arXiv subjects

Wei Pan

Publications and source records attributed to Wei Pan.

At least 55 records · Page 3Linked to original sources

arXiv2026

Flat-Band Generation in InAs/GaSb Quantum Wells through Vertically Engineered Heterostructures

Quantum materials constitute a novel category of substances wherein quantum effects and electron-electron (e-e) interactions give rise to unforeseen phenomena on a macroscopic scale. Of particular interest within the realm of quantum materials are flat bands, which promote heavy conduction electrons and enhance e-e correlation effects. While the engineering of such flat bands has been demonstrated in graphene and two-dimensional transition metal dichalcogenides moiré superlattices and in lithography defined semiconductor moiré superlattices, conventional tear-and-stack fabrication methods face challenges due to inevitable twist-angle disorder, strain, and relaxation effects, leading to issues with reproducibility and scalability. Here, we explore the creation and modification of flat bands through vertically engineered III-V semiconductor heterostructures, without the need for twisting. These artificial quantum materials offer a reproducible and scalable means for producing high-quality flat-band materials via molecular beam epitaxy growth. Our investigation includes magnetotransport and infrared magneto-spectroscopy studies of quad-layer InAs/GaSb quantum wells, accompanied by k*p band structure calculations, which illustrate the flattening of bands in vertically designed heterostructures.

cond-mat.mes-hall↗

arXiv2026

Towards Terrain-Aware Safe Locomotion for Quadrupedal Robots Using Proprioceptive Sensing

Achieving safe quadrupedal locomotion in real-world environments has attracted much attention in recent years. When walking over uneven terrain, achieving reliable estimation and realising safety-critical control based on the obtained information is still an open question. To address this challenge, especially for low-cost robots equipped solely with proprioceptive sensors (e.g., IMUs, joint encoders, and contact force sensors), this work first presents an estimation framework that generates a 2.5-D terrain map and extracts support plane parameters, which are then integrated into contact and state estimation. Then, we integrate this estimation framework into a safety-critical control pipeline by formulating control barrier functions that provide rigorous safety guarantees. Experiments demonstrate that the proposed terrain estimation method provides smooth terrain representations. Moreover, the coupled estimation framework of terrain, state, and contact reduces the mean absolute error of base position estimation by 64.8%, decreases the estimation variance by 47.2%, and improves the robustness of contact estimation compared to a decoupled framework. The terrain-informed CBFs integrate historical terrain information and current proprioceptive measurements to ensure global safety by keeping the robot out of hazardous areas and local safety by preventing body-terrain collision, relying solely on proprioceptive sensing.

cs.RO↗

arXiv2026

MIRACL: A Diverse Meta-Reinforcement Learning for Multi-Objective Multi-Echelon Combinatorial Supply Chain Optimisation

Multi-objective reinforcement learning (MORL) is effective for multi-echelon combinatorial supply chain optimisation, where tasks involve high dimensionality, uncertainty, and competing objectives. However, its deployment in dynamic environments is hindered by the need for task-specific retraining and substantial computational cost. We introduce MIRACL (Meta multI-objective Reinforcement leArning with Composite Learning), a hierarchical Meta-MORL framework that allows for a few-shot generalisation across diverse tasks. MIRACL decomposes each task into structured subproblems for efficient policy adaptation and meta-learns a global policy across tasks using a Pareto-based adaptation strategy to encourage diversity in meta-training and fine-tuning. To our knowledge, this is the first integration of Meta-MORL with such mechanisms in combinatorial optimisation. Although validated in the supply chain domain, MIRACL is theoretically domain-agnostic and applicable to broader dynamic multi-objective decision-making problems. Empirical evaluations show that MIRACL outperforms conventional MORL baselines in simple to moderate tasks, achieving up to 10% higher hypervolume and 5% better expected utility. These results underscore the potential of MIRACL for robust, efficient adaptation in multi-objective problems.

