Search arXiv⌕ Search

arXiv subjects

Tao Yu

Publications and source records attributed to Tao Yu.

At least 37 records · Page 2Linked to original sources
arXiv2026

Conditional-Coverage Contributor Selection for Regional Digital Twins Under Mobility

Regional digital twins (DTs) under mobility must coordinate contributor admission over congested broadcast networks without fixed infrastructure. Per-sender redundancy mitigation cannot make this set-level decision because only the host has a region-wide coverage map. Treating regional state as a public good, this letter develops a host-coordinated protocol admitting contributors whose timely, non-redundant coverage gain exceeds a congestion price within a cycle deadline. A 13-byte beacon digest enables pre-transmission scoring. Standards-based simulation shows the protocol reduces the timely actionable coverage deficit from 5.6\% to 1.4\% at load comparable to ETSI redundancy mitigation and by 26\% versus random admission at matched tight-budget load.

cs.IT↗
arXiv2026

Geometry-Aware Multi-UAV Full-Duplex Communication: System Design and Experiment

The deployment of unmanned aerial vehicle (UAV) systems relies on high-performance yet lightweight wireless links between UAVs and ground stations (GSs). This paper presents a geometry-aware multi-UAV in-band full-duplex (MU-IBFD) communication system that uses high-gain directional antennas and separated uplink/downlink channels to convert self-interference into controllable co-channel interference (CCI) between UAVs, thereby avoiding energy-intensive self-interference cancelers on UAVs. We also derive a geometry-aware CCI model and define a reliable operating region (ROR) in the 3D airspace, within which the SINR requirement is satisfied. A prototype consisting of two UAVs and a GS is developed, and field trials are conducted. The measured CCI as a function of UAV positions agrees well with the theoretically predicted non-ROR region, and the downlink capacity significantly exceeds that of a conventional time-division duplex (TDD) with omni-directional scheme and higher transmit power and approaches that of ideal IBFD in most of the airspace. A proof-of-concept 4K/60p video transmission further demonstrates the practical potential of the proposed MU-IBFD system.

cs.IT↗
arXiv2026

ShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search

In recent years, large language models (LLMs) have made rapid progress in information retrieval, yet existing research has mainly focused on text or static multimodal settings. Open-domain video shot retrieval, which involves richer temporal structure and more complex semantics, still lacks systematic benchmarks and analysis. To fill this gap, we introduce ShotFinder, a benchmark that formalizes editing requirements as keyframe-oriented shot descriptions and introduces five types of controllable single-factor constraints: Temporal order, Color, Visual style, Audio, and Resolution. We curate 1,210 high-quality samples from YouTube across 20 thematic categories, using large models for generation with human verification. Based on the benchmark, we propose ShotFinder, a text-driven three-stage retrieval and localization pipeline: (1) query expansion via video imagination, (2) candidate video retrieval with a search engine, and (3) description-guided shot localization. Experiments on multiple closed-source and open-source models reveal a significant gap to human performance, with clear imbalance across constraints: temporal localization is relatively tractable, while color and visual style remain major challenges. These results reveal that open-domain video shot retrieval is still a critical capability that multimodal large models have yet to overcome.

cs.CV↗
arXiv2026

SlipSense: Multimodal Tactile Learning for Low-Latency and Generalized Slip Detection

Slip detection is fundamental to dexterous manipulation, yet existing systems often lack precise characterization of detection latency and cross-platform generalization. We present SlipSense, a multimodal tactile slip-detection framework built on TacV5, a compact sensor integrating a $32 \times 32$ piezoresistive array operating at 240 Hz and a 3-axis MEMS accelerometer operating at 8 kHz. The piezoresistive array captures spatial pressure distributions, while the accelerometer captures friction-induced vibrations, providing complementary slip cues. The framework performs modality-specific encoding, intra-sensor fusion, and cross-modal attention with causal temporal prediction at 240 Hz. Experiments on a dataset of 1.4 million frames spanning 37 objects demonstrate the complementarity of the two modalities. SlipSense achieves 96.7% Macro F1 with a false-positive rate below 1.6%, detecting 76% of slip events within 23.1 ms. When trained solely on UMI data, SlipSense generalizes zero-shot to a Tesollo dexterous hand, transferring across unseen objects, distinct sensor units, and robotic platforms without retraining.

