Searcharxiv⌕ Search

arXiv subjects

Wei Zhou

Publications and source records attributed to Wei Zhou.

At least 55 records · Page 3Linked to original sources
arXiv2026

Harness Robotic OS: A Unified Embodied-Agent Runtime for Closed-Loop Quadruped Inspection

Autonomous property inspection requires more than robust robot navigation: a deployable system must connect heterogeneous sensing, reusable autonomy capabilities, multimodal scene understanding, human interaction, and enterprise response within a traceable operational loop. Existing quadruped inspection systems commonly integrate these functions through task-specific interfaces, making contextual coordination, knowledge reuse, and controlled adaptation difficult. This paper presents \textit{Harness Robotic OS} (HROS), a unified embodied-agent runtime, and Argos, its realization for residential-community inspection. HROS organizes the system into robot runtime, embodied autonomy skills, cognitive agent runtime, and interaction and operations planes. A shared context connects physical state with agent reasoning; streaming ASR/TTS supports voice-based mission interaction; hierarchical working, episodic, and semantic memory preserves operational knowledge; and a safety-gated self-evolution loop converts execution traces into versioned candidate updates without permitting unconstrained online modification. The Argos prototype integrates a Vbot quadruped, Fast-LIO2 localization and mapping, Hobot-Stereo depth perception, PCT-Planner global planning, EGO-Planner local motion generation, and OpenClaw-orchestrated Qwen3-VL inspection analysis. Experiments in a residential property environment achieved 100\% waypoint reachability, outdoor localization error below 10~cm, local obstacle-response latency below 200~ms, representative hazard-detection rates of 85--95\%, and 99\% success in alarm delivery and structured-report generation. These results validate the deployed navigation and inspection closed loop, while HROS provides an extensible software foundation for memory-augmented, voice-aware, and continuously improvable embodied inspection agents.

cs.RO↗
arXiv2026

Observation of Magnetic-Anisotropy Crossover and High-Temperature Skyrmions in the Dirac Magnet Fe3Ge with a Distorted Kagome Lattice

Topological materials that simultaneously host robust high-temperature skyrmions and nontrivial electronic band structures have attracted tremendous interest owing to their distinctive advantages for both fundamental research and prospective technological applications. Here, we report the observation of robust skyrmions in the Dirac kagome magnet Fe3Ge, which exhibits a high Curie temperature of ~ 650 K. At room temperature, Fe3Ge shows a large intrinsic anomalous Hall conductivity of ~ 380 Ω-1cm-1, originating from its nontrivial electronic band topology. Systematic magnetization measurements reveal a spin reorientation transition at ~ 375 K, indicating a crossover from easy-plane to easy-axis magnetic anisotropy. Below the spin reorientation temperature, a large topological Hall effect is observed, arising from microscopic noncoplanar spin structures. Lorentz transmission electron microscopy shows that mesoscopic skyrmions are stabilized in the easy-axis magnetic anisotropy regime and persist over an exceptionally wide temperature window of 375-650 K, far exceeding that of most previously reported skyrmion-hosting materials. These results establish Fe3Ge as a promising platform for exploring diverse topological properties, with strong potential for advancing future high-temperature spintronic applications, ranging from next-generation information storage to logic computing devices.

cond-mat.mtrl-sci↗
arXiv2026

Inventory-Grounded Policy-Level Optimization for Training-Free AI Search

Early in deployment, an AI search system typically operates over a frequently updated product catalog, so the available items and their properties cannot be treated as stable knowledge that can be encoded in fixed prompts or strategies. Fine-tuning, reinforcement learning, and static prompt patches fit poorly: labels are scarce, rewards drift with inventory, model releases are costly, and prompt fixes quickly stale. We present Inventory-Grounded Policy-Level Optimization (IGPO), a training-free approach for fixed AI search pipelines. IGPO separates policy from environment facts: it learns Policy Guidelines for acting on runtime inventory evidence rather than memorizing available items. Online, IGPO grounds each query by probing the inventory and constructing an inventory portrait, then injects relevant Policy Guidelines into the retrieval and selection prompts. Offline, stochastic rollouts are grouped by query -- mixed outcome groups directly yield contrastive signal, and an inventory-guided exploration loop distinguishes missed retrieval routes from cases where no matching support is found under the observed inventory evidence. Since May 2026, IGPO has been deployed in a commercial smart-assistant AI search system. A 14-day online A/B test of the complete IGPO treatment shows a 3.17% relative CTR lift and a 38.9% reduction in audited bad cases.

