arXiv subjects

Zijing Zhang

Publications and source records attributed to Zijing Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Chiral superconductors and competing states across a Lifshitz transition in rhombohedral pentalayer graphene

Rhombohedral multilayer graphene hosts a distinctive low-energy electronic structure in which strong Coulomb interactions and nontrivial quantum geometry intertwine to generate exotic quantum states. Recent experiments reported signatures of chiral superconductivity in electron-doped rhombohedral multilayer graphene within the spin- and valley-polarized regime. Here we map the normal-state fermiology surrounding chiral superconductivity in rhombohedral pentalayer graphene. Quantum oscillation measurements reveal an electrically controlled Lifshitz transition between a simply-connected circular quarter-metal Fermi surface and an annular quarter-metal Fermi surface. The Lifshitz boundary itself shifts with perpendicular magnetic field, consistent with the strongly momentum-dependent orbital magnetic moment of the low-energy band. Approaching the transition from either side, the electron effective mass becomes strongly enhanced, implying the formation of a nearly dispersionless band bottom and a strongly reduced kinetic-energy scale. This singular electronic structure produces a regime of exceptionally strong instability in which chiral superconductivity competes with Wigner crystalline phases and reentrant quantum Hall states. In particular, two superconducting regions with signatures of orbital time-reversal-symmetry breaking lie on opposite sides of the Lifshitz boundary and have comparable transition temperatures, yet the annular-side state is suppressed by a substantially smaller perpendicular magnetic field. Our calculation finds comparable chiral pairing tendencies on the two parent Fermi surfaces while producing a much lower orbital-Zeeman pair-breaking scale and an additional finite-momentum pairing tendency for the annular state. These results identify Fermi-surface topology as a key control parameter for chiral superconductivity in rhombohedral graphene.

cond-mat.mes-hall↗

arXiv2026

MemGuard: Persisting Verifier Signals for LLM-Agent Memory Governance

LLM agents are moving from single-prompt use to long task streams in which reusable memory becomes a core capability for terminal, software-engineering, and web tasks. Such memory is useful only when stored experience remains reliable across hundreds of interactions, but two failure modes break that assumption in practice. The first is unreliable admission: failed trajectories,accidental successes, and misleading observations enter memory because they appear relevant, then mislead later decisions. The second is memory drift: long-running banks accumulate duplicate, stale, and conflicting records that retrieval alone cannot repair. MemGuard's key distinction is to treat verifier output not as a one-shot filter, but as persistent lifecycle metadata. It converts multi-criteria score-token verification into reward, confidence, label, and uncertainty descriptors that are attached to every candidate before activation and reused during retrieval, conflict resolution, summarization, and archival. We evaluate MemGuard on Terminal-Bench 2.0, SWE-Bench Verified, WebArena, and Mind2Web across four backbones, comparing against four memory baselines plus a verifier-only control under matched runtime budgets. Averaged over five seeds, MemGuard achieves the best success metric and lowest average steps in all 16 backbone-benchmark settings, improving over ReasoningBank, the strongest prior baseline among the memory methods we evaluate, with a largest gain of 7.9 success-rate points on WebArena, 5.6 step-success-rate points on Mind2Web, and 2.4-3.5 points on terminal and software-engineering benchmarks. Code is available at https://github.com/whyyyyy123/MemGuard.

cs.AI↗

arXiv2026

Lightweight Safe Reinforcement Learning for End-to-End UAV Navigation

With the rapid development of autonomous aerial systems, Unmanned Aerial Vehicles (UAVs) are increasingly deployed in applications such as inspection, environmental monitoring, and rescue, creating growing demand for reliable autonomous navigation. However, autonomous UAV navigation in dense environments remains challenging under sparse perception and dynamic constraints. Most reinforcement learning (RL) methods lack explicit safety mechanisms, leading to unsafe exploration, unstable training, and risky behaviors, especially during high-speed flight. Even in safe RL approaches, safety is often enforced by projecting policy outputs onto a safe action set, which may introduce instability. Meanwhile, many learning-based methods rely on dense inputs or large networks, increasing computational burden and limiting lightweight onboard deployment. Facing the above challenges, we propose a safety-constrained perception-control integrated framework for UAV navigation. A lightweight network encodes sparse observations into collision-risk-aware features using asymmetric and depthwise separable convolutions. We formulate the task as a constrained Markov decision process within a hierarchical control architecture and solve it using a Lagrangian-based safe PPO algorithm. Curriculum learning further improves training stability. Experiments with varying obstacle densities and flight speeds demonstrate higher success rates, improved safety, and better efficiency than existing reinforcement learning baselines.

cs.RO↗

arXiv2026

Can non-orthogonal bases form stable skyrmionic beams?