cs.RO↗
arXiv2026

Touch2Trace: Tactile-Driven Imitation Learning for Dexterous Cable Tracing

Dexterous manipulation of deformable objects demands continuous fingertip-level regulation of pressure, friction, and incipient slip. We study one of the most challenging cases: dexterous cable tracing, feeding a cable through the hand with repeated pinch-and-curl motions of the thumb and index finger. We introduce Touch2Trace, a tactile-driven imitation-learning system for this task, and provide, to our knowledge, the first systematic real-world characterization of how encoder pretraining, control rate, temporal context, and spatial resolution each shape policy performance. The winning learning recipe combines a tactile encoder pretrained for a custom 32 x 32 piezoresistive sensor (TacV5) via self-supervised learning with a lightweight transformer policy trained on teleoperated demonstrations via behavior cloning, deployed at 60 Hz on a Tesollo DG-5F hand. Tactile feedback without vision or explicit cable-state estimation significantly improves tracing performance versus a proprioception-only baseline: from 0.2 cm to 20.1 cm mean distance and 0% to 93% success rate, with zero-shot transfer to unseen cables and routing conditions. The results quantify the influence of key parameters in tactile-driven systems for reliable dexterous deformable object manipulation.

cs.RO↗
arXiv2026

Why Does Weak-OOD Help? A Further Step Towards Understanding Jailbreaking VLMs

Large Vision-Language Models (VLMs) are susceptible to jailbreak attacks: researchers have developed various attack strategies that bypass the safety mechanisms of VLMs. Among these approaches, jailbreak methods based on the Out-of-Distribution (OOD) strategy have garnered widespread attention due to their simplicity and effectiveness. This paper further advances the understanding of OOD-based VLM jailbreak methods. We show that mild OOD manipulations can achieve stronger jailbreak performance than both clean inputs and overly strong perturbations, a non-monotonic pattern we define as "weak-OOD". We explain this phenomenon through a trade-off between two dominant factors: input intent perception and model refusal triggering. Our evidence suggests that these two factors respond differently to OOD manipulations, which is consistent with a discrepancy between broad pre-training robustness and narrower safety alignment. Building on this insight, we draw inspiration from optical character recognition (OCR) capability enhancement---a core task in the pre-training phase of mainstream VLMs. Leveraging this capability, we design JOCR (Jailbreak via OCR-Aware Embedded Text Perturbation), a practical OCR-readable extension of embedded-text jailbreaks that achieves the best average ASR among evaluated baselines. Code is available at GitHub: https://github.com/Yuxuan2003/weak-ood-jailbreak.

cs.CR↗
arXiv2026

Revisiting dependence in multiple testing: empirical distribution approaches for FDP control

Large-scale multiple hypothesis testing is central to the analysis of high-throughput data, where controlling false discoveries is critical. Classical procedures typically rely on theoretical null distributions and often adjust for dependence among test statistics, but these approaches may be misleading when the empirical distribution of null statistics deviates from theoretical assumptions. Motivated by this observation, we investigate the role of the empirical cumulative distribution function (c.d.f.) of null test statistics in controlling the false discovery proportion (FDP). We first show that, under an oracle scenario where the empirical c.d.f. of the test statistics for all null hypotheses is known, FDP control can be achieved optimally regardless of the dependence structure, highlighting that explicit modeling of dependence may be unnecessary. Building on this insight, we propose an empirical c.d.f.-based FDP control (eFDP) method, implemented via a multivariate mixture model framework and a nonparametric estimation procedure for the empirical c.d.f.s, establish its asymptotic convergence, and construct an FDP control procedure that achieves asymptotic FDP control. Extensive simulations demonstrate that eFDP attains more accurate FDP control and higher power than existing approaches, particularly under strong dependence, and analysis of a high-dimensional breast cancer gene expression dataset confirms its practical utility.