cs.LG↗

arXiv2026

SoraNav: Adaptive UAV Task-Centric Navigation via Zeroshot VLM Reasoning

Autonomous navigation under natural language instructions represents a crucial step toward embodied intelligence, enabling complex task execution in environments ranging from industrial facilities to domestic spaces. However, language-driven 3D navigation for Unmanned Aerial Vehicles (UAVs) requires precise spatial reasoning, a capability inherently lacking in current zero-shot Vision-Language Models (VLMs) which often generate ambiguous outputs and cannot guarantee geometric feasibility. Furthermore, existing Vision-Language Navigation (VLN) methods are predominantly tailored for 2.5D ground robots, rendering them unable to generalize to the unconstrained 3D spatial reasoning required for aerial tasks in small-scale, cluttered environments. In this paper, we present SoraNav, a novel framework enabling zero-shot VLM reasoning for UAV task-centric navigation. To address the spatial-semantic gap, we introduce Multi-modal Visual Annotation (MVA), which encodes 3D geometric priors directly into the VLM's 2D visual input. To mitigate hallucinated or infeasible commands, we propose an Adaptive Decision Making (ADM) strategy that validates VLM proposals against exploration history, seamlessly switching to geometry-based exploration to avoid dead-ends and redundant revisits. Deployed on a custom PX4-based micro-UAV, SoraNav demonstrates robust real-world performance. Quantitative results show our approach significantly outperforms state-of-the-art baselines, increasing Success Rate (SR) by 25.7% and navigation efficiency (SPL) by 17.3% in 2.5D scenarios, and achieving improvements of 39.3% (SR) and 24.7% (SPL) in complex 3D scenarios.

cs.RO↗

arXiv2026

DiffInk: Glyph- and Style-Aware Latent Diffusion Transformer for Text to Online Handwriting Generation

Deep generative models have advanced text-to-online handwriting generation (TOHG), which aims to synthesize realistic pen trajectories conditioned on textual input and style references. However, most existing methods still primarily focus on character- or word-level generation, resulting in inefficiency and a lack of holistic structural modeling when applied to full text lines. To address these issues, we propose DiffInk, the first latent diffusion Transformer framework for full-line handwriting generation. We first introduce InkVAE, a novel sequential variational autoencoder enhanced with two complementary latent-space regularization losses: (1) an OCR-based loss enforcing glyph-level accuracy, and (2) a style-classification loss preserving writing style. This dual regularization yields a semantically structured latent space where character content and writer styles are effectively disentangled. We then introduce InkDiT, a novel latent diffusion Transformer that integrates target text and reference styles to generate coherent pen trajectories. Experimental results demonstrate that DiffInk outperforms existing state-of-the-art (SOTA) methods in both glyph accuracy and style fidelity, while significantly improving generation efficiency.

cs.CV↗

arXiv2026

2.5D co-packaged optical I/O chipsets on a SiON/Si interposer for 4 $\times$ 100G optical interconnection

Optical I/O technologies have emerged as a potential industrial solution for high-performance data interconnection in AI/ML computing acceleration. While optical I/Os are deployed at the edge of computational chips by co-packaged optics (CPO), flexible and high-performance integration architectures need to be explored to address system-level challenges. In this work, we present and experimentally demonstrate a SiON/Si-based optical interposer that integrates high-bandwidth and energy-efficient optical I/O chipsets. High-performance photonic and electronic components are co-packaged on the interposer, leading to low-loss, signal-integrity-friendly, and thermally efficient characteristics. The optical interposer incorporates low-loss SiON photonic circuits to realize scalable waveguide routing and wavelength-division multiplexing (WDM) with polarization-insensitive operation and high fabrication tolerance, while supporting flip-chip integration with InP-based active devices, including electro-absorption modulated lasers (EMLs) and photodetectors (PDs). Based on this architecture, a 400-Gb/s single-fiber optical transceiver is implemented and experimentally evaluated. Clear eye diagrams and high receiver sensitivity demonstrate reliable high-speed data transmission, which offers scalable, high-bandwidth optical I/Os in future high-performance computational clusters.

physics.optics↗

arXiv2026

Reinforcement Learning for Control with Probabilistic Stability Guarantee: A Finite-Sample Approach

This paper presents a novel approach to reinforcement learning (RL) for control systems that provides probabilistic stability guarantees using finite data. Leveraging Lyapunov's method, we propose a probabilistic stability theorem that ensures mean square stability using only a finite number of sampled trajectories. The probability of stability increases with the number and length of trajectories, converging to certainty as data size grows. Additionally, we derive a policy gradient theorem for stabilizing policy learning and develop an RL algorithm, L-REINFORCE, that extends the classical REINFORCE algorithm to stabilization problems. The effectiveness of L-REINFORCE is demonstrated through simulations on a Cartpole task, where it outperforms the baseline in ensuring stability. This work bridges a critical gap between RL and control theory, enabling stability analysis and controller design in a model-free framework with finite data.