cs.IR↗
arXiv2026

Personalized Task Dependency Graphs for Mitigating Signal Erosion in Multi-Task Recommendation

Optimizing multiple conversion objectives is a core challenge in industrial recommendation, often limited by signal erosion in rigid architectures. Existing Multi-Task Learning (MTL) methods typically enforce uniform dependency strengths across a static conversion funnel, overlooking how task correlations naturally vary based on item characteristics. Hierarchical message passing along these fixed chains leads to cumulative signal attenuation, which degrades performance on sparse, deep-funnel objectives. To address this, we propose the Personalized Task Dependency Graphs (PTDG). While respecting necessary physical causal constraints (e.g., Click -> Pay), PTDG dynamically "rewires" the intensity of dependency pathways for each item via low-rank approximation to ensure structural robustness. We implement a GCN-based propagation with hard causal masking to establish adaptive information shortcuts. Additionally, we introduce an Adaptive Progressive Masking (APM) strategy that decouples shared parameters according to task sparsity, helping to stabilize optimization. Experiments on KuaiRand1K and an industrial dataset show that PTDG significantly improves AUC on sparse conversion tasks by up to 1.45%, while maintaining comparable performance on dense objectives. Online A/B testing shows PTDG improves Conversion Rate (CVR) by 1.2% and effective Cost Per Mille (eCPM) by 1.9% relative to the baseline.

cs.IR↗
arXiv2026

Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation

LLM agents can combine individually non-revealing tool returns and disclose a sensitive conclusion, creating Tools Orchestration Privacy Risk (TOP-R). We formalize TOP-R through three conditions: conclusion sensitivity, single-source non-inferability, and compositional inferability. We introduce Library-Grounded Reverse-Inference Seed Expansion (LRSE), a four-library reverse-construction pipeline, and use it to build TOP-Bench, a 1,000-instance benchmark evaluated under a controlled two-stage tool-use protocol. Across six LLM agents, average task completion, leakage, and H-score are 98.0 percent, 88.6 percent, and 20.4. With native reasoning enabled, four models average 81.4 percent final-response leakage and 82.4 percent reasoning-trace leakage. With reasoning disabled, three prompt-only safeguards improve H-score by an average of about 3.4 points on TOP-Bench. We further propose TOP-Align, an SFT+DPO method for learning safer task-completion boundaries. On a separate post-training evaluation set, TOP-Align improves H-score by 16.2 points over the base model, versus a 5.0-point average gain from prompt-only mitigation on the same set. These results show that TOP-R requires defenses beyond prompting alone. Dataset and code are available at https://github.com/1Ponder/TOP-R.

cs.CR↗
arXiv2026

MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables

Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of the downstream objectives, the extracted representations may not be optimal for downstream tasks. To address this limitation, we introduce a discrete latent variable model on mel spectrograms that jointly optimizes the encoder and the speech language model. Joint optimization not only brings improvements over codec-based and other mel-spectrogram-based baselines on zero-shot Text-to-Speech (TTS) and Speech-to-Text (STT) tasks, but also effectively alleviates common issues in autoregressive mel spectrogram modeling, such as prolonged silence generation and word omissions.

eess.AS↗
arXiv2026

Learning Personalized Prompts for Healthcare Guidance

The rapid development of large language models (LLMs) has transformed many industries, including healthcare. In practice, hospitals and patients increasingly seek LLM-based systems capable of interpreting personal health records and providing healthcare guidance. However, existing approaches mainly rely on general medical knowledge and often fail to account for individual variability, limiting their ability to provide personalized guidance. To address this, we propose personalized prompt learning (PPL), a framework that learns individualized prompts to guide LLMs in generating personalized healthcare recommendations. PPL constructs initial personalized prompts by leveraging both self-informed patient information and peer-informed signals derived from clinically similar cases. These prompts are then refined using reinforcement learning (RL) to better align the generated responses with physician recommendations written for each patient. PPL operates with hard prompts, enabling seamless integration with proprietary LLMs without modifying the underlying models. We evaluate PPL on real-world obstetrics and gynecology data. The results show that our approach produces more personalized healthcare guidance and wins 97 out of 100 comparisons in expert evaluation, demonstrating its potential for broader healthcare applications. Our code is publicly available at https://github.com/CGCL-codes/PPL.

