arXiv subjects

Zhi Wang

Publications and source records attributed to Zhi Wang.

At least 145 records · Page 8Linked to original sources

arXiv2025

Berry Curvature Induced Spin Nernst and Thermal Edelstein Effects in Proximity Superconductors

We propose two thermo-spintronic responses in proximity induced superconductors with spin-orbit coupled band - spin Nernst effect and thermal Edelstein effect stemming respectively from momentum-space and mixed superconducting Berry curvatures. We unveil that the Bloch band spin-orbit coupling and pairing are entangled in shaping the superconducting Berry curvatures rather than in an additive manner. The resulting thermo-spintronic responses are significantly enhanced at low temperatures by the emergence of Bogoliubov Fermi surface, and can be effectively controlled by tuning the latter. The effects render a probe of Bogoliubov Fermi surface and superconducting Berry curvatures supported by it. Our work reveals Berry curvature properties in topologically trivial proximity superconductors with spin-orbit coupling, and opens a new route to superconducting spintronics.

cond-mat.supr-con↗

arXiv2025

Enhancing Cutoff Energy of Solid High-Harmonic Generation from Bonding Length Perspective

High-harmonic generation (HHG) from solid state offers promising potential for attosecond optics with enhanced efficiency and compact configurations. However, Current implementations face critical limitations imposed by material damage thresholds, directly restricting spectral cutoff energies in nonperturbative regime. In this study, we control the cutoff energy through tailoring the bond length of materials, which is available by experimental strain. Employing real-time time-dependent density theory (rt-TDDFT) simulations, we find that the cutoff energy increases by nearly one third under a bond length compression of 7.5%. Our results reveal that it originates the band gap widening inducing the enhancement of interband cutoff energy, which is material-independent. This work provides novel theoretical insights for optimizing extreme ultraviolet sources, advancing potential applications in attosecond physics.

physics.optics↗

arXiv2025

Music-Aligned Holistic 3D Dance Generation via Hierarchical Motion Modeling

Well-coordinated, music-aligned holistic dance enhances emotional expressiveness and audience engagement. However, generating such dances remains challenging due to the scarcity of holistic 3D dance datasets, the difficulty of achieving cross-modal alignment between music and dance, and the complexity of modeling interdependent motion across the body, hands, and face. To address these challenges, we introduce SoulDance, a high-precision music-dance paired dataset captured via professional motion capture systems, featuring meticulously annotated holistic dance movements. Building on this dataset, we propose SoulNet, a framework designed to generate music-aligned, kinematically coordinated holistic dance sequences. SoulNet consists of three principal components: (1) Hierarchical Residual Vector Quantization, which models complex, fine-grained motion dependencies across the body, hands, and face; (2) Music-Aligned Generative Model, which composes these hierarchical motion units into expressive and coordinated holistic dance; (3) Music-Motion Retrieval Module, a pre-trained cross-modal model that functions as a music-dance alignment prior, ensuring temporal synchronization and semantic coherence between generated dance and input music throughout the generation process. Extensive experiments demonstrate that SoulNet significantly surpasses existing approaches in generating high-quality, music-coordinated, and well-aligned holistic 3D dance sequences.

cs.MM↗

arXiv2025

Generative molecule evolution using 3D pharmacophore for efficient Structure-Based Drug Design

Recent advances in generative models, particularly diffusion and auto-regressive models, have revolutionized fields like computer vision and natural language processing. However, their application to structure-based drug design (SBDD) remains limited due to critical data constraints. To address the limitation of training data for models targeting SBDD tasks, we propose an evolutionary framework named MEVO, which bridges the gap between billion-scale small molecule dataset and the scarce protein-ligand complex dataset, and effectively increase the abundance of training data for generative SBDD models. MEVO is composed of three key components: a high-fidelity VQ-VAE for molecule representation in latent space, a diffusion model for pharmacophore-guided molecule generation, and a pocket-aware evolutionary strategy for molecule optimization with physics-based scoring function. This framework efficiently generate high-affinity binders for various protein targets, validated with predicted binding affinities using free energy perturbation (FEP) methods. In addition, we showcase the capability of MEVO in designing potent inhibitors to KRAS$^{\textrm{G12D}}$, a challenging target in cancer therapeutics, with similar affinity to the known highly active inhibitor evaluated by FEP calculations. With high versatility and generalizability, MEVO offers an effective and data-efficient model for various tasks in structure-based ligand design.

