arXiv subjects

Jian Liu

Publications and source records attributed to Jian Liu.

At least 199 records · Page 11Linked to original sources

arXiv2025

PointNorm-Net: Self-Supervised Normal Prediction of 3D Point Clouds via Multi-Modal Distribution Estimation

Although supervised deep normal estimators have recently shown impressive results on synthetic benchmarks, their performance deteriorates significantly in real-world scenarios due to the domain gap between synthetic and real data. Building high-quality real training data to boost those supervised methods is not trivial because point-wise annotation of normals for varying-scale real-world 3D scenes is a tedious and expensive task. This paper introduces PointNorm-Net, the first self-supervised deep learning framework to tackle this challenge. The key novelty of PointNorm-Net is a three-stage multi-modal normal distribution estimation paradigm that can be integrated into either deep or traditional optimization-based normal estimation frameworks. Extensive experiments show that our method achieves superior generalization and outperforms state-of-the-art conventional and deep learning approaches across three real-world datasets that exhibit distinct characteristics compared to the synthetic training data.

cs.CV↗

arXiv2025

Large asymmetric anomalous Nernst effect in the antiferromagnet SrIr$_{0.8}$Sn$_{0.2}$O$_3$

A large anomalous Nernst effect is essential for thermoelectric energy harvesting in the transverse geometry without external magnetic field. It is often connected with anomalous Hall effect, especially when electronic Berry curvature is believed to be the driving force. This approach implicitly assumes the same symmetry for the Nernst and Hall coefficients, which is however not necessarily true. Here we report a large anomalous Nernst effect in antiferromagnetic SrIr$_{0.8}$Sn$_{0.2}$O$_3$ that defies the antisymmetric constraint on the anomalous Hall effect imposed by the Onsager reciprocal relation. The observed spontaneous Nernst thermopower quickly reaches the sub-$μ$V/K level below the Néel transition around 250 K, which is comparable with many topological antiferromagnetic semimetals and far excels other magnetic oxides. Our analysis indicates that the coexistence of significant symmetric and antisymmetric contributions plays a key role, pointing to the importance of extracting both contributions and a new pathway to enhanced anomalous Nernst effect for transverse thermoelectrics

cond-mat.mtrl-sci↗

arXiv2025

TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions

Adversarial robustness is a critical challenge in deploying deep neural networks for real-world applications. While adversarial training is a widely recognized defense strategy, most existing studies focus on balanced datasets, overlooking the prevalence of long-tailed distributions in real-world data, which significantly complicates robustness. This paper provides a comprehensive analysis of adversarial training under long-tailed distributions and identifies limitations in the current state-of-the-art method, AT-BSL, in achieving robust performance under such conditions. To address these challenges, we propose a novel training framework, TAET, which integrates an initial stabilization phase followed by a stratified equalization adversarial training phase. Additionally, prior work on long-tailed robustness has largely ignored the crucial evaluation metric of balanced accuracy. To bridge this gap, we introduce the concept of balanced robustness, a comprehensive metric tailored for assessing robustness under long-tailed distributions. Extensive experiments demonstrate that our method surpasses existing advanced defenses, achieving significant improvements in both memory and computational efficiency. This work represents a substantial advancement in addressing robustness challenges in real-world applications. Our code is available at: https://github.com/BuhuiOK/TAET-Two-Stage-Adversarial-Equalization-Training-on-Long-Tailed-Distributions.

cs.LG↗

arXiv2025

Constraint Phase Space Formulations for Finite-State Quantum Systems: The Relation between Commutator Variables and Complex Stiefel Manifolds

