arXiv subjects

Ying Zhou

Publications and source records attributed to Ying Zhou.

At least 55 records · Page 3Linked to original sources

arXiv2026

DiffuGR: Generative Document Retrieval with Diffusion Language Models

Generative retrieval (GR) reframes document retrieval as an end-to-end task of generating sequential document identifiers (DocIDs). Existing GR methods predominantly rely on left-to-right auto-regressive decoding, which suffers from two fundamental limitations: (i) a \emph{mismatch between DocID generation and natural language generation}, whereby an incorrect DocID token generated at an early step can lead to entirely erroneous retrieval; and (ii) an \emph{inability to dynamically balance the trade-off between retrieval efficiency and accuracy}, which is crucial for practical applications. To tackle these challenges, we propose generative document retrieval with diffusion language models, termed \emph{DiffuGR}. DiffuGR formulates DocID generation as a discrete diffusion process. During training, DocIDs are corrupted through a stochastic masking process, and a diffusion language model is trained to recover them under a retrieval-aware objective. For inference, DiffuGR generates DocID tokens in parallel and refines them through a controllable number of denoising steps. Unlike auto-regressive decoding, DiffuGR introduce \emph{a novel mechanism to first generate plenty of confident DocID tokens and then refine the generation through diffusion-based denoising}. Moreover, DiffuGR also offers \emph{explicit runtime control over the quality-latency tradeoff}. Extensive experiments on widely-applied retrieval benchmarks show that DiffuGR outperforms strong auto-regressive generative retrievers. Additionally, we verify that DiffuGR achieves flexible control over the quality-latency trade-off via variable denoising budgets.

cs.IR↗

arXiv2026

Integrated Sensing, Communication and Control enabled Agile UAV Swarm

Uncrewed aerial vehicle (UAV) swarms are pivotal in the applications such as disaster relief, aerial base station (BS) and logistics transportation. These scenarios require the capabilities in accurate sensing, efficient communication and flexible control for real-time and reliable task execution. However, sensing, communication and control are studied independently in traditional research, which limits the overall performance of UAV swarms. To overcome this disadvantage, we propose a deeply coupled scheme of integrated sensing, communication and control (ISCC) for UAV swarms, which is a systemic paradigm that transcends traditional isolated designs of sensing, communication and control by establishing a tightly-coupled closed-loop through the co-optimization of sensing, communication and control. In this article, we firstly analyze the requirements of scenarios and key performance metrics. Subsequently, the enabling technologies are proposed, including communication-and-control-enhanced sensing, sensing-and-control-enhanced communication, and sensing-and-communication-enhanced control. Simulation results validate the performance of the proposed ISCC framework, demonstrating its application potential in the future.

eess.SP↗

arXiv2026

Diagnostic Performance of Universal-Learning Ultrasound AI Across Multiple Organs and Tasks: the UUSIC25 Challenge

IMPORTANCE: Modern ultrasound systems are universal diagnostic tools capable of imaging the entire body. However, current AI solutions remain fragmented into single-task tools. This critical gap between hardware versatility and software specificity limits workflow integration and clinical utility. OBJECTIVE: To evaluate the diagnostic accuracy, versatility, and efficiency of single general-purpose deep learning models for multi-organ classification and segmentation. DESIGN: The Universal UltraSound Image Challenge 2025 (UUSIC25) involved developing algorithms on 11,644 images aggregated from 12 sources (9 public, 3 private). Evaluation used an independent, multi-center private test set of 2,479 images, including data from a center completely unseen during training to assess generalization. OUTCOMES: Diagnostic performance (Dice Similarity Coefficient [DSC]; Area Under the Receiver Operating Characteristic Curve [AUC]) and computational efficiency (inference time, GPU memory). RESULTS: Of 15 valid algorithms, the top model (SMART) achieved a macro-averaged DSC of 0.854 across 5 segmentation tasks and AUC of 0.766 for binary classification. Models demonstrated high capability in anatomical segmentation (e.g., fetal head DSC: 0.942) but variability in complex diagnostic tasks subject to domain shift. Specifically, in breast cancer molecular subtyping, the top model's performance dropped from an AUC of 0.571 (internal) to 0.508 (unseen external center), highlighting the challenge of generalization. CONCLUSIONS: General-purpose AI models can achieve high accuracy and efficiency across multiple tasks using a single architecture. However, significant performance degradation on unseen data suggests domain generalization is critical for future clinical deployment.