cs.LG↗

arXiv2025

Origin of Suppressed Ferroelectricity in k-Ga$_2$O$_3$: Interplay Between Polarization and Lattice Domain Walls

The large discrepancy between experimental and theoretical remanent polarization and coercive field limits the applications of wide-band-gap ferroelectric materials. Here, using a machine-learning potential trained on ab-initio molecular dynamics data, we identify a new mechanism of the interplay between polarization domain wall (PDW) and lattice domain wall (LDW) in ferroelectric k-phase gallium oxide (Ga2O3), which reconciles predictions with experimental observations. Our results reveal that the reversal of out-of-plane polarization is achieved through in-plane sliding and shear of the Ga-O sublayers. This pathway creates strong anisotropy in PDW propagation, and crucially leads to topologically forbidden PDW propagation across the 120 degree LDWs observed in synthesized samples. The resulting stable network of residual domain walls bypasses slow nucleation and suppresses the observable polarization and coercive field. These insights highlight the potential for tailoring the ferroelectric response in k-Ga2O3 from lattice-domain engineering.

cond-mat.mtrl-sci↗

arXiv2025

CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning

Utilizing large language models (LLMs) for tool planning has emerged as a promising avenue for developing general AI systems, where LLMs automatically schedule external tools (e.g., vision models) to tackle complex tasks based on task descriptions. To push this paradigm toward practical applications, it is crucial for LLMs to consider tool execution costs (e.g., execution time) for tool planning. Unfortunately, prior studies overlook the tool execution costs, leading to the generation of expensive plans whose costs outweigh their benefits in terms of task performance. To fill this gap, we propose the Cost-Aware Tool Planning with LLMs (CATP-LLM) framework, which for the first time provides a coherent design to empower LLMs for cost-aware tool planning. Specifically, To facilitate efficient concurrent tool execution and cost reduction, we design a tool planning language to enhance the LLM for creating multi-branch non-sequential plans. Moreover, we propose a cost-aware offline reinforcement learning algorithm to fine-tune the LLM to optimize the performance-cost trade-off in tool planning. In the lack of public cost-related datasets, we further present OpenCATP, the first dataset for cost-aware planning, which comprises 11,100 evaluation samples from diverse tasks. Extensive experiments show that CATP-LLM outperforms GPT-4 even when using Llama2-7B as its backbone, with the average improvement of 1.5%-93.9% in terms of plan quality. Codes and dataset are available at: https://github.com/duowuyms/OpenCATP-LLM.

cs.AI↗

arXiv2025

Revealing Material-Dependent Bicircular High-Order Harmonic Generation in 2D Semiconductors via Real-Space Trajectories

Solid-state high-order harmonic generation (HHG) presents unique features different from gases.Whereas the gaseous harmonics driven by counter-rotating bicircular (CRB) pulse universally peak at a "magic" field ratio approximately E_2ω:E_ω=1.5:1, crystals exhibit significant material-dependent responses. In monolayer MoS2, the harmonic yield experiences two maxima at the gas-like 1.5:1 ratio, and again in the single-color limit, whereas monolayer hBN shows a monotonic increase as the 2ω component dominates. Combining time-dependent density-functional theory (TDDFT) and a minimal real-space trajectory analysis, we show that these differences arise from the interplay of Bloch velocity and anomalous Hall velocity. The trajectory model quantitatively reproduces the ab-initio results, and offers an intuitive prediction of the harmonics yield without further heavy computation. These insights provide practical guidance for tailoring solid-state HHG and for selecting 2D compounds with desirable responses.