stat.ME↗
arXiv2026

FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies

Vision-Language-Action (VLA) models are increasingly expected to not only complete robot tasks, but also follow human instructions about how those tasks should be executed. However, existing robot datasets usually pair trajectories with coarse goal-level language, leaving execution-critical details such as active arm, approach direction, and contact region unspecified. This limits steerable policy learning and robotic video understanding. We introduce FineVLA, an open framework for action-aligned fine-grained VLA supervision. The framework includes: (1) a data construction tool that unifies 972,247 trajectories across 85K tasks from 10 open-source robot datasets and builds FineVLA-Data, a human-verified dataset of 47,159 fine-grained trajectories; (2) a held-out benchmark with 500 videos, 11,631 atomic facts, and 1,030 VQA questions; (3) a robotics-specialized VLM annotator for scalable fine-grained annotation; and (4) a steerable VLA policy trained with controlled mixtures of fine-grained and raw goal-level instructions. Our experiments yield three findings. First, fine-grained supervision does not sacrifice goal-level success: FG-only improves over Raw-only by +1.4 to +8.1 success-rate points across settings. Second, fine-grained and raw instructions are complementary, following a consistent inverted-U trend peaking at FG:Raw = 1:2 to 1:1. The best mixed setting reaches 86.8%/82.5% in RoboTwin simulation and 62.7/100 in real-world dual-arm manipulation (vs. 49.9 Raw-only). Third, fine-grained supervision improves steerable control: the largest real-world gains appear on pose (+23), color (+18), and approach direction (+18)--factors where goal-level instructions provide no guidance. Overall, fine-grained language should augment goal-level instructions: specifying how to execute alongside what to achieve. Project page: https://finevla.xlang.ai/

cs.RO↗
arXiv2026

FFSlim: An Efficient and Lightweight Format for Multi-modal Data Storage and Retrieval

With the rapid expansion of large-scale media-text corpora, multi-modal datasets increasingly require efficient storage and retrieval. Existing formats such as Files, TDP, and FFRecord work adequately for uni-modal data but expose fundamental limitations in multi-modal settings, including storage redundancy, massive small-file overheads, cache-unfriendly layouts, and heavy index structures. These issues jointly inflate storage and memory usage and make I/O the dominant bottleneck in real training workloads. We present FFSlim, a lightweight format for storing and retrieving multi-modal data. FFSlim improves storage efficiency and loading throughput through three components: a unified file format that removes media duplication and avoids small-file proliferation; an adaptive retrieval mechanism that enables low-overhead pair-level access and accelerates repeated media loading; and a redundancy detection and aggregation module that converts existing datasets into the FFSlim layout. The experimental results demonstrate that FFSlim achieves 2.07x and 8.26x higher data loading and write throughput on average than the strongest baseline, with minimal storage and index overhead. Consequently, these underlying I/O accelerations enable FFSlim to reduce end-to-end training time by 5.36%-14.18% across seven diverse multi-modal models.

