Search arXiv⌕ Search

arXiv subjects

Qi Wu

Publications and source records attributed to Qi Wu.

At least 91 records · Page 5Linked to original sources
arXiv2026

SpatialAnt: Autonomous Zero-Shot Robot Navigation via Active Scene Reconstruction and Visual Anticipation

Vision-and-Language Navigation (VLN) has recently benefited from Multimodal Large Language Models (MLLMs), enabling zero-shot navigation. While recent exploration-based zero-shot methods have shown promising results by leveraging global scene priors, they rely on high-quality human-crafted scene reconstructions, which are impractical for real-world robot deployment. When encountering an unseen environment, a robot should build its own priors through pre-exploration. However, these self-built reconstructions are inevitably incomplete and noisy, which severely degrade methods that depend on high-quality scene reconstructions. To address these issues, we propose SpatialAnt, a zero-shot navigation framework designed to bridge the gap between imperfect self-reconstructions and robust execution. SpatialAnt introduces a physical grounding strategy to recover the absolute metric scale for monocular-based reconstructions. Furthermore, rather than treating the noisy self-reconstructed scenes as absolute spatial references, we propose a novel visual anticipation mechanism. This mechanism leverages the noisy point clouds to render future observations, enabling the agent to perform counterfactual reasoning and prune paths that contradict human instructions. Extensive experiments in both simulated and real-world environments demonstrate that SpatialAnt significantly outperforms existing zero-shot methods. We achieve a 66% Success Rate (SR) on R2R-CE and 50.8% SR on RxR-CE benchmarks. Physical deployment on a Hello Robot further confirms the efficiency and efficacy of our framework, achieving a 52% SR in challenging real-world settings.

cs.RO↗
arXiv2026

From School AI Readiness to Student AI Literacy: A National Multilevel Mediation Analysis of Institutional Capacity and Teacher Capability

Artificial intelligence (AI) is increasingly embedded in vocational education systems, yet empirical evidence linking institutional AI readiness to student learning outcomes remains limited. This study develops and tests a 2-2-1 cross-level mediation framework examining how school-level AI readiness is associated with student AI literacy through aggregated teacher mechanisms. Using linked survey data from 1,007 vocational institutions, 156,125 teachers, and 2,379,546 students nationwide, multilevel models were estimated to assess direct, indirect, and contextual effects. Results indicate that overall school AI readiness is positively associated with student AI literacy after adjusting for institutional and regional characteristics. When examined independently, all readiness dimensions show positive associations, while simultaneous modelling suggests that readiness operates as an integrated organisational configuration. Cross-level mediation analyses reveal that aggregated teacher-perceived AI capability partially mediates the relationship between institutional readiness and student literacy, whereas general attitudinal acceptance measures do not demonstrate stable transmission effects. Robustness analyses further show that this readiness-capability-literacy pathway remains structurally stable across heterogeneous regional AI development contexts and under alternative modelling specifications. These findings reposition institutional AI readiness as a multilevel organisational condition linked to student AI literacy, identify collective teacher capability as its central transmission mechanism, and underscore the need to align infrastructural investment with sustained professional capacity development.

cs.CY↗
arXiv2026

Click-to-Ask: An AI Live Streaming Assistant with Offline Copywriting and Online Interactive QA

Live streaming commerce has become a prominent form of broadcasting in the modern era. To facilitate more efficient and convenient product promotions for streamers, we present Click-to-Ask, an AI-driven assistant for live streaming commerce with complementary offline and online components. The offline module processes diverse multimodal product information, transforming complex inputs into structured product data and generating compliant promotional copywriting. During live broadcasts, the online module enables real-time responses to viewer inquiries by allowing streamers to click on questions and leveraging both the structured product information generated by the offline module and an event-level historical memory maintained in a streaming architecture. This system significantly reduces the time needed for promotional preparation, enhances content engagement, and enables prompt interaction with audience inquiries, ultimately improving the effectiveness of live streaming commerce. On our collected dataset of TikTok live stream frames, the proposed method achieves a Question Recognition Accuracy of 0.913 and a Response Quality score of 0.876, demonstrating considerable potential for practical application. The video demonstration can be viewed here: https://www.youtube.com/shorts/mWIXK-SWhiE.

