arXiv subjects

Yu Liu

Publications and source records attributed to Yu Liu.

At least 343 records · Page 19Linked to original sources

arXiv2025

WXSOD: A Benchmark for Robust Salient Object Detection in Adverse Weather Conditions

Salient object detection (SOD) in complex environments remains a challenging research topic. Most existing methods perform well in natural scenes with negligible noise, and tend to leverage multi-modal information (e.g., depth and infrared) to enhance accuracy. However, few studies are concerned with the damage of weather noise on SOD performance due to the lack of dataset with pixel-wise annotations. To bridge this gap, this paper introduces a novel Weather-eXtended Salient Object Detection (WXSOD) dataset. It consists of 14,945 RGB images with diverse weather noise, along with the corresponding ground truth annotations and weather labels. To verify algorithm generalization, WXSOD contains two test sets, i.e., a synthesized test set and a real test set. The former is generated by adding weather noise to clean images, while the latter contains real-world weather noise. Based on WXSOD, we propose an efficient baseline, termed Weather-aware Feature Aggregation Network (WFANet), which adopts a fully supervised two-branch architecture. Specifically, the weather prediction branch mines weather-related deep features, while the saliency detection branch fuses semantic features extracted from the backbone with weather features for SOD. Comprehensive comparisons against 17 SOD methods shows that our WFANet achieves superior performance on WXSOD. The code and benchmark results will be made publicly available at https://github.com/C-water/WXSOD

cs.CV↗

arXiv2025

CSMD: Curated Multimodal Dataset for Chinese Stock Analysis

The stock market is a complex and dynamic system, where it is non-trivial for researchers and practitioners to uncover underlying patterns and forecast stock movements. The existing studies for stock market analysis rely on leveraging various types of information to extract useful factors, which are highly conditional on the quality of the data used. However, the currently available resources are mainly based on the U.S. stock market in English, which is inapplicable to adapt to other countries. To address these issues, we propose CSMD, a multimodal dataset curated specifically for analyzing the Chinese stock market with meticulous processing for validated quality. In addition, we develop a lightweight and user-friendly framework LightQuant for researchers and practitioners with expertise in financial domains. Experimental results on top of our datasets and framework with various backbone models demonstrate their effectiveness compared with using existing datasets. The datasets and code are publicly available at the link: https://github.com/ECNU-CILAB/LightQuant.

cs.CE↗

arXiv2025

Occlusion-Aware Diffusion Model for Pedestrian Intention Prediction

Predicting pedestrian crossing intentions is crucial for the navigation of mobile robots and intelligent vehicles. Although recent deep learning-based models have shown significant success in forecasting intentions, few consider incomplete observation under occlusion scenarios. To tackle this challenge, we propose an Occlusion-Aware Diffusion Model (ODM) that reconstructs occluded motion patterns and leverages them to guide future intention prediction. During the denoising stage, we introduce an occlusion-aware diffusion transformer architecture to estimate noise features associated with occluded patterns, thereby enhancing the model's ability to capture contextual relationships in occluded semantic scenarios. Furthermore, an occlusion mask-guided reverse process is introduced to effectively utilize observation information, reducing the accumulation of prediction errors and enhancing the accuracy of reconstructed motion features. The performance of the proposed method under various occlusion scenarios is comprehensively evaluated and compared with existing methods on popular benchmarks, namely PIE and JAAD. Extensive experimental results demonstrate that the proposed method achieves more robust performance than existing methods in the literature.

cs.CV↗

arXiv2025

Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance

Recent advances in generative modeling enable neural networks to generate weights without relying on gradient-based optimization. However, current methods are limited by issues of over-coupling and long-horizon. The former tightly binds weight generation with task-specific objectives, thereby limiting the flexibility of the learned optimizer. The latter leads to inefficiency and low accuracy during inference, caused by the lack of local constraints. In this paper, we propose Lo-Hp, a decoupled two-stage weight generation framework that enhances flexibility through learning various optimization policies. It adopts a hybrid-policy sub-trajectory balance objective, which integrates on-policy and off-policy learning to capture local optimization policies. Theoretically, we demonstrate that learning solely local optimization policies can address the long-horizon issue while enhancing the generation of global optimal weights. In addition, we validate Lo-Hp's superior accuracy and inference efficiency in tasks that require frequent weight updates, such as transfer learning, few-shot learning, domain generalization, and large language model adaptation.