Skyrmions, topologically stable spin textures, have recently garnered significant attention in optics promising robust high-density information transition and nontrivial light-matter interaction. It was believed that the optical skyrmionic beams should be constructed by superposition of two orthogonal spatial modes with orthogonal polarizations to obtain topologically stable propagation. Here, we surprisingly find that propagation-stable skyrmionic beams can still be formed by superpositions of neither orthogonal spatial modes nor orthogonal polarizations. We theoretically present the mechanism to control the stable skyrmionics beams through the hybrid superposition of modes from the Hermite-Gaussian and Laguerre-Gaussian families and experimentally control the longitudinal on-demand dynamics of the skyrmions. This work redefines the topological stability of optical skyrmions, breaks limits and reduces the requirement for manipulating topologically structured light for practical multidimensional implementation of topologically robust information technologies.

physics.optics↗

arXiv2025

RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success often reinforce flawed or inefficient reasoning paths, a problem we term inefficient exploration. This leads to agents that are brittle and fail to generalize, as they learn to find solutions without learning how to reason coherently. To address this, we introduce RLVMR, a novel framework that integrates dense, process-level supervision into end-to-end RL by rewarding verifiable, meta-reasoning behaviors. RLVMR equips an agent to explicitly tag its cognitive steps, such as planning, exploration, and reflection, and provides programmatic, rule-based rewards for actions that contribute to effective problem-solving. These process-centric rewards are combined with the final outcome signal and optimized using a critic-free policy gradient method. On the challenging ALFWorld and ScienceWorld benchmarks, RLVMR achieves new state-of-the-art results, with our 7B model reaching an 83.6% success rate on the most difficult unseen task split. Our analysis confirms these gains stem from improved reasoning quality, including significant reductions in redundant actions and enhanced error recovery, leading to more robust, efficient, and interpretable agents.

cs.LG↗

arXiv2025

GRAIN: Multi-Granular and Implicit Information Aggregation Graph Neural Network for Heterophilous Graphs

Graph neural networks (GNNs) have shown significant success in learning graph representations. However, recent studies reveal that GNNs often fail to outperform simple MLPs on heterophilous graph tasks, where connected nodes may differ in features or labels, challenging the homophily assumption. Existing methods addressing this issue often overlook the importance of information granularity and rarely consider implicit relationships between distant nodes. To overcome these limitations, we propose the Granular and Implicit Graph Network (GRAIN), a novel GNN model specifically designed for heterophilous graphs. GRAIN enhances node embeddings by aggregating multi-view information at various granularity levels and incorporating implicit data from distant, non-neighboring nodes. This approach effectively integrates local and global information, resulting in smoother, more accurate node representations. We also introduce an adaptive graph information aggregator that efficiently combines multi-granularity and implicit data, significantly improving node representation quality, as shown by experiments on 13 datasets covering varying homophily and heterophily. GRAIN consistently outperforms 12 state-of-the-art models, excelling on both homophilous and heterophilous graphs.

cs.LG↗

arXiv2022

Novel Muscle Monitoring by Radiomyography(RMG) and Application to Hand Gesture Recognition

Conventional electromyography (EMG) measures the continuous neural activity during muscle contraction, but lacks explicit quantification of the actual contraction. Mechanomyography (MMG) and accelerometers only measure body surface motion, while ultrasound, CT-scan and MRI are restricted to in-clinic snapshots. Here we propose a novel radiomyography (RMG) for continuous muscle actuation sensing that can be wearable and touchless, capturing both superficial and deep muscle groups. We verified RMG experimentally by a forearm wearable sensor for detailed hand gesture recognition. We first converted the radio sensing outputs to the time-frequency spectrogram, and then employed the vision transformer (ViT) deep learning network as the classification model, which can recognize 23 gestures with an average accuracy up to 99% on 8 subjects. By transfer learning, high adaptivity to user difference and sensor variation were achieved at an average accuracy up to 97%. We further demonstrated RMG to monitor eye and leg muscles and achieved high accuracy for eye movement and body postures tracking. RMG can be used with synchronous EMG to derive stimulation-actuation waveforms for many future applications in kinesiology, physiotherapy, rehabilitation, and human-machine interface.

cs.HC↗

arXiv2022

Objective dyspnea evaluation on COVID-19 patients learning from exertion-induced dyspnea scores