cs.CV↗
arXiv2026

Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale

Goal-oriented vision-language navigation requires robust exploration capabilities for agents to navigate to specified goals in unknown environments without step-by-step instructions. Existing methods tend to exclusively utilize shortest-path trajectories, lacking effective exploration priors for training navigation agents. To address the above challenges, we present SID, a goal-oriented vision-and-language navigation learning approach with Self-Improving Demonstrations. Specifically, SID learns an initial agent on the shortest-path data sampled from environments and then leverages this agent to generate novel exploration trajectories. The novel rollouts provide demonstrations with stronger exploration strategies to train a better agent, which in turn produces higher-quality agent demonstrations for the next round of training. We show that this iterative self-improving pipeline readily scales to new environments, and the resulting demonstrations are highly transferable, elevating the performance ceiling across a variety of vision-and-language navigation tasks. Extensive experiments demonstrate that SID significantly boosts the exploration capabilities and generalization of navigation agents. The resulting agent achieves new state-of-the-art performance on goal-oriented vision-and-language navigation benchmarks, including REVERIE, SOON as well as strong transferability to object-goal navigation and VLN-CE. It notably achieves a 50.9% success rate on the unseen validation splits of SOON, surpassing prior leading approaches by a margin of 13.9%.

cs.CV↗
arXiv2026

Efficient 2.5-D FEM-Based Scattering Analysis of the Human Body for RF Sensing

Model training for Device-Free Localization (DFL) and Radio-Frequency (RF) sensing heavily relies on large-scale datasets, which are difficult, expensive, and time-consuming to obtain through measurements. This paper proposes a fast 2.5-dimensional Finite Element Method (2.5-D FEM) for computing the scattering fields of a Body of Revolution (BoR) human model under the excitation of a z-directed dipole. The proposed method can evaluate the effect of human micro-movements through the statistical characteristics of the Received Signal Strength Indicator (RSSI). The numerical accuracy and the practical applicability of the proposed method are validated through comparisons with full-wave simulations and indoor RF sensing experiments. The simulation results show agreement with the experimental measurements, demonstrating that the method is a reliable tool for evaluating micro-movement-induced statistical variations. The proposed method provides a practical and efficient means for generating large-scale, labeled RF training datasets, thereby accelerating the development of indoor localization tools as well as the calibration and tuning of tomographic reconstruction methods.

eess.SP↗
arXiv2026

Dribble Master: Learning Agile Humanoid Dribbling through Legged Locomotion

Humanoid soccer dribbling is a highly challenging task that demands dexterous ball manipulation while maintaining dynamic balance. Traditional rule-based methods often struggle to achieve accurate ball control due to their reliance on fixed walking patterns and limited adaptability to real-time ball dynamics. To address these challenges, we propose a two-stage curriculum learning framework that enables a humanoid robot to acquire dribbling skills without explicit dynamics or predefined trajectories. In the first stage, the robot learns basic locomotion skills; in the second stage, we fine-tune the policy for agile dribbling maneuvers. We further introduce a virtual camera model in simulation that simulates the field of view and perception constraints of the real robot, enabling realistic ball perception during training. We also design heuristic rewards to encourage active sensing, promoting a broader visual range for continuous ball perception. The policy is trained in simulation and successfully transferred to a physical humanoid robot. Experiment results demonstrate that our method enables effective ball manipulation, achieving flexible and visually appealing dribbling behaviors across multiple environments. This work highlights the potential of reinforcement learning in developing agile humanoid soccer robots. Additional details and videos are available at https://zhuoheng0910.github.io/dribble-master/.