cs.LG↗

arXiv2026

Buried Dirac points in quantum spin Hall insulators: Implications for Majorana Kramers pair-based quantum computing

For heterostructures formed by a quantum spin Hall insulator (QSHI) placed in proximity to a superconductor (SC), no external magnetic field is necessary to drive the system into a phase supporting topological superconductivity with Majorana zero energy states, making them very attractive for the realization of non-Abelian states and fault-tolerant qubits. Despite considerable work investigating QSHI edge states, there is still an open question about their resilience to large magnetic fields and the implication of such resilience for the formation of a quasi-1D topological superconducting state. In this work, we investigate the transport properties of helical edge states in a QSHI-SC junction formed by a InAs/GaSb (15nm/5nm) double quantum well and a superconducting tantalum (Ta) constriction. We observe a robust conductance plateau up to 2 T, signaling resilient edge state transport. Such resilience is consistent with the Dirac point for the edge states being buried in the bulk valence band. Using a modified Landauer-Buttiker analysis, we find that the conductance is consistent with 98% Andreev reflection probability owing to the high transparency of the InAs/GaSb-Ta interface. We further theoretically show that a buried Dirac point does not affect the robustness of the quasi-1D topological superconducting phase, and favors the hybridization of Majorana Kramer pairs and fermionic modes in the QSHI resulting in extended MKP states, highlighting the subtle role of buried Dirac points in probing MKPs.

cond-mat.supr-con↗

arXiv2026

Virtual-force Based Visual Servo for Multiple Peg-in-Hole Assembly with Tightly Coupled Multi-Manipulator

Multiple Peg-in-Hole (MPiH) assembly is one of the fundamental tasks in robotic assembly. In the MPiH tasks for large-size parts, it is challenging for a single manipulator to simultaneously align multiple distant pegs and holes, necessitating tightly coupled multi-manipulator systems. For such MPiH tasks using tightly coupled multiple manipulators, we propose a collaborative visual servo control framework that uses only the monocular in-hand cameras of each manipulator to reduce positioning errors. Initially, we train a state classification neural network and a positioning neural network. The former divides the states of the peg and hole in the image into three categories: obscured, separated, and overlapped, while the latter determines the position of the peg and hole in the image. Based on these findings, we propose a method to integrate the visual features of multiple manipulators using virtual forces, which can naturally combine with the cooperative controller of the multi-manipulator system. To generalize our approach to holes of different appearances, we varied the appearance of the holes during the dataset generation process. The results confirm that by considering the appearance of the holes, classification accuracy and positioning precision can be improved. Finally, the results show that our method achieves 100\% success rate in dual-manipulator dual peg-in-hole tasks with a clearance of 0.2 mm, while robust to camera calibration errors.

cs.RO↗

arXiv2026

CoINS: Counterfactual Interactive Navigation via Skill-Aware VLM

Recent Vision-Language Models (VLMs) have demonstrated significant potential in robotic planning. However, they typically function as semantic reasoners, lacking an intrinsic understanding of the specific robot's physical capabilities. This limitation is particularly critical in interactive navigation, where robots must actively modify cluttered environments to create traversable paths. Existing VLM-based navigators are predominantly confined to passive obstacle avoidance, failing to reason about when and how to interact with objects to clear blocked paths. To bridge this gap, we propose Counterfactual Interactive Navigation via Skill-aware VLM (CoINS), a hierarchical framework that integrates skill-aware reasoning and robust low-level execution. Specifically, we fine-tune a VLM, named InterNav-VLM, which incorporates skill affordance and concrete constraint parameters into the input context and grounds them into a metric-scale environmental representation. By internalizing the logic of counterfactual reasoning through fine-tuning on the proposed InterNav dataset, the model learns to implicitly evaluate the causal effects of object removal on navigation connectivity, thereby determining interaction necessity and target selection. To execute the generated high-level plans, we develop a comprehensive skill library through reinforcement learning, specifically introducing traversability-oriented strategies to manipulate diverse objects for path clearance. A systematic benchmark in Isaac Sim is proposed to evaluate both the reasoning and execution aspects of interactive navigation. Extensive simulations and real-world experiments demonstrate that CoINS significantly outperforms representative baselines, achieving a 17\% higher overall success rate and over 80\% improvement in complex long-horizon scenarios compared to the best-performing baseline