physics.optics↗

arXiv2025

SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction

Current 4D Gaussian frameworks for dynamic scene reconstruction deliver impressive visual fidelity and rendering speed, however, the inherent trade-off between storage costs and the ability to characterize complex physical motions significantly limits the practical application of these methods. To tackle these problems, we propose SD-GS, a compact and efficient dynamic Gaussian splatting framework for complex dynamic scene reconstruction, featuring two key contributions. First, we introduce a deformable anchor grid, a hierarchical and memory-efficient scene representation where each anchor point derives multiple 3D Gaussians in its local spatiotemporal region and serves as the geometric backbone of the 3D scene. Second, to enhance modeling capability for complex motions, we present a deformation-aware densification strategy that adaptively grows anchors in under-reconstructed high-dynamic regions while reducing redundancy in static areas, achieving superior visual quality with fewer anchors. Experimental results demonstrate that, compared to state-of-the-art methods, SD-GS achieves an average of 60\% reduction in model size and an average of 100\% improvement in FPS, significantly enhancing computational efficiency while maintaining or even surpassing visual quality.

cs.GR↗

arXiv2025

SAT-BO: Verification Rule Learning and Optimization for FraudTransaction Detection

Electronic payment platforms are estimated to process billions oftransactions daily, with the cumulative value of these transactionspotentially reaching into the trillions. Even a minor error within thishigh-volume environment could precipitate substantial financiallosses. To mitigate this risk, manually constructed verification rules,developed by domain experts, are typically employed to identifyand scrutinize transactions in production environments. However,due to the absence of a systematic approach to ensure the robust-ness of these verification rules against vulnerabilities, they remainsusceptible to exploitation.To mitigate this risk, manually constructed verification rules, de-veloped by domain experts, are typically employed to identify andscrutinize transactions in production environments. However, dueto the absence of a systematic approach to ensure the robustness ofthese verification rules against vulnerabilities, they remain suscep-tible to exploitation. To ensure data security, database maintainersusually compose complex verification rules to check whether aquery/update request is valid. However, the rules written by ex-perts are usually imperfect, and malicious requests may bypassthese rules. As a result, the demand for identifying the defects ofthe rules systematically emerges.

cs.CR↗

arXiv2025

Learning to Reason under Off-Policy Guidance

Recent advances in large reasoning models (LRMs) demonstrate that sophisticated behaviors such as multi-step reasoning and self-reflection can emerge via reinforcement learning with verifiable rewards~(\textit{RLVR}). However, existing \textit{RLVR} approaches are inherently ``on-policy'', limiting learning to a model's own outputs and failing to acquire reasoning abilities beyond its initial capabilities. To address this issue, we introduce \textbf{LUFFY} (\textbf{L}earning to reason \textbf{U}nder o\textbf{FF}-polic\textbf{Y} guidance), a framework that augments \textit{RLVR} with off-policy reasoning traces. LUFFY dynamically balances imitation and exploration by combining off-policy demonstrations with on-policy rollouts during training. Specifically, LUFFY combines the Mixed-Policy GRPO framework, which has a theoretically guaranteed convergence rate, alongside policy shaping via regularized importance sampling to avoid superficial and rigid imitation during mixed-policy training. Compared with previous RLVR methods, LUFFY achieves an over \textbf{+6.4} average gain across six math benchmarks and an advantage of over \textbf{+6.2} points in out-of-distribution tasks. Most significantly, we show that LUFFY successfully trains weak models in scenarios where on-policy RLVR completely fails. These results provide compelling evidence that LUFFY transcends the fundamental limitations of on-policy RLVR and demonstrates the great potential of utilizing off-policy guidance in RLVR.

cs.LG↗

arXiv2025

Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World

Despite progress, deep neural networks still suffer performance declines under distribution shifts between training and test domains, leading to a substantial decrease in Quality of Experience (QoE) for applications. Existing test-time adaptation (TTA) methods are challenged by dynamic, multiple test distributions within batches. We observe that feature distributions across different domains inherently cluster into distinct groups with varying means and variances. This divergence reveals a critical limitation of previous global normalization strategies in TTA, which inevitably distort the original data characteristics. Based on this insight, we propose Feature-based Instance Neighbor Discovery (FIND), which comprises three key components: Layer-wise Feature Disentanglement (LFD), Feature Aware Batch Normalization (FABN) and Selective FABN (S-FABN). LFD stably captures features with similar distributions at each layer by constructing graph structures. While FABN optimally combines source statistics with test-time distribution specific statistics for robust feature representation. Finally, S-FABN determines which layers require feature partitioning and which can remain unified, thereby enhancing inference efficiency. Extensive experiments demonstrate that FIND significantly outperforms existing methods, achieving a 30\% accuracy improvement in dynamic scenarios while maintaining computational efficiency.