cs.CL↗
arXiv2026

Magnetotransport evolution and nonlinear Hall effect in altermagnetic MnTe

Hexagonal MnTe is a prototypical semiconducting altermagnet whose properties are heavily influenced by intrinsic disorder, yet how the resulting diverse transport regimes shape its magnetotransport behavior remains to be clarified alongside the role of relativistic spin-orbit coupling (SOC). Here, we present a systematic study of the anisotropic magnetoresistance (AMR), planar Hall effect (PHE), and nonlinear transport in MnTe bulk single crystals. Below the Néel temperature (TN ~ 304 K), the emergence of high-order harmonics in AMR and PHE within the high-temperature metallic regime reveals the interplay of magnetic order, crystalline symmetry, and SOC. At relatively lower temperatures, the disappearance of higher-order symmetries coincides with a transport crossover into the hopping conduction regime, suggesting that carrier localization diminishes the transport sensitivity to the Fermi-surface topology. In addition, we detect distinct second-order nonlinear Hall signals, providing evidence for a macroscopic inversion-asymmetric response in altermagnetic MnTe. Extending the investigations into the localized regime provides key insights into the subtle role of disorder and SOC in macroscopic charge transport. Our work thus underscores the necessity of exploring magnetotransport across diverse conducting regimes to comprehensively understand altermagnetic properties.

cond-mat.mtrl-sci↗
arXiv2026

Blind Stereoscopic Omnidirectional Image Quality Assessment Using Predictive Coding Hierarchy

Stereoscopic omnidirectional images (SOIs) have provided users with newly immersive quality of experience in virtual reality environments. However, developing efficient and accurate perceptual quality assessment metrics for SOIs remains challenging due to many factors such as freely changeable field of views and binocular vision. In this paper, based on the characteristics of the human visual system (HVS), we propose a Predictive Coding Hierarchy-inspired metric (PCH) for blind/no-reference stereoscopic omnidirectional image quality assessment. Motivated by the viewing process of SOIs, the proposed PCH includes a local cyclopean perception module, a global predictive perception module, and a visual quality regressor. First, observers browse different spherical sceneries from viewports, and aggregate the local visual information to infer the perceptual quality of SOIs. Therefore, we extract various viewports, followed by cyclopean conversion and saliency detection to approach the perception and attention of the human brain. After the local aggregation, viewers then infer the global scene in their minds. Based on the binocular mechanism, we fuse left and right views to perform predictive coding hierarchy modelling. Finally, the visual quality regressor is exploited to obtain the ultimate quality score related to both local and global perceptual cues. Extensive experiments demonstrate that the proposed PCH achieves competitive and consistently improved performance compared with state-of-the-art quality assessment methods.

cs.CV↗
arXiv2026

MetaRAG: Belief-Action Aligned Policy Optimization for Agentic RAG

Agentic retrieval-augmented generation (RAG) requires language models to decide when to continue searching and when to answer. Existing RL-based methods rely on external supervision and overlook the agent's internal belief about whether the current evidence is sufficient. To address this problem, we reformulate the search decision quality as belief-action alignment and propose MetaRAG, a belief-action aligned policy optimization framework for agentic RAG. MetaRAG uses Verify-first Action Generation to elicit an explicit verification process before each actual action, and Internal Belief Probing to estimate the policy model's own answerability belief from the same question-history context. Based on these, MetaRAG derives a consistency reward that is further gated by answer correctness, avoiding reinforcement of internally consistent but incorrect trajectories. The belief probe is used only during training and introduces no inference-time overhead. Experiments on seven public QA benchmarks show that MetaRAG consistently improves the accuracy-efficiency trade-off over strong RL-based agentic RAG baselines, with gains that transfer to deep research settings, different optimizers, and multiple model backbones.

cs.AI↗
arXiv2026

On-Policy Self-Distillation in Diffusion Models

Reinforcement learning can align diffusion models with human preferences and task-specific objectives, but endpoint rewards do not specify how an intermediate denoising prediction should change. We introduce DiffusionOPSD as an on-policy self-distillation framework that converts image-level reward guidance into explicit targets for clean-output predictions at sampled queries. At each outer iteration, a frozen behavior policy generates trajectories and supplies query states and anchors. Reward gradients construct bounded positive and negative targets around each anchor. The trainable policy fits these targets as detached supervision through finite fitting before an exponential moving average update refreshes the behavior policy. This setup lets us measure target construction and finite realization separately. Controlled same-query experiments show that larger target-construction gains do not necessarily translate into larger realized gains after a single fitting update. Across SD 3.5-M and the step-distilled Z-Image-Turbo, our approach achieves the best final held-out scores in 19 of 20 reward-matched settings across two backbones and ten evaluators. It outperforms the strongest competing method by up to 44.0% and reduces training GPU-hours relative to DiffusionNFT by 40% on SD 3.5-M and 63% on Z-Image-Turbo. These results support on-policy self-distillation as an efficient and analyzable approach to diffusion post-training by converting image-level reward guidance into explicit and continually refreshed intermediate supervision, thereby opening a path toward more efficient and diagnosable alignment.

