arXiv subjects

Jin Cao

Publications and source records attributed to Jin Cao.

At least 19 recordsLinked to original sources

arXiv2026

ASTRA - Agentic System for Ticket Resolution and Analysis

Technical operations teams resolve large volumes of incidents by synthesizing fragmented evidence from ticket text, historical cases, system logs, and technical documentation. Existing automation often relies on monolithic generation without explicit evidence modeling or provenance, making outputs difficult to verify when critical signals are sparse across sources. We propose ASTRA, an agentic system for ticket resolution in which a central orchestrator coordinates three specialist information-gathering agents and drives a judge-orchestrator refinement loop to produce evidence-backed troubleshooting reports. TicketSimilarityAgent retrieves relevant historical precedents through dense retrieval and LLM reranking; LogAgent distills hundreds of thousands of log lines into structured, quote-grounded findings using deterministic filtering and constrained LLM analysis; and DomainKnowledgeAgent retrieves relevant technical knowledge via the Model Context Protocol (MCP). Their outputs are transformed into a claim-evidence representation linking each claim to a verbatim source passage, assigning a support level, and preventing cross-attribution. A JudgeAgent scores the report on five criteria, while the OrchestratorAgent converts low scores into targeted follow-up queries for bounded iterative refinement. Evaluated on 987 real-world telecom fault tickets across seven product lines, ASTRA achieves a mean quality score of 4.13/5.0, with 59.9% of reports identifying the fault area at the component-family level or better. Relevance and Clarity scores are 4.88 and 4.94, respectively, while fabricated technical details remain below 3% of error cases. Stratification by fault type reveals that hardware faults remain substantially harder than software or configuration faults (Cohen's d=0.80), pointing to a fundamental limitation of text-based evidence channels for hardware fault diagnosis.

cs.MA↗

arXiv2026

TraceGrant: A Contract-Governed Security Framework for the Task-Effect Lifecycle of Networked LLM Agents

Networked large language model (LLM) agents retrieve information from email, cloud storage, calendars, transaction platforms, and Web services to complete multistep tasks that produce persistent external effects. The same content needed for legitimate execution may also contain indirect prompt injections that redirect tool use, alter sensitive arguments, or disrupt task completion. Existing defenses mainly constrain untrusted content or individual tool calls, leaving user intent, runtime evidence, realized effects, and task completion insufficiently connected. We present TraceGrant, a security framework that governs the task-effect lifecycle of networked LLM agents through an explicit Contract. Before execution, TraceGrant establishes a task-effect boundary from the trusted user request. During execution, admitted evidence can instantiate only authority already established by the Contract. After execution, task completion is verified against actual tool results. Across 949 AgentDojo and 400 Agent Security Bench attack cases under fixed benchmark settings, TraceGrant recorded no attack successes while retaining utility under attack rates of 77.32% and 83.00%, respectively. We further evaluate TraceGrant through white-box defense-aware attacks, Contract quality analysis, stage ablations, targeted stress tests, and runtime overhead measurements. The results show that TraceGrant provides a unified governance layer that connects trusted user intent, runtime evidence, concrete tool execution, and verified task completion.

cs.CR↗

arXiv2026

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow

We present ShadowDancer, a novel approach to any-action, frame-level control of interactive video world models. The obstacle is representational: existing interfaces either encode an action loosely, leaving how it unfolds for the model to improvise, or encode it exactly through structured signals that serve one family and are hard to acquire, so precise control across diverse dynamics remains impractical. Demonstration videos are the natural remedy, specifying any dynamics frame by frame; yet a video shows its dynamics only through one particular appearance, a single shadow of the underlying dynamics, so actions learned from demonstrations transfer poorly to new scenes. ShadowDancer addresses this with two key innovations: (1) shadow pairs, video pairs that replay the same dynamics under independently resampled appearance, constructed at scale by our Shadow Library, so that a dynamics family becomes controllable exactly when such pairs can be constructed for it; and (2) cross-shadow prediction, which learns actions by predicting one shadow from the other, so that whatever the pairing resamples is discarded by construction and whatever it preserves becomes the action, yielding a unified dynamics representation that drives a block-causal world model. Any demonstrated clip thus becomes a reusable action asset, replayed in new environments without action labels, motion estimators, or fine-tuning. Experiments demonstrate improved action transfer and long action rollout over strong latent-action and interactive world model baselines across diverse dynamics families, with an average blinded win rate of 86% in rollout comparisons. We show video results at https://ShadowDancer-1.github.io