cs.PF↗
arXiv2026

openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents

Long-horizon coding agents operate over evolving repository states while increasingly relying on heterogeneous capabilities, delegated agents, and multi-agent coordination. These trends pose two complementary challenges for the agent harness. First, developers need to compose capabilities, reconfigure execution logic, and scale increasingly complex agent systems without repeatedly rebuilding orchestration. Second, complex coding tasks continuously produce new evidence---such as semantic diagnostics, execution outcomes, task progress, and changing context relevance---that should dynamically influence subsequent runtime decisions. We characterize these challenges as Structural Composability and Runtime Adaptivity. We present openJiuwen, an open-source harness designed for both developer composability and adaptive task execution. openJiuwen provides a shared execution substrate and Rail-based capability composition across single agents, delegated sub-agents, and Swarm Flow, enabling developers to construct sophisticated agent harnesses under common execution semantics. It further adapts framework-controlled runtime decisions around a fixed model policy, allowing evolving evidence to dynamically affect context, feedback, and task control toward successful completion. We systematically evaluate openJiuwen on SWE-bench Verified and Terminal-Bench 2.1, where it achieves 82.6% and 87.19%, respectively, exceeding the strongest selected official-leaderboard point estimates by 3.4 and 3.39 percentage points. These results show that openJiuwen achieves strong performance on complex coding tasks while providing a composable and adaptive harness design.

cs.AI↗
arXiv2026

Physics-Informed WiFi Sensing for Robust 3D Human Pose Estimation in Mobile and Cross-Environment Settings

Device-free human pose estimation using commodity WiFi signals has emerged as a promising paradigm for pervasive sensing in mobile computing systems. However, existing approaches often suffer from severe performance degradation when deployed across heterogeneous environments due to complex multipath propagation and domain shifts in wireless signals. In this paper, we present a physics-informed WiFi sensing framework for robust 3D human pose estimation under mobile and cross-environment settings. Our approach explicitly models wireless signal propagation characteristics and incorporates multipath-aware attention to capture environment-dependent signal variations. To further improve generalization, we introduce a disentangled representation learning scheme that separates pose-related features from environment-specific factors, enabling effective cross-domain adaptation without requiring extensive retraining. We implement our system using commodity WiFi devices and evaluate it on multiple public benchmarks, including Person-in-WiFi-3D and MM-Fi, as well as real-world deployments across diverse indoor environments. Experimental results demonstrate that our framework significantly improves robustness and generalization performance compared to state-of-the-art methods, particularly under cross-environment scenarios. These results highlight the potential of physics-informed wireless sensing for enabling reliable, scalable, and infrastructure-free human-centric applications in mobile computing systems.

eess.SP↗
arXiv2026

Scattering-Induced Magnon Layer-Hall Transport beyond Band Geometry

The layer Hall effect has been exclusively attributed to layer-locked Berry curvature, posing a fundamental barrier to its realization in conventional magnets. Here we report a fundamentally distinct layer Hall effect for bosonic excitations, i.e., magnons, which originates solely from non-reciprocal dipolar scattering at heterointerfaces, thereby decoupling the phenomenon from geometric-phase mechanisms. Using a microscopic scattering theory, we demonstrate that a longitudinal temperature gradient drives opposite transverse thermal Hall currents in a nanowire atop a magnetic film, with the direction fully reconfigurable by the applied magnetic field. The effect yields a significant Hall angle of $\sim 6^{\circ}$ in conventional magnetic heterostructures, eliminating the need for topological engineering. Our findings establish a scattering-driven paradigm for layer Hall effect, extendable to ferrons and polar phonons, and predict a Hall response that is readily detectable in conventional magnetic heterostructures.

cond-mat.mes-hall↗
arXiv2026

SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Tasks

Model routing aims to select the most suitable model from a candidate pool for each query, balancing quality and cost. Existing VLM routing research is limited to traditional VQA evaluation, lacks systematic calibration optimization for open-set scenarios, and employs training objectives that dilute multi-positive signals via softmax normalization without incorporating cost. We address these limitations with three contributions: (1)VLM-ExecRouterBench, the first execution-oriented VLM routing benchmark covering Code, Agentic, and Search domains with 11 candidate models spanning nearly two orders of magnitude in pricing; (2)SCOPE-Router, a dual-tower router that matches queries to model behavior profiles constructed via hybrid calibration (random/diagnostic/diversity sampling), enabling new models to join routing without retraining; (3)CRM+RCCR, an architecture-agnostic cost-aware objective that encodes cost preference into continuous relevance targets through per-pair independent scoring, eliminating multi-positive dilution while regularizing queries with similar routing preferences to be closer in the routing space. Empirically, SCOPE-Router achieves the best Rank Score on all three benchmarks, surpassing the runner-up by 1.84 points under OOD settings and by 6.75 points under doubly OOD open-set evaluation. When applied to four diverse routers, CRM+RCCR improves Rank Score by 1.25--6.21 points.