cs.LG↗

arXiv2025

Magnetic properties of $R$Rh$_6$Ge$_4$ ($R$ = Pr, Nd, Sm, Gd-Er) single crystals

Single crystals of $R$Rh$_6$Ge$_4$ ($R$ = Pr, Nd, Sm, Gd - Er) were synthesized using a Bi flux and their physical properties were characterized by magnetization, resistivity, and specific heat measurements. These compounds crystallize in the noncentrosymmetric LiCo$_6$P$_4$-type structure (space group $P\bar{6}m2$), where rare-earth atoms form a triangular lattice in the $ab$-plane and chains along the $c$-axis. PrRh$_6$Ge$_4$ and ErRh$_6$Ge$_4$ do not exhibit magnetic transitions above 0.4 K. NdRh$_6$Ge$_4$ and SmRh$_6$Ge$_4$ are ferromagnets, while GdRh$_6$Ge$_4$ and DyRh$_6$Ge$_4$ show antiferromagnetic transitions, \red{whereas HoRh$_6$Ge$_4$ is a ferrimagnet}. In addition, DyRh$_6$Ge$_4$ shows multiple transitions and magnetization plateaus when a magnetic field is applied along the $c$-axis. In SmRh$_6$Ge$_4$, like the Ce counterpart, the crystalline-electric field (CEF) effect leads to an easy plane anisotropy, while in other compounds it gives rise to a pronounced uniaxial anisotropy.

cond-mat.str-el↗

arXiv2025

Dexbotic: Open-Source Vision-Language-Action Toolbox

In this paper, we present Dexbotic, an open-source Vision-Language-Action (VLA) model toolbox based on PyTorch. It aims to provide a one-stop VLA research service for professionals in the field of embodied intelligence. It offers a codebase that supports multiple mainstream VLA policies simultaneously, allowing users to reproduce various VLA methods with just a single environment setup. The toolbox is experiment-centric, where the users can quickly develop new VLA experiments by simply modifying the Exp script. Moreover, we provide much stronger pretrained models to achieve great performance improvements for state-of-the-art VLA policies. Dexbotic will continuously update to include more of the latest pre-trained foundation models and cutting-edge VLA models in the industry.

cs.RO↗

arXiv2025

A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Prediction

Human activity intensity prediction is crucial to many location-based services. Despite tremendous progress in modeling dynamics of human activity, most existing methods overlook physical constraints of spatial interaction, leading to uninterpretable spatial correlations and over-smoothing phenomenon. To address these limitations, this work proposes a physics-informed deep learning framework, namely Gravity-informed Spatiotemporal Transformer (Gravityformer) by integrating the universal law of gravitation to refine transformer attention. Specifically, it (1) estimates two spatially explicit mass parameters based on spatiotemporal embedding feature, (2) models the spatial interaction in end-to-end neural network using proposed adaptive gravity model to learn the physical constraint, and (3) utilizes the learned spatial interaction to guide and mitigate the over-smoothing phenomenon in transformer attention. Moreover, a parallel spatiotemporal graph convolution transformer is proposed for achieving a balance between coupled spatial and temporal learning. Systematic experiments on six real-world large-scale activity datasets demonstrate the quantitative and qualitative superiority of our model over state-of-the-art benchmarks. Additionally, the learned gravity attention matrix can be not only disentangled and interpreted based on geographical laws, but also improved the generalization in zero-shot cross-region inference. This work provides a novel insight into integrating physical laws with deep learning for spatiotemporal prediction.