We have recently developed the \textit{constraint} coordinate-momentum \textit{phase space} (CPS) formulation for finite-state quantum systems. It has been implemented for the electronic subsystem in nonadiabatic transition dynamics to develop practical trajectory-based approaches. In the generalized CPS formulation for the mapping Hamiltonian of the classical mapping model with commutator variables (CMMcv) method [\textit{J. Phys. Chem. A} \textbf{2021}, 125, 6845-6863], each {connected} component of the generalized CPS is the \textit{complex Stiefel manifold} labeled by the eigenvalue set of the mapping kernel. Such a phase space structure allows for exact trajectory-based dynamics for pure discrete (electronic) degrees of freedom (DOFs), where the equations of motion of each trajectory are isomorphic to the time-dependent Schrödinger equation. We employ covariant kernels {within the generalized CPS framework} to develop two approaches that naturally yield exact evaluation of time correlation functions (TCFs) for pure discrete (electronic) DOFs. In addition, we briefly discuss the phase space mapping formalisms where the contribution of each trajectory to the integral expression of the {TCF} of population dynamics is strictly positive semi-definite. The generalized CPS formulation also indicates that the equations of motion in phase space mapping model I of our previous work [\textit{J. Chem. Phys.} \textbf{2016}, 145, 204105; \textbf{2017}, 146, 024110; \textbf{2019}, 151, 024105] lead to a complex Stiefel manifold $\mathrm{U}(F)/\mathrm{U}(F-2)$. It is expected that the generalized CPS formulation has implications for simulations of both nonadiabatic transition dynamics and many-body quantum dynamics for spins/bosons/fermions.

quant-ph↗

arXiv2025

Strain-tunable anomalous Hall plateau in antiferromagnet CoNb$_3$S$_6$

Antiferromagnets exhibiting the anomalous Hall effect represent a fascinating convergence of magnetism, topology, and electronic structure. Identifying antiferromagnets with large and tunable anomalous Hall effects is crucial for the development of spintronic applications. Here, we report a strain-tunable anomalous Hall plateau in CoNb$_3$S$_6$, which is a prime candidate for altermagnetism. The plateau emerges as a flat extended intermediate step of the anomalous Hall hysteresis loop with a controllable step height with temperature and strain. The remarkable tunability of the plateau position is in contrast with typical magnetic plateau associated with a field-induced metastable magnetic structure, but indicates the existence of a hidden phase transition that significantly alters the magnetic anisotropy energy without changing the magnetic order. The symmetry analysis of the strain tuning suggests that the hidden phase preserves the rotational symmetry of the ab-plane. Our results show the plateau reflects the phase coexistence during the hidden transition, and anomalous Hall resistivity of the plateau is thus non-volatile, enabling a novel four-state switching of the anomalous Hall effect.

cond-mat.mtrl-sci↗

arXiv2025

Scalable Autoregressive Monocular Depth Estimation

This paper shows that the autoregressive model is an effective and scalable monocular depth estimator. Our idea is simple: We tackle the monocular depth estimation (MDE) task with an autoregressive prediction paradigm, based on two core designs. First, our depth autoregressive model (DAR) treats the depth map of different resolutions as a set of tokens, and conducts the low-to-high resolution autoregressive objective with a patch-wise casual mask. Second, our DAR recursively discretizes the entire depth range into more compact intervals, and attains the coarse-to-fine granularity autoregressive objective in an ordinal-regression manner. By coupling these two autoregressive objectives, our DAR establishes new state-of-the-art (SOTA) on KITTI and NYU Depth v2 by clear margins. Further, our scalable approach allows us to scale the model up to 2.0B and achieve the best RMSE of 1.799 on the KITTI dataset (5% improvement) compared to 1.896 by the current SOTA (Depth Anything). DAR further showcases zero-shot generalization ability on unseen datasets. These results suggest that DAR yields superior performance with an autoregressive prediction paradigm, providing a promising approach to equip modern autoregressive large models (e.g., GPT-4o) with depth estimation capabilities.

cs.CV↗

arXiv2025

Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs

In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost inefficiency and resource limitations prevalent in such systems. To address these issues, we present two differently sized MoE large language models (LLMs), namely Ling-Lite and Ling-Plus (referred to as "Bailing" in Chinese, spelled Bǎilíng in Pinyin). Ling-Lite contains 16.8 billion parameters with 2.75 billion activated parameters, while Ling-Plus boasts 290 billion parameters with 28.8 billion activated parameters. Both models exhibit comparable performance to leading industry benchmarks. This report offers actionable insights to improve the efficiency and accessibility of AI development in resource-constrained settings, promoting more scalable and sustainable technologies. Specifically, to reduce training costs for large-scale MoE models, we propose innovative methods for (1) optimization of model architecture and training processes, (2) refinement of training anomaly handling, and (3) enhancement of model evaluation efficiency. Additionally, leveraging high-quality data generated from knowledge graphs, our models demonstrate superior capabilities in tool use compared to other models. Ultimately, our experimental findings demonstrate that a 300B MoE LLM can be effectively trained on lower-performance devices while achieving comparable performance to models of a similar scale, including dense and MoE models. Compared to high-performance devices, utilizing a lower-specification hardware system during the pre-training phase demonstrates significant cost savings, reducing computing costs by approximately 20%. The models can be accessed at https://huggingface.co/inclusionAI.