cs.CV↗
arXiv2026

Dynamic SpectraFormer for Ultra-High-Definition Underwater Image Enhancement

Underwater images suffer from color distortion, haze, and poor visibility due to light refraction and absorption in water. These challenges significantly impact the utilization of Autonomous Underwater Vehicles (AUVs) or marine robots. Typically, color and brightness distortions manifest at lower frequencies, while edge and texture distortions are prevalent at higher frequencies. Traditional methods struggle to concurrently rectify these mixed distortions as they primarily concentrate on the spatial domain. To address these issues, we introduce the Dynamic SpectraFormer, which enhances underwater images through a frequency domain transformer. The Dynamic SpectraFormer introduces an ultra-high-resolution sparse spectrum attention module, which could capture the long-term dependency without losing the universal approximating power. Additionally, we have developed a dynamic spectrum weight generation layer that serves as an adaptive spectrum band selector, accentuating critical frequency bands and suppressing less relevant ones. Consequently, this method significantly improves underwater image quality by addressing both high- and low-frequency distortions. Our extensive ablation studies and comparative evaluations consolidate the Dynamic SpectraFormer's efficacy across multiple underwater image enhancement benchmarks. The source code is available at https://github.com/arifence2024/DynamicSpectraFormer.git.

cs.CV↗
arXiv2026

How Roadside Units Enhance Intersection Safety? Cooperative Autonomous Driving System Design and A Proof of Concept

Intersections remain one of the most hazardous locations in urban road networks, where heterogeneous traffic participants and limited visibility frequently lead to severe traffic conflicts. In this paper, a vehicle-to-infrastructure-to-vehicle (V2I2V) cooperative system is proposed for improving road safety and traffic efficiency by using digital twins (DTs) deployed on roadside units (RSUs) to eliminate blind spots and centrally coordinate connected and automated vehicles (CAVs) in smart intersections. The proposed system integrates cloud-based global DTs for macroscopic guidance and RSU-based local DTs for real-time operations. Within this architecture, a hierarchical reinforcement learning (HRL) framework combines offline pre-training with online fine-tuning to achieve robust cooperative control. Experimental results show that the proposed system achieves substantial improvements in safety and efficiency in simulation experiments and real-world proof-of-concept (PoC) trials. In simulations, our system ensures high safety, efficiency, and smoothness under realistic communications and traffic constraints. In PoC trials, the RSU-centric control loop achieves a decision-making latency of approximately 42 ms and maintains a safe stopping distance of 8.5 m for pedestrians, while also shortening stop duration and overall traversal time. These results indicate that the proposed system provides robust and scalable performance at smart intersections.

eess.SY↗
arXiv2026

Green Wireless Network Scaling for Joint Deployment: Multi-BSs or Multi-RISs?

The imminent emergence of sixth-generation (6G) networks faces critical challenges from spatially heterogeneous traffic and escalating energy consumption, necessitating sustainable scaling strategies for network infrastructure such as base stations (BSs) and reconfigurable intelligent surfaces (RISs). This paper presents a systematic scaling analysis of the Integrated Relative Energy Efficiency (IREE) metric under joint multi-BS and multi-RIS deployment in traffic-mismatched scenarios. Specifically, we propose an Alternating Directional Dual Radial Basis Function (ADD-RBF) framework that models the spatial capacity contributions of BSs and RISs through two separately parameterized RBF-type branches and maximizes IREE through accepted alternating optimization, with established representation expressiveness and stage-wise convergence properties. Theoretical analysis reveals distinct scaling behaviors: BS proliferation drives logarithmic capacity growth $\mathcal{O}(\log N^{BS})$ and polynomial large-scale mismatch reduction $\mathcal{O}\big((N^{BS})^{-t_g/2}\big)$, whereas RIS deployment provides a bounded passive capacity-gain correction and residual-structure-dependent mismatch reduction. Specifically, the RIS-side mismatch decreases polynomially as $\mathcal{O}\big((N^R)^{-t_\ell/2}\big)$ for spatially diffuse residuals and follows the stretched-exponential order $\mathcal{O}\big(\exp[-c_R\sqrt{N^R}]\big)$ for hotspot-dominated residuals. Simulation results show that RISs are effective in refining spatial traffic-capacity mismatch and alleviating hotspots, making them particularly attractive when mismatch dominates, while BSs are generally preferable under capacity shortages. These findings offer practical guidelines for green 6G network design.