cs.LG↗

arXiv2025

Critical fluctuations and conserved dynamics in a strange ferromagnetic metal

The origin of the strange metallic behavior observed in a wide range of quantum materials is an open challenge to condensed matter physics. Historically, strange metals were uniquely associated with antiferromagnetic quantum critical points (QCPs), but a new generation of materials reveals their association with uniform order parameters, such as ferromagnetism, valley or nematic order, suggesting a deeper common denominator. At a QCP, order parameter fluctuations are characterized by the dynamical critical exponent $z$, which quantifies the space-time scaling asymmetry. Here, we report the observation of a divergence in the Grüneisen ratio at the QCP of the strange-metal ferromagnet CeRh$_6$Ge$_4$ with a dynamical critical exponent $z=3$, signaling that the underlying quantum singularity involves a conserved degree of freedom. Yet the magnetization of this easy-plane ferromagnet is not conserved. We argue that the $z=3$ strange criticality requires a description beyond the Landau paradigm, proposing a link with the gauge modes of the small-to-large Fermi surface transition and the associated gauge charge of the delocalizing heavy electrons.

cond-mat.str-el↗

arXiv2025

ABACUS: An Electronic Structure Analysis Package for the AI Era

ABACUS (Atomic-orbital Based Ab-initio Computation at USTC) is an open-source software for first-principles electronic structure calculations and molecular dynamics simulations. It mainly features density functional theory (DFT) and molecular dynamics functions and is compatible with both plane-wave basis sets and numerical atomic orbital basis sets. ABACUS serves as a platform that facilitates the integration of various electronic structure methods, such as Kohn-Sham DFT, stochastic DFT, orbital-free DFT, and real-time time-dependent DFT, etc. In addition, with the aid of high-performance computing, ABACUS is designed to perform efficiently and provide massive amounts of first-principles data for generating general-purpose machine learning potentials, such as DPA models. Furthermore, ABACUS serves as an electronic structure platform that interfaces with several AI-assisted algorithms and packages, such as DeePKS-kit, DeePMD, DP-GEN, DeepH, DeePTB, HamGNN, etc.

cond-mat.mtrl-sci↗

arXiv2025

Defining the urban "local" with low dimensional manifolds of human mobility networks

Urban science has largely relied on universal models, rendering the heterogeneous and locally specific nature of cities effectively invisible. Here we introduce a topological framework that defines and detects localities in human mobility networks. We empirically demonstrate that these human mobility network localities are rigorous geometric entities that map directly to geographic localities, revealing that human mobility networks lie on manifolds of dimension <=5. This representation provides a compact theoretical foundation for spatial embedding and enables efficient applications to facility location and propagation modeling. Our approach reconciles local heterogeneity with universal representation, offering a new pathway toward a more comprehensive urban science.

physics.soc-ph↗

arXiv2025

Xihe: Scalable Zero-Shot Time Series Learner Via Hierarchical Interleaved Block Attention

The rapid advancement of time series foundation models (TSFMs) has been propelled by migrating architectures from language models. While existing TSFMs demonstrate impressive performance, their direct adoption of cross-domain architectures constrains effective capture of multiscale temporal dependencies inherent to time series data. This limitation becomes particularly pronounced during zero-shot transfer across datasets with divergent underlying patterns and sampling strategies. To address these challenges, we propose Hierarchical Interleaved Block Attention (HIBA) which employs hierarchical inter- and intra-block sparse attention to effectively capture multi-scale dependencies. Intra-block attention facilitates local information exchange, and inter-block attention operates across blocks to capture global temporal pattern interaction and dynamic evolution. Leveraging the HIBA architecture, we introduce Xihe, a scalable TSFM family spanning from an ultra-efficient 9.5M parameter configuration to high-capacity 1.5B variant. Evaluated on the comprehensive GIFT-Eval benchmark, our most compact Xihe-tiny model (9.5M) surpasses the majority of contemporary TSFMs, demonstrating remarkable parameter efficiency. More impressively, Xihe-max (1.5B) establishes new state-of-the-art zero-shot performance, surpassing previous best results by a substantial margin. This consistent performance excellence across the entire parameter spectrum provides compelling evidence for the exceptional generalization capabilities and architectural superiority of HIBA.