cs.CV↗

arXiv2026

Hybrid-parity sliding multiferroics

In this work, we introduce a class of hybrid-parity sliding multiferroics in which the spontaneous ferroelectric polarization is coupled to certain nonrelativistic spin splitting components through interlayer sliding, allowing these components to be reversibly switched in an electrical way. Symmetry analysis identifies coplanar magnets as natural platforms for realizing this form of sliding multiferroicity. First-principles calculations establish bilayer VBr$_2$ as a representative example, demonstrating the coupled reversal of the out-of-plane ferroelectric polarization and the signs of both even- and odd-parity nonrelativistic spin splitting components via an interlayer-sliding pathway. The signs of these nonrelativistic spin splitting components are locked to the sliding-switchable ferroelectric polarization and encoded in the spin-current responses, providing a signature of the coupled ferroic switching. Our findings expand the scope of sliding multiferroics and the functionality of sliding ferroelectrics for low-energy, nonvolatile logic devices.

cond-mat.mtrl-sci↗

arXiv2026

IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products

Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern procurement, compatibility, and safety across supply chains. These specifications are scattered across multiple heterogeneous product images, including specification tables, nameplates, and technical drawings, yet whether Multimodal Large Language Models (MLLMs) can reliably recover them remains underexplored. To fill this gap, we introduce IndustryBench-MIPU, the first large-scale benchmark for multi-image industrial product understanding, built around structured attribute extraction -- recovering property-value pairs from product images. This task jointly probes text recognition on specification tables and nameplates, visual reasoning over technical drawings, domain knowledge to decode industrial terminology, and cross-image evidence integration to assemble scattered specifications. Concretely, the benchmark comprises 4,559 products across 27,652 images with 103,703 annotations spanning 18 industrial categories, constructed through multi-model consensus and three-tier quality assurance. Evaluating nine MLLMs under both single-image and product-level multi-image settings reveals a stark completeness gap: models achieve high precision (86--94%) but the best recovers only 49.9% of product-level attributes; moving from single-image to multi-image extraction costs 15--34 percentage points of recall. Multi-image completeness, not single-image accuracy, is the core bottleneck. Dataset and code are publicly available.

cs.CV↗

arXiv2026

Surface Originated Cross-Field Anomalous Transport in Magnetoelectric Multilayers

In material systems with slab geometry, the surface contribution to physical responses is commonly expected to diminish rapidly with increasing thickness, giving way to the bulk response. Here, we show that this conventional wisdom is violated in a class of gate-induced responses, including gate-induced orbital and spin magnetization as well as cross-field anomalous thermoelectric transport. We develop a general framework for these effects, which naturally decomposes the total response into surface- and bulk-contributions treated on equal footing. Remarkably, the volume-averaged surface contribution remains finite in the thick-slab limit and exhibits the same thickness scaling as the bulk term. Furthermore, the surface response originates from band geometric quantities distinct from those in the bulk, being constrained solely by surface symmetries. As a result, it can dominate the overall response when the bulk contribution is symmetry-forbidden. Taking MnBi$_2$Te$_4$ multilayers as an example, we predict a strong surface-dominated cross-field anomalous Nernst effect arising from surface Berry curvature, which is readily accessible to experimental detection. These findings reveal a previously overlooked significance of surface response and open a new direction in the study of surface quantum geometry.

cond-mat.mes-hall↗

arXiv2026

Nonlinear Magnetic Orbital Hall Effect Induced by Spin-Orbit Coupling

Electrical readout of 180$^\circ$ switching in strictly compensated collinear antiferromagnets remains a major challenge in antiferromagnetic spintronics. Electrical writing of perpendicularly magnetized ferromagnets by out-of-plane orbital torque remains an important challenge in orbitronics. In this work, we propose a second-order nonlinear magnetic orbital Hall effect in the source antiferromagnet as a simultaneous recipe for both difficulties. This orbitronics effect is induced by spin-orbit coupling and is odd in the N\'eel vector, thus is a unique effect that integrates both functionalities via electric control of the N\'eel vector in the source antiferromagnet. Our first-principles calculations in CuMnAs predict significant non-perturbative orbital effects from spin-orbit coupling, with a orbital Berry-curvature dipole mechanism. These findings unveil new possibilities opened by topological antiferromagnetic orbitronics.