cs.LG↗

arXiv2025

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy. Such phenomenon is consistently observed across vast RL runs without entropy intervention, where the policy entropy dropped sharply at the early training stage, this diminished exploratory ability is always accompanied with the saturation of policy performance. In practice, we establish a transformation equation R=-a*e^H+b between entropy H and downstream performance R. This empirical law strongly indicates that, the policy performance is traded from policy entropy, thus bottlenecked by its exhaustion, and the ceiling is fully predictable H=0, R=-a+b. Our finding necessitates entropy management for continuous exploration toward scaling compute for RL. To this end, we investigate entropy dynamics both theoretically and empirically. Our derivation highlights that, the change in policy entropy is driven by the covariance between action probability and the change in logits, which is proportional to its advantage when using Policy Gradient-like algorithms. Empirical study shows that, the values of covariance term and entropy differences matched exactly, supporting the theoretical conclusion. Moreover, the covariance term stays mostly positive throughout training, further explaining why policy entropy would decrease monotonically. Through understanding the mechanism behind entropy dynamics, we motivate to control entropy by restricting the update of high-covariance tokens. Specifically, we propose two simple yet effective techniques, namely Clip-Cov and KL-Cov, which clip and apply KL penalty to tokens with high covariances respectively. Experiments show that these methods encourage exploration, thus helping policy escape entropy collapse and achieve better downstream performance.

cs.LG↗

arXiv2025

Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning

While showing sophisticated reasoning abilities, large language models (LLMs) still struggle with long-horizon decision-making tasks due to deficient exploration and long-term credit assignment, especially in sparse-reward scenarios. Inspired by the divide-and-conquer principle, we propose an innovative framework **GLIDER** (**G**rounding **L**anguage Models as Eff**I**cient **D**ecision-Making Agents via Offline Hi**E**rarchical **R**einforcement Learning) that introduces a parameter-efficient and generally applicable hierarchy to LLM policies. We develop a scheme where the low-level controller is supervised with abstract, step-by-step plans that are learned and instructed by the high-level policy. This design decomposes complicated problems into a series of coherent chain-of-thought reasoning sub-tasks, providing flexible temporal abstraction to significantly enhance exploration and learning for long-horizon tasks. Furthermore, GLIDER facilitates fast online adaptation to non-stationary environments owing to the strong transferability of its task-agnostic low-level skills. Experiments on ScienceWorld and ALFWorld benchmarks show that GLIDER achieves consistent performance gains, along with enhanced generalization capabilities.

cs.AI↗

arXiv2025

$γ$-FedHT: Stepsize-Aware Hard-Threshold Gradient Compression in Federated Learning

Gradient compression can effectively alleviate communication bottlenecks in Federated Learning (FL). Contemporary state-of-the-art sparse compressors, such as Top-$k$, exhibit high computational complexity, up to $\mathcal{O}(d\log_2{k})$, where $d$ is the number of model parameters. The hard-threshold compressor, which simply transmits elements with absolute values higher than a fixed threshold, is thus proposed to reduce the complexity to $\mathcal{O}(d)$. However, the hard-threshold compression causes accuracy degradation in FL, where the datasets are non-IID and the stepsize $γ$ is decreasing for model convergence. The decaying stepsize reduces the updates and causes the compression ratio of the hard-threshold compression to drop rapidly to an aggressive ratio. At or below this ratio, the model accuracy has been observed to degrade severely. To address this, we propose $γ$-FedHT, a stepsize-aware low-cost compressor with Error-Feedback to guarantee convergence. Given that the traditional theoretical framework of FL does not consider Error-Feedback, we introduce the fundamental conversation of Error-Feedback. We prove that $γ$-FedHT has the convergence rate of $\mathcal{O}(\frac{1}{T})$ ($T$ representing total training iterations) under $μ$-strongly convex cases and $\mathcal{O}(\frac{1}{\sqrt{T}})$ under non-convex cases, \textit{same as FedAVG}. Extensive experiments demonstrate that $γ$-FedHT improves accuracy by up to $7.42\%$ over Top-$k$ under equal communication traffic on various non-IID image datasets.