cs.CV↗

arXiv2026

Towards Compositional Generalization in LLMs for Smart Contract Security: A Case Study on Reentrancy Vulnerabilities

Large language models (LLMs) demonstrate remarkable capabilities in natural language understanding and generation. Despite being trained on large-scale, high-quality data, LLMs still fail to outperform traditional static analysis tools in specialized domains like smart contract vulnerability detection. To address this issue, this paper proposes a post-training algorithm based on atomic task decomposition and fusion. This algorithm aims to achieve combinatorial generalization under limited data by decomposing complex reasoning tasks. Specifically, we decompose the reentrancy vulnerability detection task into four linearly independent atomic tasks: identifying external calls, identifying state updates, identifying data dependencies between external calls and state updates, and determining their data flow order. These tasks form the core components of our approach. By training on synthetic datasets, we generate three compiler-verified datasets. We then employ the Slither tool to extract structural information from the control flow graph and data flow graph, which is used to fine-tune the LLM's adapter. Experimental results demonstrate that low-rank normalization fusion with the LoRA adapter improves the LLM's reentrancy vulnerability detection accuracy to 98.2%, surpassing state-of-the-art methods. On 31 real-world contracts, the algorithm achieves a 20% higher recall than traditional analysis tools.

cs.CR↗

arXiv2025

Ultrafast Optical Evidence of Coexisting Density Waves in Bilayer Nickelate La$_3$Ni$_2$O$_7$

Utilizing ultrafast optical pump-probe spectroscopy, we investigate the coexistence and competition of electronic orders in the bilayer nickelate La$_3$Ni$_2$O$_7$. Our results reveal two coexisting density waves that can be selectively manipulated with light. We directly identify a spin-density wave (SDW) with electronic nematicity emerging below $T_{\rm SDW}$ $\approx$ 140 K by measuring its spin dynamics, and discover a distinct, nonmagnetic charge order appearing below $T_{\rm DW}$ $\approx$ 115 K. The central finding is the demonstration of differential optical control: the charge order is fragile, completely suppressed by a pump fluence of approximately 40 $μ$J/cm$^2$, while the SDW is remarkably robust, persisting to 200 $μ$J/cm$^2$. This work establishes a clear hierarchy in the stability of competing electronic orders and provides a powerful method for disentangling their interplay in quantum materials.

cond-mat.str-el↗

arXiv2025

Magnetoelectric topology: the rope weaving in parameter space

Topology, as a mathematical concept, has been introduced into condensed matter physics since the discovery of quantum Hall effect, which characterizes new physical scenario beyond the Landau theory. The topologically protected physical quantities, such as the dissipationless quantum transport of edge/surface states as well as magnetic/dipole quasi-particles like skyrmions/bimerons, have attracted great research enthusiasms in the past decades. In recent years, another kind of topology in condensed matter was revealed in the magnetoelectric parameter space of multiferroics, which deepens our understanding of magnetoelectric physics. This topical review summarizes recent advances in this area, involving three type-II multiferroics. With magnetism-induced ferroelectricity, topological behaviors can be manifested during the magnetoelectric switching processes driven by magnetic/electric fields, such as Roman-surface/Riemann-surface magnetoelectricity and magnetic crankshaft. These exotic topological magnetoelectric behaviors may be helpful to pursuit energy-efficient and precise-control devices for spintronics and quantum computing.

cond-mat.mtrl-sci↗

arXiv2025

TiS-TSL: Image-Label Supervised Surgical Video Stereo Matching via Time-Switchable Teacher-Student Learning