cs.RO↗

arXiv2025

Local Path Optimization in The Latent Space Using Learned Distance Gradient

Constrained motion planning is a common but challenging problem in robotic manipulation. In recent years, data-driven constrained motion planning algorithms have shown impressive planning speed and success rate. Among them, the latent motion method based on manifold approximation is the most efficient planning algorithm. Due to errors in manifold approximation and the difficulty in accurately identifying collision conflicts within the latent space, time-consuming path validity checks and path replanning are required. In this paper, we propose a method that trains a neural network to predict the minimum distance between the robot and obstacles using latent vectors as inputs. The learned distance gradient is then used to calculate the direction of movement in the latent space to move the robot away from obstacles. Based on this, a local path optimization algorithm in the latent space is proposed, and it is integrated with the path validity checking process to reduce the time of replanning. The proposed method is compared with state-of-the-art algorithms in multiple planning scenarios, demonstrating the fastest planning speed

cs.RO↗

arXiv2025

Interplay of Quasi-Quantum Hall Effect and Coulomb Disorder in Semimetals

Low carrier densities in topological semimetals (TSMs) enable the exploration of novel magnetotransport in the quantum limit (QL). Recent findings consistent with 3D quasi-quantum Hall effect (QQHE) have positioned TSMs as promising platforms for exploring 3D quantum Hall transport, but the lack of tunability in the Fermi level has thus far limited the ability to observe a QQHE signal. Here, we tune the defect concentrations in the Dirac semimetal Cd${}_3$As${}_2$ to achieve ultra-low carrier concentrations at 2 K around $2.9\times10^{16}$cm${}^{-3}$, giving way to QQHE signal at modest fields near 10 T. At low carrier densities, where QQHE is most accessible, we find that clear QQHE is obscured by a carrier density dependent background originating from Coulomb disorder from charged point defects and Landau level broadening. Our results highlight the interplay between QQHE and Coulomb disorder, demonstrating that clear observation of QQHE in TSMs intricately depends on Fermi level and disorder magnitudes. We find that Coulomb disorder, as theoretically predicted, is an essential ingredient for understanding the magnetoresistivity for a spectrum of Fermi levels in Cd${}_3$As${}_2$, anchoring the role of defects and charged disorder in TSM applications. We discuss future constraints and opportunities in exploring 3D QQHE and quantum Hall effects in TSMs.

cond-mat.mtrl-sci↗

arXiv2025

Enhanced superconducting diode effect in hybrid Josephson junctions

The superconducting diode effect (SDE) has recently been observed in various systems, sparking interest in novel superconducting devices and offering a new platform to probe intrinsic material properties. Josephson junctions with strong Rashba spin-orbit coupling have exhibited nonreciprocal critical currents under applied magnetic fields. In this work, we investigate the SDE in Josephson junctions incorporating periodic hole arrays patterned into the superconducting leads on InAs heterostructures with epitaxial aluminum. We observe an enhanced diode effect when a top gate depletes the 2DEG in the region of the hole arrays, while preserving the overall supercurrent. Theoretical analysis shows that the physics behind this phenomenon is the increased difference of transparency between different bands in the junction. These results highlight a new pathway for engineering and controlling nonreciprocal superconducting transport in hybrid systems.

cond-mat.mes-hall↗

arXiv2025

ARCADE: Adaptive Robot Control with Online Changepoint-Aware Bayesian Dynamics Learning

Real-world robots must operate under evolving dynamics caused by changing operating conditions, external disturbances, and unmodeled effects. These may appear as gradual drifts, transient fluctuations, or abrupt shifts, demanding real-time adaptation that is robust to short-term variation yet responsive to lasting change. We propose a framework for modeling the nonlinear dynamics of robotic systems that can be updated in real time from streaming data. The method decouples representation learning from online adaptation, using latent representations learned offline to support online closed-form Bayesian updates. To handle evolving conditions, we introduce a changepoint-aware mechanism with a latent variable inferred from data likelihoods that indicates continuity or shift. When continuity is likely, evidence accumulates to refine predictions; when a shift is detected, past information is tempered to enable rapid re-learning. This maintains calibrated uncertainty and supports probabilistic reasoning about transient, gradual, or structural change. We prove that the adaptive regret of the framework grows only logarithmically in time and linearly with the number of shifts, competitive with an oracle that knows timings of shift. We validate on cartpole simulations and real quadrotor flights with swinging payloads and mid-flight drops, showing improved predictive accuracy, faster recovery, and more accurate closed-loop tracking than relevant baselines.

cs.RO↗

arXiv2025

AERMANI-Diffusion: Regime-Conditioned Diffusion for Dynamics Learning in Aerial Manipulators