cs.CV↗

arXiv2025

A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the complex nature of scientific data. This survey presents a comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate. We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge, emphasizing the multimodal, cross-scale, and domain-specific challenges that differentiate scientific corpora from general natural language processing datasets. We systematically review recent Sci-LLMs, from general-purpose foundations to specialized models across diverse scientific disciplines, alongside an extensive analysis of over 270 pre-/post-training datasets, showing why Sci-LLMs pose distinct demands -- heterogeneous, multi-scale, uncertainty-laden corpora that require representations preserving domain invariance and enabling cross-modal reasoning. On evaluation, we examine over 190 benchmark datasets and trace a shift from static exams toward process- and discovery-oriented assessments with advanced evaluation protocols. These data-centric analyses highlight persistent issues in scientific data development and discuss emerging solutions involving semi-automated annotation pipelines and expert validation. Finally, we outline a paradigm shift toward closed-loop systems where autonomous agents based on Sci-LLMs actively experiment, validate, and contribute to a living, evolving knowledge base. Collectively, this work provides a roadmap for building trustworthy, continually evolving artificial intelligence (AI) systems that function as a true partner in accelerating scientific discovery.

cs.CL↗

arXiv2025

Growth control of highly textured Bi2Te3 thin films by pulsed laser deposition

Two-dimensional materials have attracted growing interest due to their unique electronic properties and potential applications in spintronics. Interfacing strongly spin-orbit-coupled chalcogenides with functional oxides such as perovskites has a particularly high potential. In this work, highly textured Bi2Te3 thin films were deposited on (111) oriented SrTiO3 by pulsed laser deposition. We show that, by careful selection of the temperature and pressure of growth, the film's stoichiometry can be manipulated between direct stoichiometry transfer from the target and tellurium-deficient phases. Optimized pulsed laser deposition enables the growth of films with coalesced, faceted grains with grain sizes reaching up to 430 nm, while preserving crystalline quality comparable to that of molecular-beam-epitaxy-grown films. We show striking differences arising from tuning the laser's pulsing frequency and fluence, which lead to changes in surface roughness, the film's porosity, and grain boundaries, as well as grain shape. Analysis of cross-sectional transmission electron microscopy images reveals a sharp substrate-film interface without atomic intermixing and without the formation of amorphous intermediate layers. The results demonstrate that pulsed laser deposition is a viable method for producing high-quality Bi2Te3 thin films and opens the door to the integration of chalcogenides with perovskites with this growth technique.

cond-mat.mtrl-sci↗

arXiv2025

Anisotropic Strain Engineering in La0.7Sr0.3MnO3/LaFeO3 Superlattice: Structural Relaxation and Domain Formation

Anisotropic strain engineering in epitaxial oxide films provides new opportunities to control the antiferromagnetic and structural properties crucial for advancements of antiferromagnetic spintronics. Here we report on a (La0.7Sr0.3MnO3/LaFeO3)4 superlattice grown on (101)o DyScO3 substrate which imposes significant anisotropic in-plane strain. Reciprocal space mapping reveals selective strain relaxation along the tensile in-plane [010]o axis, while compression along the perpendicular in-plane [-101]o axis remains strained. Scanning precession electron diffraction and higher-order Laue zone analysis show that the relaxation is accommodated by structural domain formation in the LaFeO3 layers, initiating from the second bilayer and propagating out-of-plane. These domains minimise structural defects and correlate with the substrate step edges. X-ray magnetic dichroism measurements reveal bulk-like in-plane antiferromagnetic order with polydomain signature as previously reported. Our findings reveal the presence of structural domains coexisting with antiferromagnetic polydomain states, showing a strain-domain-magnetism relationship that provides insights for applications of strain engineering in spintronics applications.

cond-mat.mtrl-sci↗

arXiv2025

When Machines Meet Each Other: Network Effects and the Strategic Role of History in Multi-Agent AI

As artificial intelligence (AI) enters the agentic era, large language models (LLMs) are increasingly deployed as autonomous agents that interact with one another rather than operate in isolation. This shift raises a fundamental question: how do machine agents behave in interdependent environments where outcomes depend not only on their own choices but also on the coordinated expectations of peers? To address this question, we study LLM agents in a canonical network-effect game, where economic theory predicts convergence to a fulfilled expectation equilibrium (FEE). We design an experimental framework in which 50 heterogeneous GPT-5-based agents repeatedly interact under systematically varied network-effect strengths, price trajectories, and decision-history lengths. The results reveal that LLM agents systematically diverge from FEE: they underestimate participation at low prices, overestimate at high prices, and sustain persistent dispersion. Crucially, the way history is structured emerges as a design lever. Simple monotonic histories-where past outcomes follow a steady upward or downward trend-help stabilize coordination, whereas nonmonotonic histories amplify divergence and path dependence. Regression analyses at the individual level further show that price is the dominant driver of deviation, history moderates this effect, and network effects amplify contextual distortions. Together, these findings advance machine behavior research by providing the first systematic evidence on multi-agent AI systems under network effects and offer guidance for configuring such systems in practice.