Stereo matching in minimally invasive surgery (MIS) is essential for next-generation navigation and augmented reality. Yet, dense disparity supervision is nearly impossible due to anatomical constraints, typically limiting annotations to only a few image-level labels acquired before the endoscope enters deep body cavities. Teacher-Student Learning (TSL) offers a promising solution by leveraging a teacher trained on sparse labels to generate pseudo labels and associated confidence maps from abundant unlabeled surgical videos. However, existing TSL methods are confined to image-level supervision, providing only spatial confidence and lacking temporal consistency estimation. This absence of spatio-temporal reliability results in unstable disparity predictions and severe flickering artifacts across video frames. To overcome these challenges, we propose TiS-TSL, a novel time-switchable teacher-student learning framework for video stereo matching under minimal supervision. At its core is a unified model that operates in three distinct modes: Image-Prediction (IP), Forward Video-Prediction (FVP), and Backward Video-Prediction (BVP), enabling flexible temporal modeling within a single architecture. Enabled by this unified model, TiS-TSL adopts a two-stage learning strategy. The Image-to-Video (I2V) stage transfers sparse image-level knowledge to initialize temporal modeling. The subsequent Video-to-Video (V2V) stage refines temporal disparity predictions by comparing forward and backward predictions to calculate bidirectional spatio-temporal consistency. This consistency identifies unreliable regions across frames, filters noisy video-level pseudo labels, and enforces temporal coherence. Experimental results on two public datasets demonstrate that TiS-TSL exceeds other image-based state-of-the-arts by improving TEPE and EPE by at least 2.11% and 4.54%, respectively.

cs.CV↗

arXiv2025

RailS: Load Balancing for All-to-All Communication in Distributed Mixture-of-Experts Training

Training Mixture-of-Experts (MoE) models introduces sparse and highly imbalanced all-to-all communication that dominates iteration time. Conventional load-balancing methods fail to exploit the deterministic topology of Rail architectures, leaving multi-NIC bandwidth underutilized. We present RailS, a distributed load-balancing framework that minimizes all-to-all completion time in MoE training. RailS leverages the Rail topology's symmetry to prove that uniform sending ensures uniform receiving, transforming global coordination into local scheduling. Each node independently executes a Longest Processing Time First (LPT) spraying scheduler to proactively balance traffic using local information. RailS activates N parallel rails for fine-grained, topology-aware multipath transmission. Across synthetic and real-world MoE workloads, RailS improves bus bandwidth by 20%--78% and reduces completion time by 17%--78%. For Mixtral workloads, it shortens iteration time by 18%--40% and achieves near-optimal load balance, fully exploiting architectural parallelism in distributed training.

cs.DC↗

arXiv2025

Layout-Aware Parsing Meets Efficient LLMs: A Unified, Scalable Framework for Resume Information Extraction and Evaluation

Automated resume information extraction is critical for scaling talent acquisition, yet its real-world deployment faces three major challenges: the extreme heterogeneity of resume layouts and content, the high cost and latency of large language models (LLMs), and the lack of standardized datasets and evaluation tools. In this work, we present a layout-aware and efficiency-optimized framework for automated extraction and evaluation that addresses all three challenges. Our system combines a fine-tuned layout parser to normalize diverse document formats, an inference-efficient LLM extractor based on parallel prompting and instruction tuning, and a robust two-stage automated evaluation framework supported by new benchmark datasets. Extensive experiments show that our framework significantly outperforms strong baselines in both accuracy and efficiency. In particular, we demonstrate that a fine-tuned compact 0.6B LLM achieves top-tier accuracy while significantly reducing inference latency and computational cost. The system is fully deployed in Alibaba's intelligent HR platform, supporting real-time applications across its business units.

cs.CL↗

arXiv2025

Enhancing Talent Search Ranking with Role-Aware Expert Mixtures and LLM-based Fine-Grained Job Descriptions

Talent search is a cornerstone of modern recruitment systems, yet existing approaches often struggle to capture nuanced job-specific preferences, model recruiter behavior at a fine-grained level, and mitigate noise from subjective human judgments. We present a novel framework that enhances talent search effectiveness and delivers substantial business value through two key innovations: (i) leveraging LLMs to extract fine-grained recruitment signals from job descriptions and historical hiring data, and (ii) employing a role-aware multi-gate MoE network to capture behavioral differences across recruiter roles. To further reduce noise, we introduce a multi-task learning module that jointly optimizes click-through rate (CTR), conversion rate (CVR), and resume matching relevance. Experiments on real-world recruitment data and online A/B testing show relative AUC gains of 1.70% (CTR) and 5.97% (CVR), and a 17.29% lift in click-through conversion rate. These improvements reduce dependence on external sourcing channels, enabling an estimated annual cost saving of millions of CNY.