Aerial manipulators undergo rapid, configuration-dependent changes in inertial coupling forces and aerodynamic forces, making accurate dynamics modeling a core challenge for reliable control. Analytical models lose fidelity under these nonlinear and nonstationary effects, while standard data-driven methods such as deep neural networks and Gaussian processes cannot represent the diverse residual behaviors that arise across different operating conditions. We propose a regime-conditioned diffusion framework that models the full distribution of residual forces using a conditional diffusion process and a lightweight temporal encoder. The encoder extracts a compact summary of recent motion and configuration, enabling consistent residual predictions even through abrupt transitions or unseen payloads. When combined with an adaptive controller, the framework enables dynamics uncertainty compensation and yields markedly improved tracking accuracy in real-world tests.

cs.RO↗

arXiv2025

Enhancing Channel Estimation for OTFS systems using Sparse Bayesian Learning with Adaptive Threshold

Orthogonal time frequency space (OTFS) modulation is a two-dimensional modulation scheme designed in the delay-Doppler (DD) domain, exhibiting superior performance over orthogonal frequency division multiplexing (OFDM) modulation in environments with high Doppler frequency shifts. We investigated the channel estimation in the DD domain of OTFS systems, modeling it as a sparse signal recovery problem. Subsequently, within the existing sparse Bayesian learning framework, we proposed an adaptive Bayesian threshold-based active denoising mechanism. Combined with inverse-free sparse Bayesian learning, this effectively addresses the pseudo-peak issue in low signal-to-noise ratio (SNR) scenarios while maintaining low complexity. The simulation results demonstrate that this algorithm outperforms existing channel estimation algorithms in terms of anti-noise performance and complexity.

cs.IT↗

arXiv2025

Vehicle Dynamics Embedded World Models for Autonomous Driving

World models have gained significant attention as a promising approach for autonomous driving. By emulating human-like perception and decision-making processes, these models can predict and adapt to dynamic environments. Existing methods typically map high-dimensional observations into compact latent spaces and learn optimal policies within these latent representations. However, prior work usually jointly learns ego-vehicle dynamics and environmental transition dynamics from the image input, leading to inefficiencies and a lack of robustness to variations in vehicle dynamics. To address these issues, we propose the Vehicle Dynamics embedded Dreamer (VDD) method, which decouples the modeling of ego-vehicle dynamics from environmental transition dynamics. This separation allows the world model to generalize effectively across vehicles with diverse parameters. Additionally, we introduce two strategies to further enhance the robustness of the learned policy: Policy Adjustment during Deployment (PAD) and Policy Augmentation during Training (PAT). Comprehensive experiments in simulated environments demonstrate that the proposed model significantly improves both driving performance and robustness to variations in vehicle dynamics, outperforming existing approaches.

cs.RO↗

arXiv2025

VLM-SFD: VLM-Assisted Siamese Flow Diffusion Framework for Dual-Arm Cooperative Manipulation

Dual-arm cooperative manipulation holds great promise for tackling complex real-world tasks that demand seamless coordination and adaptive dynamics. Despite substantial progress in learning-based motion planning, most approaches struggle to generalize across diverse manipulation tasks and adapt to dynamic, unstructured environments, particularly in scenarios involving interactions between two objects such as assembly, tool use, and bimanual grasping. To address these challenges, we introduce a novel VLM-Assisted Siamese Flow Diffusion (VLM-SFD) framework for efficient imitation learning in dual-arm cooperative manipulation. The proposed VLM-SFD framework exhibits outstanding adaptability, significantly enhancing the ability to rapidly adapt and generalize to diverse real-world tasks from only a minimal number of human demonstrations. Specifically, we propose a Siamese Flow Diffusion Network (SFDNet) employs a dual-encoder-decoder Siamese architecture to embed two target objects into a shared latent space, while a diffusion-based conditioning process - conditioned by task instructions - generates two-stream object-centric motion flows that guide dual-arm coordination. We further design a dynamic task assignment strategy that seamlessly maps the predicted 2D motion flows into 3D space and incorporates a pre-trained vision-language model (VLM) to adaptively assign the optimal motion to each robotic arm over time. Experiments validate the effectiveness of the proposed method, demonstrating its ability to generalize to diverse manipulation tasks while maintaining high efficiency and adaptability. The code and demo videos are publicly available on our project website https://sites.google.com/view/vlm-sfd/.

cs.RO↗