cs.LG↗

arXiv2025

Inverse ac Josephson effect in Josephson diode

We study the Josephson junction where nonreciprocal critical current was induced by the interplay of the $4π$-periodic and $2π$-periodic current-phase relation of the junction. We take the model of a topological junction which serves as a Josephson diode with nonreciprocal critical currents. For this Josephson diode, we demonstrate an inverse ac Josephson effect where an effective dc voltage is induced by a pure ac driving current. We show that this inverse ac Josephson effect originates from the voltage rectification by the nonreciprocal critical current of the system. We explore the dependence of the induced dc voltage on the amplitude and frequency of the ac driving current and reveal the optimized condition for the inverse ac Josephson effect.

cond-mat.supr-con↗

arXiv2025

SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model

Remote sensing has become critical for understanding environmental dynamics, urban planning, and disaster management. However, traditional remote sensing workflows often rely on explicit segmentation or detection methods, which struggle to handle complex, implicit queries that require reasoning over spatial context, domain knowledge, and implicit user intent. Motivated by this, we introduce a new task, \ie, geospatial pixel reasoning, which allows implicit querying and reasoning and generates the mask of the target region. To advance this task, we construct and release the first large-scale benchmark dataset called EarthReason, which comprises 5,434 manually annotated image masks with over 30,000 implicit question-answer pairs. Moreover, we propose SegEarth-R1, a simple yet effective language-guided segmentation baseline that integrates a hierarchical visual encoder, a large language model (LLM) for instruction parsing, and a tailored mask generator for spatial correlation. The design of SegEarth-R1 incorporates domain-specific adaptations, including aggressive visual token compression to handle ultra-high-resolution remote sensing images, a description projection module to fuse language and multi-scale features, and a streamlined mask prediction pipeline that directly queries description embeddings. Extensive experiments demonstrate that SegEarth-R1 achieves state-of-the-art performance on both reasoning and referring segmentation tasks, significantly outperforming traditional and LLM-based segmentation methods. Our data and code will be released at https://github.com/earth-insights/SegEarth-R1.

cs.CV↗

arXiv2025

DoorBot: Closed-Loop Task Planning and Manipulation for Door Opening in the Wild with Haptic Feedback

Robots operating in unstructured environments face significant challenges when interacting with everyday objects like doors. They particularly struggle to generalize across diverse door types and conditions. Existing vision-based and open-loop planning methods often lack the robustness to handle varying door designs, mechanisms, and push/pull configurations. In this work, we propose a haptic-aware closed-loop hierarchical control framework that enables robots to explore and open different unseen doors in the wild. Our approach leverages real-time haptic feedback, allowing the robot to adjust its strategy dynamically based on force feedback during manipulation. We test our system on 20 unseen doors across different buildings, featuring diverse appearances and mechanical types. Our framework achieves a 90% success rate, demonstrating its ability to generalize and robustly handle varied door-opening tasks. This scalable solution offers potential applications in broader open-world articulated object manipulation tasks.

cs.RO↗

arXiv2025

Open-CD: A Comprehensive Toolbox for Change Detection

We present Open-CD, a change detection toolbox that contains a rich set of change detection methods as well as related components and modules. The toolbox started from a series of open source general vision task tools, including OpenMMLab Toolkits, PyTorch Image Models, etc. It gradually evolves into a unified platform that covers many popular change detection methods and contemporary modules. It not only includes training and inference codes, but also provides some useful scripts for data analysis. We believe this toolbox is by far the most complete change detection toolbox. In this report, we introduce the various features, supported methods and applications of Open-CD. In addition, we also conduct a benchmarking study on different methods and components. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and develop their own new change detectors. Code and models are available at https://github.com/likyoo/open-cd. Pioneeringly, this report also includes brief descriptions of the algorithms supported in Open-CD, mainly contributed by their authors. We sincerely encourage researchers in this field to participate in this project and work together to create a more open community. This toolkit and report will be kept updated.

cs.CV↗