cs.CV↗
arXiv2026

Reference-free Human-Object Interaction Editing

This paper presents InteractEdit, a novel framework for reference-free Human-Object Interaction (HOI) editing that tackles the challenging task of transforming an existing interaction in an image into a new, desired interaction while preserving the identities of the subject and object. Unlike prior image editing tasks such as attribute manipulation, object replacement or style transfer, HOI editing involves complex spatial, contextual, and relational dependencies inherent in HOI. Existing methods often overfit to the source image structure, limiting adaptability to the substantial structural modifications demanded by the new interactions. To address this, InteractEdit disassembles each scene into subject, object, and background components to disentangle intricate HOI relationship, and introduces a selective inversion strategy combined with Selective-Rank Adaptation (SeRA) to leverage pretrained interaction priors while learning visual identity from the source image. This enables a balanced trade-off between interaction editing and identity preservation. We also introduce IEBench, a new benchmark for HOI editing, and a new metric that jointly evaluates the trade-off between successful interaction editing and identity preservation. Extensive experiments show that InteractEdit outperforms 23 existing methods, providing a strong baseline for future HOI editing research. Code and the dataset: https://jiuntian.github.io/InteractEdit/.

cs.GR↗
arXiv2026

More Granular, Less Trust: Enforcing Intra-Process Isolation with Arm CCA in an Untrusted Management Environment

With the increasing adoption of confidential computing, security-sensitive applications are often deployed in confidential virtual machines (CVMs), which reduce reliance on third-party cloud providers. However, privilege attacks originating from the OS remain a significant threat in these environments. Existing finer-grained isolation schemes, such as SHELTER, provide process-level protection but are still vulnerable to intraprocess attacks and potential collusion between the OS and intra-process adversaries. Many current intra-process isolation techniques continue to depend on the OS to manage and enforce isolation domains, leading to a large Trusted Computing Base (TCB). This gap highlights the need for more granular, less trust-dependent confidential computing solutions. In this paper, we present CCAegis, a system that extends the Arm Confidential Compute Architecture (CCA) to enforce intra-process isolation of sensitive data and operations, safeguarding them from both intraprocess adversaries and the OS. We employ static analysis to track the flow of sensitive data and identify functions that handle such data. Permission-switching instructions are inserted at the function call and return points, adjusting permissions via the Granule Protection Table (GPT) to ensure that only designated functions can access the isolated data. Notably, CCAegis places trust solely in the Secure Monitor, which configures the GPTs and manages domain switching, thereby minimizing the TCB. We implemented CCAegis on both an official emulator and a real development board to assess its performance. Our experimental results show that CCAegis effectively isolates sensitive data and operations, with performance overheads ranging from 1.01x to 1.43x compared to the original version across real-world cryptographic workloads.

cs.CR↗
arXiv2026

An Information-theoretic Propagation Denoising and Fusion Framework for Fake News Detection

Incomplete propagation data significantly hinders robust fake news detection. Recent approaches leverage large language models to simulate missing user interactions via role-playing, thereby enriching propagation with synthetic signals. However, such propagation data is intrinsically unreliable, and directly fusing it can lead to biased representations and limited detection performance. In this paper, we alleviate the unreliability of synthetic propagation from the mutual information perspective and propose a novel information-theoretic propagation denoising and fusion (InfoPDF) framework to learn effective representations from both real and synthetic propagation. Specifically, we first generate attribute-specific synthetic propagation using large language models. Then we model each synthetic propagation graph as a probabilistic latent distribution to guide reliability-aware adaptive fusion with real propagation. During training, we design a mutual information-based objective to learn compressed and task-sufficient propagation representations. It jointly suppresses noisy signals across attribute-specific synthetic propagation, maintains consistency between real and synthetic propagation representations, and ensures task sufficiency for fake news detection and attribute prediction. Experiments on three real-world datasets show that InfoPDF consistently achieves superior performance across various fake news detection tasks. Further analysis demonstrates that InfoPDF can estimate attribute-level reliabilities and learn more discriminative propagation representations.