cs.LG↗

arXiv2025

Huge Stress-induced Adiabatic Temperature Change in a High-Toughness All-d-metal Heusler Alloy

The elastocaloric effect (eCE), referring to the thermal effect triggered by a uniaxial stress, provides a promising and versatile routine for green and high efficient thermal management. However, current eCE materials generally suffer from relatively low eCE and poor mechanical properties, hindering their practical applications. Here, we report a exceptionally huge eCE with a directly measured adiabatic temperature change of up to 57.2 K in a dual-phase all-d-metal Heusler Mn50Ni37.5Ti12.5 polycrystalline alloy, revealing an extra contribution to the latent heat during the stress-induced martensitic transformation from B2 to L10, and breaking the record of adiabatic temperature change for elastocaloric alloys. Moreover, thanks to the combined strengthening effect of d-d hybridization and well-dispersed secondary cubic γ phase, the alloy can endure a uniaxial stress up to 1760 MPa. Such an abnormal huge eCE is attributed to the combination of the enhanced entropy change associated with a stress-induced B2 to L10 martensitic transformation under higher stress, in contrast with the thermally induced B2 to 5-layer modulated structure one, and the high transformation fraction due to the multi-point nucleation facilitated by the γ phase dispersed in the main phase. This work provides insight into making full use of the transformation heat to enhance the caloric effect for high-efficient thermal management systems.

cond-mat.mtrl-sci↗

arXiv2025

A Survey on Ordinal Regression: Applications, Advances and Prospects

Ordinal regression refers to classifying object instances into ordinal categories. Ordinal regression is crucial for applications in various areas like facial age estimation, image aesthetics assessment, and even cancer staging, due to its capability to utilize ordered information effectively. More importantly, it also enhances model interpretation by considering category order, aiding the understanding of data trends and causal relationships. Despite significant recent progress, challenges remain, and further investigation of ordinal regression techniques and applications is essential to guide future research. In this survey, we present a comprehensive examination of advances and applications of ordinal regression. By introducing a systematic taxonomy, we meticulously classify the pertinent techniques and applications into three well-defined categories based on different strategies and objectives: Continuous Space Discretization, Distribution Ordering Learning, and Ambiguous Instance Delving. This categorization enables a structured exploration of diverse insights in ordinal regression problems, providing a framework for a more comprehensive understanding and evaluation of this field and its related applications. To our best knowledge, this is the first systematic survey of ordinal regression, which lays a foundation for future research in this fundamental and generic domain.

cs.CV↗

arXiv2025

Full Scaling Automation for Sustainable Development of Green Data Centers

The rapid rise in cloud computing has resulted in an alarming increase in data centers' carbon emissions, which now accounts for >3% of global greenhouse gas emissions, necessitating immediate steps to combat their mounting strain on the global climate. An important focus of this effort is to improve resource utilization in order to save electricity usage. Our proposed Full Scaling Automation (FSA) mechanism is an effective method of dynamically adapting resources to accommodate changing workloads in large-scale cloud computing clusters, enabling the clusters in data centers to maintain their desired CPU utilization target and thus improve energy efficiency. FSA harnesses the power of deep representation learning to accurately predict the future workload of each service and automatically stabilize the corresponding target CPU usage level, unlike the previous autoscaling methods, such as Autopilot or FIRM, that need to adjust computing resources with statistical models and expert knowledge. Our approach achieves significant performance improvement compared to the existing work in real-world datasets. We also deployed FSA on large-scale cloud computing clusters in industrial data centers, and according to the certification of the China Environmental United Certification Center (CEC), a reduction of 947 tons of carbon dioxide, equivalent to a saving of 1538,000 kWh of electricity, was achieved during the Double 11 shopping festival of 2022, marking a critical step for our company's strategic goal towards carbon neutrality by 2030.