Objective: Dyspnea is one of the most common symptoms for many pulmonary diseases including COVID-19. Clinical assessment of dyspnea is mainly performed by subjective self-report, which has limited accuracy and is challenging for continuous monitoring. The objective of this research study is to determine if dyspnea progression in COVID patients can be assessed using a non-invasive wearable sensor and if the findings are comparable to a learning model of physiologically induced dyspnea on healthy subjects. Methods: Non-invasive wearable respiratory sensors were employed to retrieve continuous respiratory characteristics with user comfort and convenience. Overnight (~16h) respiratory waveforms were collected on 12 COVID-19 patients, and a benchmark on 13 healthy subjects with exertion-induced dyspnea were also performed for blind comparison. The learning model was built from the respiratory features with self report on 32 healthy subjects under exertion and airway blockage. Results: High similarity between dyspnea on COVID patients and physiologically induced dyspnea on healthy subjects was established. COVID patients have consistently high objective dyspnea scores in comparison with normal breathing of healthy subjects. We also exhibited continuous dyspnea scoring capability for 12-16 hours on patients. Conclusion: This paper validates the viability to use our objective dyspnea scoring for clinical dyspnea assessment on COVID patients. Significance: The proposed system can help the identification of dyspneic exacerbation in conditions such as COVID, leading to early intervention and possibly improving their outcome. This approach can be potentially applied to other pulmonary disorders such as asthma, emphysema, and pneumonia.

eess.SY↗

arXiv2022

Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction

Graph convolutional network based methods that model the body-joints' relations, have recently shown great promise in 3D skeleton-based human motion prediction. However, these methods have two critical issues: first, deep graph convolutions filter features within only limited graph spectrums, losing sufficient information in the full band; second, using a single graph to model the whole body underestimates the diverse patterns on various body-parts. To address the first issue, we propose adaptive graph scattering, which leverages multiple trainable band-pass graph filters to decompose pose features into richer graph spectrum bands. To address the second issue, body-parts are modeled separately to learn diverse dynamics, which enables finer feature extraction along the spatial dimensions. Integrating the above two designs, we propose a novel skeleton-parted graph scattering network (SPGSN). The cores of the model are cascaded multi-part graph scattering blocks (MPGSBs), building adaptive graph scattering on diverse body-parts, as well as fusing the decomposed features based on the inferred spectrum importance and body-part interactions. Extensive experiments have shown that SPGSN outperforms state-of-the-art methods by remarkable margins of 13.8%, 9.3% and 2.7% in terms of 3D mean per joint position error (MPJPE) on Human3.6M, CMU Mocap and 3DPW datasets, respectively.

cs.CV↗

arXiv2021

Accurate parameter estimation using scan-specific unsupervised deep learning for relaxometry and MR fingerprinting

We propose an unsupervised convolutional neural network (CNN) for relaxation parameter estimation. This network incorporates signal relaxation and Bloch simulations while taking advantage of residual learning and spatial relations across neighboring voxels. Quantification accuracy and robustness to noise is shown to be significantly improved compared to standard parameter estimation methods in numerical simulations and in vivo data for multi-echo T2 and T2* mapping. The combination of the proposed network with subspace modeling and MR fingerprinting (MRF) from highly undersampled data permits high quality T1 and T2 mapping.

eess.IV↗

arXiv2021

Ultrafast Spin-to-Orbit and Orbit-to-Local-Spin Conversions of Tightly Focused Hybridly Polarized Light Pulses

Spin-orbit interaction (SOI) have provided a new viable roadmap for the development of spin-based photonics devices. However, existing strategies to control the SOI focus commonly on tailoring the spatial dimension of light fields yet neglecting the inherent temporal one. Herein, we first present ultrafast temporal effects on both spin-to-orbit and orbit-to-local-spin conversions based on the time-assistant vectorial diffractive theory and the fast Fourier transformation. Such interconversions depend upon whether the incident hybridly vectorial light pulse carries vortex phase or not in a single high numerical aperture geometry. For the case of the absence of vortex phase, we find that it enables orbit angular momentum-carrying transverse component fields, and the resultant orbit angular momentum embedded within focused light fields remains constantly revolving as time elapses, which indicates that the controllable spin-to-orbit conversion occurs. By contrast, it is revealed that hybridly polarized vectorial-vortex light pulses allow access to the locally excited circular polarization at the focus, and this induced local circular polarization is independent of ultrafast varying time, whereas the resulting spin angular momentum density components experience the alternation between the appearance and annihilation over time, thus giving rise to the tunable orbit-to-local-spin conversion. These exotic ultrafast interconversions not only breathe a new life into the area of ultrafast photonics, but refresh our understanding on the paradigm of photonic SOI.