econ.GN↗

arXiv2025

Addressing the ID-Matching Challenge in Long Video Captioning

Generating captions for long and complex videos is both critical and challenging, with significant implications for the growing fields of text-to-video generation and multi-modal understanding. One key challenge in long video captioning is accurately recognizing the same individuals who appear in different frames, which we refer to as the ID-Matching problem. Few prior works have focused on this important issue. Those that have, usually suffer from limited generalization and depend on point-wise matching, which limits their overall effectiveness. In this paper, unlike previous approaches, we build upon LVLMs to leverage their powerful priors. We aim to unlock the inherent ID-Matching capabilities within LVLMs themselves to enhance the ID-Matching performance of captions. Specifically, we first introduce a new benchmark for assessing the ID-Matching capabilities of video captions. Using this benchmark, we investigate LVLMs containing GPT-4o, revealing key insights that the performance of ID-Matching can be improved through two methods: 1) enhancing the usage of image information and 2) increasing the quantity of information of individual descriptions. Based on these insights, we propose a novel video captioning method called Recognizing Identities for Captioning Effectively (RICE). Extensive experiments including assessments of caption quality and ID-Matching performance, demonstrate the superiority of our approach. Notably, when implemented on GPT-4o, our RICE improves the precision of ID-Matching from 50% to 90% and improves the recall of ID-Matching from 15% to 80% compared to baseline. RICE makes it possible to continuously track different individuals in the captions of long videos.

cs.CV↗

arXiv2025

Centering Emotion Hotspots: Multimodal Local-Global Fusion and Cross-Modal Alignment for Emotion Recognition in Conversations

Emotion Recognition in Conversations (ERC) is hard because discriminative evidence is sparse, localized, and often asynchronous across modalities. We center ERC on emotion hotspots and present a unified model that detects per-utterance hotspots in text, audio, and video, fuses them with global features via Hotspot-Gated Fusion, and aligns modalities using a routed Mixture-of-Aligners; a cross-modal graph encodes conversational structure. This design focuses modeling on salient spans, mitigates misalignment, and preserves context. Experiments on standard ERC benchmarks show consistent gains over strong baselines, with ablations confirming the contributions of HGF and MoA. Our results point to a hotspot-centric view that can inform future multimodal learning, offering a new perspective on modality fusion in ERC.

cs.CL↗

arXiv2025

Unraveling longitudinal field mediated versatile Stokes polarimetry

Stokes polarimetry has been considered as an alluring platform that enables a plethora of applications ranging from single-molecule orientation to deep-space sensing. Existing polarimetry avenues, however, rely primarily on the transversely polarized field reconstruction, thus suffering from several challenges such as multiple time sequenced detections, complex demodulation algorithms, and intricate engineering procedures. To circumvent these challenges, here we first demonstrate a longitudinally polarized field mediated recipe for the realization of efficacious and refined Stokes polarimetry in situ. This is achieved by unraveling the spin-to-orbit momentum conversion under non-paraxial focusing conditions enabling the direct mapping of the polarization ellipse. Leveraging this mechanism, we reveal an analytical solution of polarization ellipse via the local sampling of longitudinal field, in which the robustness can be fairly reinforced by relevant global retrieval based on convolutional neural network. The resultant Stokes polarimetry is shown to simultaneously exhibit in-situ signal acquisition (direct discernment), unparalleled demodulation time (up tomicrosecond level), superior detection efficiency (no need of troublesome design), and ultra-high retrieved accuracy (less than 1%), which is fundamentally inaccessible with traditional polarimetry methods. Our work holds great promise for empowering an allin-one versatile vector polarimeter, which opens up a host of applications relevant to polarization control.

physics.optics↗