cs.DC↗

arXiv2025

FederBoost: Private Federated Learning for GBDT

Federated Learning (FL) has been an emerging trend in machine learning and artificial intelligence. It allows multiple participants to collaboratively train a better global model and offers a privacy-aware paradigm for model training since it does not require participants to release their original training data. However, existing FL solutions for vertically partitioned data or decision trees require heavy cryptographic operations. In this paper, we propose a framework named FederBoost for private federated learning of gradient boosting decision trees (GBDT). It supports running GBDT over both vertically and horizontally partitioned data. Vertical FederBoost does not require any cryptographic operation and horizontal FederBoost only requires lightweight secure aggregation. The key observation is that the whole training process of GBDT relies on the ordering of the data instead of the values. We fully implement FederBoost and evaluate its utility and efficiency through extensive experiments performed on three public datasets. Our experimental results show that both vertical and horizontal FederBoost achieve the same level of accuracy with centralized training where all data are collected in a central server, and they are 4-5 orders of magnitude faster than the state-of-the-art solutions for federated decision tree training; hence offering practical solutions for industrial applications.

cs.CR↗

arXiv2025

PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object Detection

Single-Domain Generalized Object Detection~(S-DGOD) aims to train on a single source domain for robust performance across a variety of unseen target domains by taking advantage of an object detector. Existing S-DGOD approaches often rely on data augmentation strategies, including a composition of visual transformations, to enhance the detector's generalization ability. However, the absence of real-world prior knowledge hinders data augmentation from contributing to the diversity of training data distributions. To address this issue, we propose PhysAug, a novel physical model-based non-ideal imaging condition data augmentation method, to enhance the adaptability of the S-DGOD tasks. Drawing upon the principles of atmospheric optics, we develop a universal perturbation model that serves as the foundation for our proposed PhysAug. Given that visual perturbations typically arise from the interaction of light with atmospheric particles, the image frequency spectrum is harnessed to simulate real-world variations during training. This approach fosters the detector to learn domain-invariant representations, thereby enhancing its ability to generalize across various settings. Without altering the network architecture or loss function, our approach significantly outperforms the state-of-the-art across various S-DGOD datasets. In particular, it achieves a substantial improvement of $7.3\%$ and $7.2\%$ over the baseline on DWD and Cityscape-C, highlighting its enhanced generalizability in real-world settings.

cs.CV↗

arXiv2025

Bridging the Data Gap in AI Reliability Research and Establishing DR-AIR, a Comprehensive Data Repository for AI Reliability

Artificial intelligence (AI) technology and systems have been advancing rapidly. However, ensuring the reliability of these systems is crucial for fostering public confidence in their use. This necessitates the modeling and analysis of reliability data specific to AI systems. A major challenge in AI reliability research, particularly for those in academia, is the lack of readily available AI reliability data. To address this gap, this paper focuses on conducting a comprehensive review of available AI reliability data and establishing DR-AIR: a data repository for AI reliability. Specifically, we introduce key measurements and data types for assessing AI reliability, along with the methodologies used to collect these data. We also provide a detailed description of the currently available datasets with illustrative examples. Furthermore, we outline the setup of the DR-AIR repository and demonstrate its practical applications. This repository provides easy access to datasets specifically curated for AI reliability research. We believe these efforts will significantly benefit the AI research community by facilitating access to valuable reliability data and promoting collaboration across various academic domains within AI. We conclude our paper with a call to action, encouraging the research community to contribute and share AI reliability data to further advance this critical field of study.

stat.AP↗

arXiv2025

Compressive Sensing Empirical Wavelet Transform for Frequency-Banded Power Measurement Considering Interharmonics

