus tackle the problem of designing bus lines so as to minimize the inequality in the geographical distribution of accessibility. We combine state-of-the-art Message Passing Neural Networks (MPNN) and Reinforcement Learning. We show the efficacy of our method against metaheuristics (classically used in TND) in a use case representing in simplified terms the city of Montreal.

cs.AI↗

arXiv2024

HiHGNN: Accelerating HGNNs through Parallelism and Data Reusability Exploitation

Heterogeneous graph neural networks (HGNNs) have emerged as powerful algorithms for processing heterogeneous graphs (HetGs), widely used in many critical fields. To capture both structural and semantic information in HetGs, HGNNs first aggregate the neighboring feature vectors for each vertex in each semantic graph and then fuse the aggregated results across all semantic graphs for each vertex. Unfortunately, existing graph neural network accelerators are ill-suited to accelerate HGNNs. This is because they fail to efficiently tackle the specific execution patterns and exploit the high-degree parallelism as well as data reusability inside and across the processing of semantic graphs in HGNNs. In this work, we first quantitatively characterize a set of representative HGNN models on GPU to disclose the execution bound of each stage, inter-semantic-graph parallelism, and inter-semantic-graph data reusability in HGNNs. Guided by our findings, we propose a high-performance HGNN accelerator, HiHGNN, to alleviate the execution bound and exploit the newfound parallelism and data reusability in HGNNs. Specifically, we first propose a bound-aware stage-fusion methodology that tailors to HGNN acceleration, to fuse and pipeline the execution stages being aware of their execution bounds. Second, we design an independency-aware parallel execution design to exploit the inter-semantic-graph parallelism. Finally, we present a similarity-aware execution scheduling to exploit the inter-semantic-graph data reusability. Compared to the state-of-the-art software framework running on NVIDIA GPU T4 and GPU A100, HiHGNN respectively achieves an average 41.5$\times$ and 8.6$\times$ speedup as well as 106$\times$ and 73$\times$ energy efficiency with quarter the memory bandwidth of GPU A100.

cs.AR↗

arXiv2024

Design of Magnetic Polar Double-Double Perovskite Oxides through Cation Ordering

Commencing from the centrosymmetric MnRMnSbO$_6$ compound, we explore the realm of magnetic polar double-double perovskite oxides characterized by significant ferroelectric polarization. Employing symmetry operations, first-principles methodologies, and Monte Carlo simulations, our investigation delves into the structural, magnetic, ferroelectric, and electronic attributes of the polar LaFeMnNiO$_6$ and LaTiMnNiO$_6$ compounds. The structural analysis uncovers that the paraelectric-ferroelectric phase transition is intricately linked to the Fe/Ti-displacement of square planar Fe/TiO$_4$. Notably, the magnetic LaFeMnNiO$_6$ and LaTiMnNiO$_6$ compounds demonstrate robust ferroelectric polarizations, measuring 20.0 $μ$C/cm$^2$ and 21.8 $μ$C/cm$^2$, respectively, accompanied by minimalist forbidden energy gaps of 1.40 eV and 1.18 eV using the GGA+U method. Furthermore, we pinpoint elevated magnetic transition temperatures for these compounds. Additionally, our study scrutinizes the energies associated with diverse spin configurations and identifies potential minimum decomposition pathways into stable oxides. This comprehensive analysis ensures the meticulous formation of the LaFeMnNiO$_6$ and LaTiMnNiO$_6$ compounds.

cond-mat.mtrl-sci↗

arXiv2023

AccEq-DRT: Planning Demand-Responsive Transit to reduce inequality of accessibility