physics.optics↗

arXiv2021

BUDA-SAGE with self-supervised denoising enables fast, distortion-free, high-resolution T2, T2*, para- and dia-magnetic susceptibility mapping

To rapidly obtain high resolution T2, T2* and quantitative susceptibility mapping (QSM) source separation maps with whole-brain coverage and high geometric fidelity. We propose Blip Up-Down Acquisition for Spin And Gradient Echo imaging (BUDA-SAGE), an efficient echo-planar imaging (EPI) sequence for quantitative mapping. The acquisition includes multiple T2*-, T2'- and T2-weighted contrasts. We alternate the phase-encoding polarities across the interleaved shots in this multi-shot navigator-free acquisition. A field map estimated from interim reconstructions was incorporated into the joint multi-shot EPI reconstruction with a structured low rank constraint to eliminate geometric distortion. A self-supervised MR-Self2Self (MR-S2S) neural network (NN) was utilized to perform denoising after BUDA reconstruction to boost SNR. Employing Slider encoding allowed us to reach 1 mm isotropic resolution by performing super-resolution reconstruction on BUDA-SAGE volumes acquired with 2 mm slice thickness. Quantitative T2 and T2* maps were obtained using Bloch dictionary matching on the reconstructed echoes. QSM was estimated using nonlinear dipole inversion (NDI) on the gradient echoes. Starting from the estimated R2 and R2* maps, R2' information was derived and used in source separation QSM reconstruction, which provided additional para- and dia-magnetic susceptibility maps. In vivo results demonstrate the ability of BUDA-SAGE to provide whole-brain, distortion-free, high-resolution multi-contrast images and quantitative T2 and T2* maps, as well as yielding para- and dia-magnetic susceptibility maps. Derived quantitative maps showed comparable values to conventional mapping methods in phantom and in vivo measurements. BUDA-SAGE acquisition with self-supervised denoising and Slider encoding enabled rapid, distortion-free, whole-brain T2, T2* mapping at 1 mm3 isotropic resolution in 90 seconds.

physics.med-ph↗

arXiv2021

Multidimensional Information Assisted Deep Learning Realizing Flexible Recognition of Vortex Beam Modes

Because of the unlimited range of state space, orbital angular momentum (OAM) as a new degree of freedom of light has attracted great attention in optical communication field. Recently there are a number of researches applying deep learning on recognition of OAM modes through atmospheric turbulence. However, there are several limitations in previous deep learning recognition methods. They all require a constant distance between the laser and receiver, which makes them clumsy and not practical. As far as we know, previous deep learning methods cannot sort vortex beams with positive and negative topological charges, which can reduce information capacity. A Multidimensional Information Assisted Deep Learning Flexible Recognition (MIADLFR) method is proposed in this letter. In MIADLR we utilize not only the intensity profile, also spectrum information to recognize OAM modes unlimited by distance and sign of topological charge (TC). As far as we know, we first make use of multidimensional information to recognize OAM modes and we first utilize spectrum information to recognize OAM modes. Recognition of OAM modes unlimited by distance and sign of TC achieved by MIADLFR method can make optical communication and detection by OAM light much more attractive.

physics.optics↗

arXiv2021

Highly Accelerated EPI with Wave Encoding and Multi-shot Simultaneous Multi-Slice Imaging

We introduce wave encoded acquisition and reconstruction techniques for highly accelerated echo planar imaging (EPI) with reduced g-factor penalty and image artifacts. Wave-EPI involves playing sinusoidal gradients during the EPI readout while employing interslice shifts as in blipped-CAIPI acquisitions. This spreads the aliasing in all spatial directions, thereby taking better advantage of 3D coil sensitivity profiles. The amount of voxel spreading that can be achieved by the wave gradients during the short EPI readout period is constrained by the slew rate of the gradient coils and peripheral nerve stimulation (PNS) monitor. We propose to use a half-cycle sinusoidal gradient to increase the amount of voxel spreading that can be achieved while respecting the slew and stimulation constraints. Extending wave-EPI to multi-shot acquisition minimizes geometric distortion and voxel blurring at high in-plane resolution, while structured low-rank regularization mitigates shot-to-shot phase variations without additional navigators. We propose to use different point spread functions (PSFs) for the k-space lines with positive and negative polarities, which are calibrated with a FLEET-based reference scan and allow for addressing gradient imperfections. Wave-EPI provided whole-brain single-shot gradient echo (GE) and multi-shot spin echo (SE) EPI acquisitions at high acceleration factors and was combined with g-Slider slab encoding to boost the SNR level in 1mm isotropic diffusion imaging. Relative to blipped-CAIPI, wave-EPI reduced average and maximum g-factors by up to 1.21- and 1.37-fold, respectively. In conclusion, wave-EPI allows highly accelerated single- and multi-shot EPI with reduced g-factor and artifacts and may facilitate clinical and neuroscientific applications of EPI by improving the spatial and temporal resolution in functional and diffusion imaging.