cs.IR↗

arXiv2025

Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models

In this work, we address the task of table image to LaTeX code generation, with the goal of automating the reconstruction of high-quality, publication-ready tables from visual inputs. A central challenge of this task lies in accurately handling complex tables -- those with large sizes, deeply nested structures, and semantically rich or irregular cell content -- where existing methods often fail. We begin with a comprehensive analysis, identifying key challenges and highlighting the limitations of current evaluation protocols. To overcome these issues, we propose a reinforced multimodal large language model (MLLM) framework, where a pre-trained MLLM is fine-tuned on a large-scale table-to-LaTeX dataset. To further improve generation quality, we introduce a dual-reward reinforcement learning strategy based on Group Relative Policy Optimization (GRPO). Unlike standard approaches that optimize purely over text outputs, our method incorporates both a structure-level reward on LaTeX code and a visual fidelity reward computed from rendered outputs, enabling direct optimization of the visual output quality. We adopt a hybrid evaluation protocol combining TEDS-Structure and CW-SSIM, and show that our method achieves state-of-the-art performance, particularly on structurally complex tables, demonstrating the effectiveness and robustness of our approach.

cs.AI↗

arXiv2025

SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval

In long structured document retrieval, existing methods typically fine-tune pre-trained language models (PLMs) using contrastive learning on datasets lacking explicit structural information. This practice suffers from two critical issues: 1) current methods fail to leverage structural features and element-level semantics effectively, and 2) the lack of datasets containing structural metadata. To bridge these gaps, we propose \our, a novel contrastive learning framework. It leverages structure-aware learning to preserve semantic hierarchies and masked element alignment for fine-grained semantic discrimination. Furthermore, we release \dataset, a long structured document retrieval dataset with rich structural annotations. Extensive experiments on both released and industrial datasets across various modern PLMs, along with online A/B testing, demonstrate consistent performance improvements, boosting NDCG@10 from 73.96\% to 77.84\% on BGE-M3. The resources are available at https://github.com/xinhaoH/SEAL.

cs.IR↗

arXiv2025

FreeVPS: Repurposing Training-Free SAM2 for Generalizable Video Polyp Segmentation

Existing video polyp segmentation (VPS) paradigms usually struggle to balance between spatiotemporal modeling and domain generalization, limiting their applicability in real clinical scenarios. To embrace this challenge, we recast the VPS task as a track-by-detect paradigm that leverages the spatial contexts captured by the image polyp segmentation (IPS) model while integrating the temporal modeling capabilities of segment anything model 2 (SAM2). However, during long-term polyp tracking in colonoscopy videos, SAM2 suffers from error accumulation, resulting in a snowball effect that compromises segmentation stability. We mitigate this issue by repurposing SAM2 as a video polyp segmenter with two training-free modules. In particular, the intra-association filtering module eliminates spatial inaccuracies originating from the detecting stage, reducing false positives. The inter-association refinement module adaptively updates the memory bank to prevent error propagation over time, enhancing temporal coherence. Both modules work synergistically to stabilize SAM2, achieving cutting-edge performance in both in-domain and out-of-domain scenarios. Furthermore, we demonstrate the robust tracking capabilities of FreeVPS in long-untrimmed colonoscopy videos, underscoring its potential reliable clinical analysis.

cs.CV↗

arXiv2025

Piezomagnetism-driven magnetoelectric coupling in altermagnetic multiferroic K3Cr2F7

Ferroelectric control of altermagnetism in momentum space has been studied widely, while the control of magnetism in real space of altermagnets are still rare. We present a design rule to identify multiferroicity in n=2 Ruddlesden-Popper halides. Our results show that a Jahn-Teller distortion can cooperate with oxygen octahedral rotations to break inversion symmetry, which we demonstrate in K3Cr2F7 and cation-ordered KAg2Cu2Cl7, and leads to a ferrielectric-to-ferroelectric phase transition in K3Cr2F7. Altermagnetic spin order in the ferrielectric phase of K3Cr2F7 transforms into a conventional antiferromagnetic order in the ferroelectric phase, at which strain/pressure engineered sizable changes of weak ferromagnetism can occur. Our study is not only conducive to realize strong magnetoelectric coupling in multiferroics, but also reveals more functionalities in altermagnetic materials.