cs.CL↗
arXiv2026

Who Leads Now? Token-Level Modality Arbitration for Chart-to-Code Generation

Chart-to-code generation requires a model to read the fine-grained visual details of a chart and write executable code that reproduces it. Existing chart-to-code methods either train visual and coding abilities separately, or fine-tune on chart-to-code data with the two abilities entangled. Neither strategy accounts for the distinct nature of the two abilities or the interference that arises when they are optimized together. We propose MoCA (Mixture of Cross-modal Arbitration), which separates the two abilities rather than blending them. MoCA is built on Cross-modal Arbitration Block (CAB), which maintains a visual branch and a code branch as two distinct pathways, and a lightweight arbiter that arbitrates their relative contributions at every layer and generated token. We train MoCA in two stages: a supervised warm-up on self-distilled reasoning trajectories that decomposes visual understanding into explicit steps, followed by reinforcement learning with rewards on both the reasoning process and the final code. Analysis shows that the arbiter learns structured rather than arbitrary allocations, with expert contributions varying systematically across tokens, layers, and instances. Across three benchmarks, MoCA delivers competitive performance against general-domain and chart-specialized models. Ablation results show that the gains cannot be attributed to a larger model size alone, but instead arise from the joint contributions of complementary visual and code branch initialization and input-conditioned arbitration through CAB.

cs.AI↗
arXiv2026

Making two action heads agree: coordination mechanisms and a runtime collapse certificate for flow-matching policies

A dual-representation flow-matching policy decodes each predicted motion into joint and end-effector spaces, and the residual between the two kinematically equivalent decodings provides a physically interpretable runtime signal. On multimodal tasks, however, independently sampled branches may choose different valid modes, causing false alarms. We study how to coordinate the two branches and at what cost. Across two robot environments and a non-robotic testbed, the tested mechanisms fall into four classes. An auxiliary latent shared by both branches but absent from the flow-matching construction is erased at the population optimum, a provable dead end confirmed within a prespecified 2% equivalence band. Sharing source noise can coordinate or anti-coordinate: its effect changes sign with the representation map and tracks the alignment of decoder mode basins. Consistency regularization gives intermediate coordination but reduces the valid-pair rate, while training-supported discrete partitions achieve near-ceiling coordination robustly. We further derive a chance-corrected coordination bound based only on each branch's Gini-Simpson diversity, yielding an attainable region and a label-free certificate that separates coordination from collapse when zero mismatch is ambiguous. On LIBERO-Plus, benign multimodality adds 1.57 percentage points of false alarms to the residual, which remains the strongest evaluated failure signal; the preregistered token intervention does not meet its false-alarm criterion or produce a seed-robust detection change. Code, models, and per-run configurations are available at https://github.com/kimo423/dual-head-coordination.

cs.RO↗
arXiv2026

DanceOPD: On-Policy Generative Field Distillation

Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing. However, these capabilities are rarely naturally aligned and often conflict. For instance, editing tends to degrade T2I performance, while global and local editing interfere with each other. Consequently, effectively composing these capabilities has become a central challenge for image generation model training. To tackle this, we introduce DanceOPD, an on-policy generative field distillation framework for flow-matching models that routes each sample to one capability field, queries one low-noise student-induced state, and trains with a simple velocity MSE objective. With each capability source defined as a velocity field over the shared flow state space, the student learns from fields queried on its own rollout states to compose expert capabilities. This formulation also absorbs operator-defined fields such as classifier-free guidance. Comprehensive experiments on T2I, editing, realism-field absorption, and CFG absorption show that our approach improves multi-capability composition, strengthening target capabilities while preserving anchor generation quality. We believe this work establishes a practical route for generative field distillation in flow-matching models.

cs.CV↗
arXiv2026

WBMM: Windowed Batch Matrix Multiplication for Efficient Large Receptive Field Convolution

Large kernel depthwise convolutions achieve strong performance but suffer from significant degradation as kernel size grows due to irregular memory access from gather-based computation; while Large Kernel Acceleration (LKA) helps on small feature maps, it becomes counterproductive on large feature maps, even slower than non-accelerated implementations. We propose Windowed Batch Matrix Multiplication (WBMM), which partitions input into contiguous windows and indexes a compact relative position bias table to construct weight matrices, enabling regular memory access via batched matrix multiplication. This yields a unique property: WBMM's throughput improves with larger windows, opposite to depthwise convolutions that degrade with larger kernels. Operator-level benchmarks show WBMM with 14x14 windows outperforms 5x5 depthwise convolution baselines in speed while providing a 7.8x larger per-layer receptive field. Combined with inter-block cross-window communication and hierarchical window reparameterization, WBMM achieves comparable or higher accuracy on ImageNet-1K, COCO, and ADE20K with 1.31-1.88x training speedup, and demonstrates consistent advantages across GPU, CPU, and edge devices without requiring specialized acceleration kernels. Our code is available at https://github.com/wansong-s/WBMM.

cs.CV↗