cond-mat.mtrl-sci↗

arXiv2026

Eccentricity valley Hall effect

Valleytronics harnesses the valley degree of freedom -- energy-degenerate extrema in the electronic band structure -- for information storage and processing. Valley Hall effect (VHE) is a cornerstone of valleytronics, enabling electric generation of pure valley currents. While extensively studied in systems with valleys located at time-reversal-breaking points, here, we shift the paradigm to valleytronic platforms with time-reversal-invariant valleys (TRIVs), revealing a novel phenomenon: eccentricity VHE. Unlike conventional VHE, the valley Hall angle for eccentricity VHE is an intrinsic geometric property, governed solely by the eccentricity of the valley Fermi surface, rendering it highly robust against variations in temperature or carrier density. Eccentricity VHE emerges universally across all 25 layer groups supporting TRIVs. We demonstrate these distinctive features in monolayer GeS$_{2}$ via first-principles calculations, predicting a significant valley Hall angle of 0.74. This effect can be detected through nonlocal transport measurements exhibiting characteristic scaling behavior, or, in certain cases, through valley-layer coupling. Our findings reveal a critical overlooked facet of valley Hall physics, transcend the established VHE paradigm, and significantly broadens the scope of valleytronics.

cond-mat.mes-hall↗

arXiv2026

Hasse-Witt invariants of Calabi-Yau varieties

We define the Hasse-Witt invariant of Calabi-Yau varieties in two different ways. The first method is through Cartier operator and the second method is through the theory of Calabi-Yau modular forms developed by the third author. We conjecture that these two definitions are equivalent and provide many examples of Calabi-Yau varieties in support of this conjecture.

math.AG↗

arXiv2026

Nonperturbative Magnetic Orbital Hall Effect in Altermagnets

Recent studies on altermagnets have focused considerable attention on nonrelativistic effects that persist in the absence of spin-orbit coupling (SOC). As a result, the relative importance of various phenomena in altermagnets has commonly been judged by their dependence on SOC. Here, we challenge this common wisdom by uncovering the magnetic orbital Hall effect, which is nonperturbative in SOC strength. We establish the symmetry properties of this effect, demonstrating that it is strictly forbidden in conventional collinear antiferromagnets yet universally allowed in all ten spin-Laue classes of collinear altermagnets. Counterintuitively, although SOC-induced, it reaches giant magnitudes in altermagnets-comparable to or even exceeding the nonrelativistic spin Hall effect. Moreover, altermagnetic symmetry enables unconventional collinear-polarized orbital currents, allowing field-free manipulation of perpendicular magnetization. Our first-principles calculations predict strong room-temperature responses in the experimentally established altermagnets CrSb and FeSb2. These findings reveal the previously overlooked potential of altermagnetic orbitronics and broaden the horizons for altermagnets in high-performance magnetic memory applications.

cond-mat.mtrl-sci↗

arXiv2025

Wearable-informed generative digital avatars predict task-conditioned post-stroke locomotion

Dynamic prediction of locomotor capacity after stroke could enable more individualized rehabilitation, yet current assessments largely provide static impairment scores and do not indicate whether patients can perform specific tasks such as slope walking or stair climbing. Here, we present a wearable-informed data-physics hybrid generative framework that reconstructs a stroke survivor's locomotor control from wearable inertial sensing and predicts task-conditioned post-stroke locomotion in new environments. From a single 20 m level-ground walking trial recorded by five IMUs, the framework personalizes a physics-based digital avatar using a healthy-motion prior and hybrid imitation learning, generating dynamically feasible, patient-specific movements for inclined walking and stair negotiation. Across 11 stroke inpatients, predicted postures reached 82.2% similarity for slopes and 69.9% for stairs, substantially exceeding a physics-only baseline. In a multicentre pilot randomized study (n = 21; 28 days), access to scenario-specific locomotion predictions to support task selection and difficulty titration was associated with larger gains in Fugl-Meyer lower-extremity scores than standard care (mean change 6.0 vs 3.7 points; $p < 0.05$). These results suggest that wearable-informed generative digital avatars may augment individualized gait rehabilitation planning and provide a pathway toward dynamically personalized post-stroke motor recovery strategies.