cond-mat.mtrl-sci↗

arXiv2025

RoTO: Robust Topology Obfuscation Against Tomography Inference Attacks

Tomography inference attacks aim to reconstruct network topology by analyzing end-to-end probe delays. Existing defenses mitigate these attacks by manipulating probe delays to mislead inference, but rely on two strong assumptions: (i) probe packets can be perfectly detected and altered, and (ii) attackers use known, fixed inference algorithms. These assumptions often break in practice, leading to degraded defense performance under detection errors or adaptive adversaries. We present RoTO, a robust topology obfuscation scheme that eliminates both assumptions by modeling uncertainty in attacker-observed delays through a distributional formulation. RoTO casts the defense objective as a min-max optimization problem that maximizes expected topological distortion across this uncertainty set, without relying on perfect probe control or specific attacker models. To approximate attacker behavior, RoTO leverages graph neural networks for inference simulation and adversarial training. We also derive an upper bound on attacker success probability, and demonstrate that our approach enhances topology obfuscation performance through the optimization of this upper bound. Experimental results show that RoTO outperforms existing defense methods, achieving average improvements of 34% in structural similarity and 42.6% in link distance while maintaining strong robustness and concealment capabilities.

cs.NI↗

arXiv2025

REACH: Reinforcement Learning for Efficient Allocation in Community and Heterogeneous Networks

Community GPU platforms are emerging as a cost-effective and democratized alternative to centralized GPU clusters for AI workloads, aggregating idle consumer GPUs from globally distributed and heterogeneous environments. However, their extreme hardware/software diversity, volatile availability, and variable network conditions render traditional schedulers ineffective, leading to suboptimal task completion. In this work, we present REACH (Reinforcement Learning for Efficient Allocation in Community and Heterogeneous Networks), a Transformer-based reinforcement learning framework that redefines task scheduling as a sequence scoring problem to balance performance, reliability, cost, and network efficiency. By modeling both global GPU states and task requirements, REACH learns to adaptively co-locate computation with data, prioritize critical jobs, and mitigate the impact of unreliable resources. Extensive simulation results show that REACH improves task completion rates by up to 17%, more than doubles the success rate for high-priority tasks, and reduces bandwidth penalties by over 80% compared to state-of-the-art baselines. Stress tests further demonstrate its robustness to GPU churn and network congestion, while scalability experiments confirm its effectiveness in large-scale, high-contention scenarios.

cs.NI↗

arXiv2025

Out-of-plane ferroelectricity, magnetoelectric coupling and persistent spin texture in two-dimensional multiferroics

Two dimensional multiferroics with out of plane ferroelectricity hold significant promise for miniaturized magnetoelectric spin-orbit transistors, yet systems combining robust ferroelectricity and strong magnetoelectric coupling are exceedingly rare. Here, we demonstrate that epitaxial strain stabilizes out of plane ferroelectricity in exfoliated two dimensional Ruddlesden Popper derivatives. The hybrid improper ferroelectric Pc phase transitions to a competing P21 phase with purely in plane polarization upon switching, accompanied by a 90 degree rotation of weak ferromagnetism. Crucially, the Pc phase exhibits altermagnetism, while P21 displays full Brillouin zone band splitting, with persistent spin textures rotating 90 degree at the phase boundary. This work establishes a pathway to engineer two dimensional multiferroics that integrate vertical polarization, magnetoelectric coupling, and switchable spin textures, key features for next generation spintronic devices.

cond-mat.mtrl-sci↗

arXiv2025

Macroscopic entanglement of three magnon modes in three cavities via optical parametric amplifier

We propose a scheme to generate bipartite and tripartite entanglements of three magnon modes in a three-cavity system using a nonlinear optical parametric amplifier (OPA). The three magnon modes in three YIG spheres are respectively placed inside three cavities near the maximum magnetic fields of the cavities and coupled to cavity modes via linear magnetic dipole interaction. Additionally, linear coupling interaction exists between two cavities. Using experimentally feasible parameters, we demonstrate that OPA can prepare the three magnon modes in a steady-state entangled state, bipartite and tripartite entanglements increase with the nonlinear interaction strength of OPA. An alternative approach to enhance quantum entanglement involves multiplexed OPA inputs. By employing individual OPA for each cavity, we observe a significant improvement in entanglement generation. All the entanglements are robust against bath temperature.

quant-ph↗