Accessibility measures how well a location is connected to surrounding opportunities. We focus on accessibility provided by Public Transit (PT). There is an evident inequality in the distribution of accessibility between city centers or close to main transportation corridors and suburbs. In the latter, poor PT service leads to a chronic car-dependency. Demand-Responsive Transit (DRT) is better suited for low-density areas than conventional fixed-route PT. However, its potential to tackle accessibility inequality has not yet been exploited. On the contrary, planning DRT without care to inequality (as in the methods proposed so far) can further improve the accessibility gap in urban areas. To the best of our knowledge this paper is the first to propose a DRT planning strategy, which we call AccEq-DRT, aimed at reducing accessibility inequality, while ensuring overall efficiency. To this aim, we combine a graph representation of conventional PT and a Continuous Approximation (CA) model of DRT. The two are combined in the same multi-layer graph, on which we compute accessibility. We then devise a scoring function to estimate the need of each area for an improvement, appropriately weighting population density and accessibility. Finally, we provide a bilevel optimization method, where the upper level is a heuristic to allocate DRT buses, guided by the scoring function, and the lower level performs traffic assignment. Numerical results in a simplified model of Montreal show that inequality, measured with the Atkinson index, is reduced by up to 34\%. Keywords: DRT Public, Transportation, Accessibility, Continuous Approximation, Network Design

math.OC↗

arXiv2023

Expressive Machine Dubbing Through Phrase-level Cross-lingual Prosody Transfer

Speech generation for machine dubbing adds complexity to conventional Text-To-Speech solutions as the generated output is required to match the expressiveness, emotion and speaking rate of the source content. Capturing and transferring details and variations in prosody is a challenge. We introduce phrase-level cross-lingual prosody transfer for expressive multi-lingual machine dubbing. The proposed phrase-level prosody transfer delivers a significant 6.2% MUSHRA score increase over a baseline with utterance-level global prosody transfer, thereby closing the gap between the baseline and expressive human dubbing by 23.2%, while preserving intelligibility of the synthesised speech.

eess.AS↗

arXiv2023

Cross-lingual Prosody Transfer for Expressive Machine Dubbing

Prosody transfer is well-studied in the context of expressive speech synthesis. Cross-lingual prosody transfer, however, is challenging and has been under-explored to date. In this paper, we present a novel solution to learn prosody representations that are transferable across languages and speakers for machine dubbing of expressive multimedia contents. Multimedia contents often contain field recordings. To enable prosody transfer from noisy audios, we introduce a novel noise modelling module that disentangles noise conditioning from prosody conditioning, and thereby gains independent control of noise levels in the synthesised speech. We augment noisy training data with clean data to improve the ability of the model to map the denoised reference audio to clean speech. Our proposed system can generate speech with context-matching prosody and closes the gap between a strong baseline and human expressive dialogs by 11.2%.

eess.AS↗

arXiv2023

Orthorhombic distortion drives orbital ordering in an antiferromagnetic 3$d^1$ Mott insulator

The orbital, which represents the shape of the electron cloud, very often strongly influences the manifestation of various exotic phenomena, e.g., magnetism, metal-insulator transition, colossal magnetoresistance, unconventional superconductivity etc. in solid-state systems. The observation of the antiferromagnetism in $RE$TiO$_3$ ($RE$=rare earth) series has been puzzling since the celebrated Kugel-Khomskii model of spin-orbital super exchange predicts ferromagnetism in an orbitally degenerate $d^1$ systems. Further, the existence of the orbitally ordered vs. orbital liquid phase in both antiferromagnetic and paramagnetic phase have been unsettled issues thus far. To address these long-standing questions, we investigate single crystalline film of PrTiO$_3$. Our synchrotron X-ray diffraction measurements confirm the retention of bulk-like orthorhombic ($D_{2h}$) symmetry in the thin film geometry. We observe similar X-ray linear dichroism signal in both paramagnetic and antiferromagnetic phase, which can be accounted by ferro orbital ordering (FOO). While the presence of $D_{2h}$ crystal field does not guarantee lifting of orbital degeneracy always, we find it to be strong enough in these rare-earth titanates, leading to the FOO state. Thus, our work demonstrates the orthorhombic distortion is the driving force for the orbital ordering of antiferromagnetic $RE$TiO$_3$.

cond-mat.str-el↗