cs.CE↗

arXiv2025

WonderZoom: Multi-Scale 3D World Generation

We present WonderZoom, a novel approach to generating 3D scenes with contents across multiple spatial scales from a single image. Existing 3D world generation models remain limited to single-scale synthesis and cannot produce coherent scene contents at varying granularities. The fundamental challenge is the lack of a scale-aware 3D representation capable of generating and rendering content with largely different spatial sizes. WonderZoom addresses this through two key innovations: (1) scale-adaptive Gaussian surfels for generating and real-time rendering of multi-scale 3D scenes, and (2) a progressive detail synthesizer that iteratively generates finer-scale 3D contents. Our approach enables users to "zoom into" a 3D region and auto-regressively synthesize previously non-existent fine details from landscapes to microscopic features. Experiments demonstrate that WonderZoom significantly outperforms state-of-the-art video and 3D models in both quality and alignment, enabling multi-scale 3D world creation from a single image. We show video results and an interactive viewer of generated multi-scale 3D worlds in https://wonderzoom.github.io/

cs.CV↗

arXiv2025

Out-of-Plane Nonlinear Orbital Hall Torque

Despite recent advances in orbitronics, generating out-of-plane orbital torques essential for field-free deterministic switching of perpendicular magnetization remains a key challenge. Here, we propose a strategy to produce such unconventional torques across broad classes of materials, by leveraging the nonlinear orbital Hall effect. We demonstrate that this nonlinear orbital response is dramatically amplified by topological band degeneracies, where it overwhelmingly dominates the spin response even in systems with strong spin-orbit coupling. These features are confirmed via a quantitative investigation of representative topological metals RhSi, YPtBi, and PbTaSe$_2$, by combining our theory with first-principles calculations. The resulting orbital torques substantially surpass those from linear mechanisms reported thus far. These findings propel the research of orbital transport into the nonlinear regime, broaden the scope of orbital source materials, and establish a new pathway towards high-performance orbitronic devices.

cond-mat.mtrl-sci↗

arXiv2025

Broad Feshbach resonance with a large background scattering length in a fermionic atom-molecule mixture

We report the observation of a broad magnetic Feshbach resonance with a large background scattering length in an ultracold fermionic mixture of $^{23}$Na$^{40}$K molecules and $^{40}$K atoms, with both species prepared in their lowest hyperfine states. The Feshbach resonance is characterized by measuring resonantly enhanced loss rates and elastic scattering cross sections via cross-species thermalization. The large background scattering length can drive the atom-molecule mixture into the hydrodynamic regime when the magnetic field is far from the resonance. We observe that the center-of-mass motions of the atoms and molecules are phase-locked and oscillate with a common frequency due to hydrodynamic drag effects. This broad atom-molecule Feshbach resonance with its large background scattering length opens up a new avenue towards studying strongly interacting fermionic gases with mass imbalance.

cond-mat.quant-gas↗

arXiv2025

Lorentz Skew Scattering Nonreciprocal Magneto-Transport

In materials with broken inversion symmetry, nonreciprocal magneto-transport (NRMT) manifests as a bilinear dependence of charge conductivity on applied electric (E) and magnetic (B) fields. This phenomenon is deeply rooted in symmetry and electronic quantum geometry, holding promise for novel rectification and detector technologies. Existing experimental studies generally attribute NRMT to Zeeman-driven mechanisms and exhibit quadratic scaling with conductivity. Here, we report a previously unknown NRMT microscopic mechanism - Lorentz skew scattering (LSK) - revealed through the discovery of an unprecedented quartic scaling law of NRMT as well as quantitative agreement between theory and experiment in BiTeBr. LSK emerges from the interplay of Lorentz force and skew scattering, bridging classical field effect to quantum scattering effect on the Fermi surface. We demonstrate that the LSK dominates NRMT in BiTeBr, and elucidate that this dominance over other possible contributions stems from high mobility and strong Rashba splitting. The finding of LSK mechanism is of unique importance because it unveils the leading NRMT effect in high-mobility systems and suggests a universal principle towards strong NRMT by enhancing electronic relaxation time in topological materials, rendering a new designing idea for low-dissipation rectifiers and high-performance quantum electronics.