Power measurement algorithms based on Fourier transform are susceptible to errors caused by interharmonics, while wavelet transform algorithms are particularly sensitive to even harmonics due to band decomposition effects. The empirical wavelet transform (EWT) has been demonstrated to improve measurement accuracy by effectively partitioning transition bands. However, for detecting interharmonic components, the limitation of the observation time window restricts spectral resolution, thereby limiting measurement accuracy. To address this challenge, this paper proposes a Compressive Sensing Empirical Wavelet Transform (CSEWT). The approach aims to enhance frequency resolution by integrating compressive sensing with the EWT, allowing precise identification of components across different frequency bands. This enables accurate determination of the power associated with the fundamental frequency, harmonics, and interharmonics. Test results indicate that the proposed CSEWT method can significantly improve the precision of individual frequency component measurements, even under dynamic and noisy conditions.

eess.SP↗

arXiv2025

Twin-Space Representation of Classical Mapping Model in the Constraint Phase Space Representation: Numerically Exact Approach to Open Quantum Systems

The constraint coordinate-momentum \textit{phase space} (CPS) has recently been developed to study nonadiabatic dynamics in gas-phase and condensed-phase molecular systems. Although the CPS formulation is exact for describing the discrete (electronic/ vibrational/spin) state degrees of freedom (DOFs), when system-bath models in condense phase are studied, previous works often employ the discretization of environmental bath DOFs, which breaks the time irreversibility and may make it difficult to obtain numerically converged results in the long-time limit. In this paper, we develop an exact trajectory-based phase space approach by adopting the twin-space (TS) formulation of quantum statistical mechanics, in which the density operator of the reduced system is transformed to the wavefunction of an expanded system with twice the DOFs. The classical mapping model (CMM) is then used to map the Hamiltonian of the expanded system to its equivalent classical counterpart on CPS. To demonstrate the applicability of the TS-CMM approach, we compare simulated population dynamics and nonlinear spectra for a few benchmark condensed phase system-bath models with those obtained from the hierarchical equations of motion method, which shows that our approach yields accurate dynamics of open quantum systems.

physics.chem-ph↗

arXiv2025

Dendrite Suppression in Zn Batteries Through Hetero-Epitaxial Residual Stresses Shield

Dendrite formation is a long-standing problem for the commercial application of aqueous zinc (Zn)-ion batteries (AZIB). Here, we investigate the effect of hetero-epitaxial residual stresses due to layered coatings on dendrite suppression. We found that atomic and molecular layered coatings can substantially reduce dendritic growth in AZIB by providing shielding due to residual stresses, even at single and a few layers of coatings. Through a combined experimental and numerical approach, we demonstrate that the residual stresses developed due to the coating of the Zn anodes significantly reduced the chemical potential polarization around dendrite embryos, forcing the deposition of zinc in the regions adjacent to the protuberances. This, in turn, results in a slower rate of dendritic growth, and eventually, dendrite suppression. The fundamental understanding of the effect of residual stresses due to coatings demonstrated herein can be extended to various metal anode batteries such as Li or Na.

cond-mat.mtrl-sci↗

arXiv2025

Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance. Our code will be made public at https://github.com/CNJianLiu/Diff9D.

cs.CV↗

arXiv2025

SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models

With the growing popularity of LLMs among the general public users, privacy-preserving and adversarial robustness have become two pressing demands for LLM-based services, which have largely been pursued separately but rarely jointly. In this paper, to the best of our knowledge, we are among the first attempts towards robust and private LLM inference by tightly integrating two disconnected fields: private inference and prompt ensembling. The former protects users' privacy by encrypting inference data transmitted and processed by LLMs, while the latter enhances adversarial robustness by yielding an aggregated output from multiple prompted LLM responses. Although widely recognized as effective individually, private inference for prompt ensembling together entails new challenges that render the naive combination of existing techniques inefficient. To overcome the hurdles, we propose SecPE, which designs efficient fully homomorphic encryption (FHE) counterparts for the core algorithmic building blocks of prompt ensembling. We conduct extensive experiments on 8 tasks to evaluate the accuracy, robustness, and efficiency of SecPE. The results show that SecPE maintains high clean accuracy and offers better robustness at the expense of merely $2.5\%$ efficiency overhead compared to baseline private inference methods, indicating a satisfactory ``accuracy-robustness-efficiency'' tradeoff. For the efficiency of the encrypted Argmax operation that incurs major slowdown for prompt ensembling, SecPE is 35.4x faster than the state-of-the-art peers, which can be of independent interest beyond this work.

cs.CR↗