eess.IV↗

arXiv2020

Efficient T2 mapping with Blip-up/down EPI and gSlider-SMS (T2-BUDA-gSlider)

Purpose: To rapidly obtain high isotropic-resolution T2 maps with whole-brain coverage and high geometric fidelity. Methods: A T2 blip-up/down echo planar imaging (EPI) acquisition with generalized Slice-dithered enhanced resolution (T2-BUDA-gSlider) is proposed. A radiofrequency (RF)-encoded multi-slab spin-echo EPI acquisition with multiple echo times (TEs) was developed to obtain high SNR efficiency with reduced repetition time (TR). This was combined with an interleaved 2-shot EPI acquisition using blip-up/down phase encoding. An estimated field map was incorporated into the joint multi-shot EPI reconstruction with a structured low rank constraint to achieve distortion-free and robust reconstruction for each slab without navigation. A Bloch simulated subspace model was integrated into gSlider reconstruction and utilized for T2 quantification. Results: In vivo results demonstrated that the T2 values estimated by the proposed method were consistent with gold standard spin-echo acquisition. Compared to the reference 3D fast spin echo (FSE) images, distortion caused by off-resonance and eddy current effects were effectively mitigated. Conclusion: BUDA-gSlider SE-EPI acquisition and gSlider-subspace joint reconstruction enabled distortion-free whole-brain T2 mapping in 2 min at ~1 mm3 isotropic resolution, which could bring significant benefits to related clinical and neuroscience applications.

physics.med-ph↗

arXiv2019

Scan-specific, Parameter-free Artifact Reduction in K-space (SPARK)

We propose a convolutional neural network (CNN) approach that works synergistically with physics-based reconstruction methods to reduce artifacts in accelerated MRI. Given reconstructed coil k-spaces, our network predicts a k-space correction term for each coil. This is done by matching the difference between the acquired autocalibration lines and their erroneous reconstructions, and generalizing this error term over the entire k-space. Application of this approach on existing reconstruction methods show that SPARK suppresses reconstruction artifacts at high acceleration, while preserving and improving on detail in moderate acceleration rates where existing reconstruction algorithms already perform well; indicating robustness. Introduction Parallel

eess.IV↗

arXiv2019

Highly efficient MRI through multi-shot echo planar imaging

Multi-shot echo planar imaging (msEPI) is a promising approach to achieve high in-plane resolution with high sampling efficiency and low T2* blurring. However, due to the geometric distortion, shot-to-shot phase variations and potential subject motion, msEPI continues to be a challenge in MRI. In this work, we introduce acquisition and reconstruction strategies for robust, high-quality msEPI without phase navigators. We propose Blip Up-Down Acquisition (BUDA) using interleaved blip-up and -down phase encoding, and incorporate B0 forward-modeling into Hankel structured low-rank model to enable distortion- and navigator-free msEPI. We improve the acquisition efficiency and reconstruction quality by incorporating simultaneous multi-slice acquisition and virtual-coil reconstruction into the BUDA technique. We further combine BUDA with the novel RF-encoded gSlider acquisition, dubbed BUDA-gSlider, to achieve rapid high isotropic-resolution MRI. Deploying BUDA-gSlider with model-based reconstruction allows for distortion-free whole-brain 1mm isotropic T2 mapping in about 1 minute. It also provides whole-brain 1mm isotropic diffusion imaging with high geometric fidelity and SNR efficiency. We finally incorporate sinusoidal wave gradients during the EPI readout to better use coil sensitivity encoding with controlled aliasing.

eess.IV↗

arXiv2018

Orbital-angular-momentum-enhanced estimation of sub-Heisenberg-limited angular displacement with two-mode squeezed vacuum and parity detection

We report on an orbital-angular-momentum-enhanced scheme for angular displacement estimation based on two-mode squeezed vacuum and parity detection. The sub-Heisenberg-limited sensitivity for angular displacement estimation is obtained in an ideal situation. Several realistic factors are also considered, including photon loss, dark counts, response-time delay, and thermal photon noise. Our results indicate that the effects of the realistic factors on the sensitivity can be offset by raising orbital angular momentum quantum number $\ell$. This reflects that the robustness and the practicability of the system can be improved via raising $\ell$ without changing mean photon number $N$.

quant-ph↗