cond-mat.mes-hall↗

arXiv2025

FOLK: Fast Open-Vocabulary 3D Instance Segmentation via Label-guided Knowledge Distillation

Open-vocabulary 3D instance segmentation seeks to segment and classify instances beyond the annotated label space. Existing methods typically map 3D instances to 2D RGB-D images, and then employ vision-language models (VLMs) for classification. However, such a mapping strategy usually introduces noise from 2D occlusions and incurs substantial computational and memory costs during inference, slowing down the inference speed. To address the above problems, we propose a Fast Open-vocabulary 3D instance segmentation method via Label-guided Knowledge distillation (FOLK). Our core idea is to design a teacher model that extracts high-quality instance embeddings and distills its open-vocabulary knowledge into a 3D student model. In this way, during inference, the distilled 3D model can directly classify instances from the 3D point cloud, avoiding noise caused by occlusions and significantly accelerating the inference process. Specifically, we first design a teacher model to generate a 2D CLIP embedding for each 3D instance, incorporating both visibility and viewpoint diversity, which serves as the learning target for distillation. We then develop a 3D student model that directly produces a 3D embedding for each 3D instance. During training, we propose a label-guided distillation algorithm to distill open-vocabulary knowledge from label-consistent 2D embeddings into the student model. FOLK conducted experiments on the ScanNet200 and Replica datasets, achieving state-of-the-art performance on the ScanNet200 dataset with an AP50 score of 35.7, while running approximately 6.0x to 152.2x faster than previous methods. All codes will be released after the paper is accepted.

cs.CV↗

arXiv2025

UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction

This paper tackles the challenge of robust reconstruction, i.e., the task of reconstructing a 3D scene from a set of inconsistent multi-view images. Some recent works have attempted to simultaneously remove image inconsistencies and perform reconstruction by integrating image degradation modeling into neural 3D scene representations. However, these methods rely heavily on dense observations for robustly optimizing model parameters. To address this issue, we propose to decouple robust reconstruction into two subtasks: restoration and reconstruction, which naturally simplifies the optimization process. To this end, we introduce UniVerse, a unified framework for robust reconstruction based on a video diffusion model. Specifically, UniVerse first converts inconsistent images into initial videos, then uses a specially designed video diffusion model to restore them into consistent images, and finally reconstructs the 3D scenes from these restored images. Compared with case-by-case per-view degradation modeling, the diffusion model learns a general scene prior from large-scale data, making it applicable to diverse image inconsistencies. Extensive experiments on both synthetic and real-world datasets demonstrate the strong generalization capability and superior performance of our method in robust reconstruction. Moreover, UniVerse can control the style of the reconstructed 3D scene. Project page: https://jin-cao-tma.github.io/UniVerse.github.io/

cs.CV↗

arXiv2025

DPFNAS: Differential Privacy-Enhanced Federated Neural Architecture Search for 6G Edge Intelligence

The Sixth-Generation (6G) network envisions pervasive artificial intelligence (AI) as a core goal, enabled by edge intelligence through on-device data utilization. To realize this vision, federated learning (FL) has emerged as a key paradigm for collaborative training across edge devices. However, the sensitivity and heterogeneity of edge data pose key challenges to FL: parameter sharing risks data reconstruction, and a unified global model struggles to adapt to diverse local distributions. In this paper, we propose a novel federated learning framework that integrates personalized differential privacy (DP) and adaptive model design. To protect training data, we leverage sample-level representations for knowledge sharing and apply a personalized DP strategy to resist reconstruction attacks. To ensure distribution-aware adaptation under privacy constraints, we develop a privacy-aware neural architecture search (NAS) algorithm that generates locally customized architectures and hyperparameters. To the best of our knowledge, this is the first personalized DP solution tailored for representation-based FL with theoretical convergence guarantees. Our scheme achieves strong privacy guarantees for training data while significantly outperforming state-of-the-art methods in model performance. Experiments on benchmark datasets such as CIFAR-10 and CIFAR-100 demonstrate that our scheme improves accuracy by 6.82\% over the federated NAS method PerFedRLNAS, while reducing model size to 1/10 and communication cost to 1/20.

cs.LG↗