eess.SY↗
arXiv2026

Qwen-CUA: Native Computer Use for (almost) Everything

Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive experience, and learning from sparse yet verifiable outcomes. We introduce Qwen-CUA, a native computer-use agent with a 397B-A17B Qwen mixture-of-experts backbone. It observes only screenshots and acts through keyboard and mouse events, without DOM trees, accessibility metadata, or task-specific APIs. Its scaffold maintains up to 20 active screenshots and folds older visual history in fixed-size blocks to retain recent evidence while preserving reusable prompt prefixes. For training, we build a cloud rollout fleet with access to nearly 100,000 vCPUs and tens of thousands of concurrent environments, construct approximately 40,000 verifiable tasks, and collect personalized long-horizon workflows across everyday and professional software. We optimize complete trajectories with verifiable rewards and trajectory slicing, while iterative training runs refresh supervised data and recalibrate reinforcement-learning tasks. Across eight benchmarks, Qwen-CUA outperforms Qwen3.7 and remains competitive with leading proprietary systems, reaching 86.2 on OSWorld-Verified and 18.5/48.4 binary/partial completion on OSWorld 2.0. Scaling the same recipe to a model with over one trillion parameters yields Qwen-CUA-Max, improving these scores to 87.6 and 21.2/53.3. Qwen-CUA also reduces RedTeamCUA attack success from 36.6 to 16.4 relative to Qwen3.7. Efficiency analyses, a browser deployment, and Bash-augmented experiments further characterize practical behavior. These results establish native computer use as a broadly capable agent foundation and highlight scalable verifiable interaction and hybrid tool use as key directions.

cs.LG↗
arXiv2026

Multiview Multi-Person Human Mesh Recovery Under Large Scenes with Occlusions

Human mesh recovery (HMR) aims to recover 3D human meshes from images. Most existing HMR benchmarks and methods focus on either multi-person reconstruction from a single view or single-person reconstruction from multiple views, where the number of subjects and the scene scale are relatively limited. Such settings are insufficient for real-world applications with large scenes and severe inter-person occlusions. To address this limitation, we introduce a large-scale synthetic benchmark for multiview multi-person HMR, termed MVMP-HMR. The proposed dataset contains 15 complex scenes with up to 50 camera views and 30 interacting persons, featuring large spatial coverage and severe occlusions, which significantly increases the difficulty of human mesh recovery. Based on this benchmark, we further propose a multiview multi-person whole-body human mesh recovery model, referred to as MVMP-HMR model. The model first fuses multiview features into a scene-level 3D feature volume, and then leverages pelvis joints predicted by a 3D pose estimation network to extract person-specific queries from the 3D feature volume. These human queries are cross-attended with the 3D feature volume and integrated to decode each person's 3D mesh. Moreover, we introduce two novel losses--the orientation loss and the 3D joint density loss--to alleviate orientation and pose ambiguities under severe occlusions. Experiments demonstrate that existing state-of-the-art HMR methods struggle on the proposed MVMP-HMR benchmark, while our method consistently outperforms prior SOTAs in large-scale scenes with severe occlusions.

cs.CV↗