cs.RO↗
arXiv2026

Sparsity Forcing: Reinforcing Token Sparsity of MLLMs

Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods merely exploit a model's inherent sparsity and thus plateau at moderate budgets (about 50\% token reduction), with little headroom to push budget lower without hurting accuracy. Other approaches attempt to enforce sparsity through trainable sparse attention or sharpness-inducing regularizers, but these either fix rigid patterns that ignore input and layer dynamics, or optimize proxy objectives without direct control over token budgets. In this paper, we explicitly reinforce token sparsity in well-posed multimodal large language models (MLLMs) through a simple RL-based post-training framework named \textit{Sparsity Forcing}. Our method explores the efficiency-accuracy trade-off by running multiple rollouts with different token budgets, where both efficiency (token reduction ratio) and performance (answer correctness) are formulated as joint rewards. By contrasting rollouts within each group, the more efficient and correct answer is rewarded while less efficient or incorrect ones are penalized, thereby turning token saving into an end-to-end, inference-consistent optimization objective. Across thirteen image and video benchmarks, Sparsity Forcing raises token reduction ratio on Qwen2-VL/Qwen2.5-VL from 20\% to 75\% with minimal accuracy decline, significantly reducing long-context inference memory by up to 3$\times$ while speeding up decoding by up to 3.3$\times$.

cs.LG↗
arXiv2026

T-linear specific heat in pressurized and magnetized Shastry-Sutherland Mott insulator SrCu2(BO3)2

The pressurized Shastry-Sutherland Mott insulator SrCu2(BO3)2 has been found to host a plaquette-singlet phase and an antiferromagnetic phase that break different symmetries spontaneously.The recent experiment showed that their transition is of a first order nature, which seems against the pursuit of exotic and deconfined degrees of freedom in this famous frustrated quantum magnet. We found a new direction in this study. By applying a magnetic field to the material, we discover that SrCu2(BO3)2 exhibits a universal and metallic T-linear specific heat behavior in a large magnetitic field range close to the pressure of zero-field first order transition between plaquette-singlet and antiferromagnetic phases. Such an unexpected gapless response from an electronically gapped Mott insulator could be attributed to magnetized Dirac spinons liberated by the combined effect of magnetic field and pressure, consistently seen from our quantum many-body thermal tensor network computation of the Shastry-Sutherland model under magnetic field. Such a robust and universal T-linear specific heat phase points out the richness of the phase diagram of the material expanded by the axes of pressure and magnetic field and is calling for new theoretical frameworks to its full explanation.

cond-mat.str-el↗
arXiv2026

One Agent to Guide Them All: Empowering MLLMs for Vision-and-Language Navigation via Explicit World Representation

A navigable agent needs to understand both high-level semantic instructions and precise spatial perceptions. Building navigation agents centered on Multimodal Large Language Models (MLLMs) demonstrates a promising solution due to their powerful generalization ability. However, the current tightly coupled design dramatically limits system performance. In this work, we propose a decoupled design that separates low-level spatial state estimation from high-level semantic planning. Unlike previous methods that rely on predefined, oversimplified textual maps, we introduce an interactive metric world representation that maintains rich and consistent information, allowing MLLMs to interact with and reason on it for decision-making. Furthermore, counterfactual reasoning is introduced to further elicit MLLMs' capacity, while the metric world representation ensures the physical validity of the produced actions. We conduct comprehensive experiments in both simulated and real-world environments. Our method establishes a new zero-shot state-of-the-art, achieving 48.8\% Success Rate (SR) in R2R-CE and 42.2\% in RxR-CE benchmarks. Furthermore, to validate the versatility of our metric representation, we demonstrate zero-shot sim-to-real transfer across diverse embodiments, including a wheeled TurtleBot 4 and a custom-built aerial drone. These real-world deployments verify that our decoupled framework serves as a robust, domain-invariant interface for embodied Vision-and-Language navigation.

cs.RO↗
arXiv2026

SoK: The Security-Safety Continuum of Multimodal Foundation Models through Information Flow and Global Game-Theoretic Analysis of Asymmetric Threats

Multimodal foundation models (MFMs) integrate diverse data modalities to support complex and wide-ranging tasks. However, this integration also introduces distinct safety and security challenges. In this paper, we unify the concepts of safety and security in the context of MFMs by identifying critical threats that arise from both model behavior and system-level interactions. We propose a taxonomy grounded in information theory, evaluating risks through the concepts of channel capacity, signal, noise, and bandwidth. This perspective provides a principled way to analyze how information flows through MFMs and how vulnerabilities can emerge across modalities. Building on this foundation, we introduce a deterministic minimax formulation to analyze defense mechanisms and to study a structural asymmetry of defense in multimodal systems. Our analysis indicates that model-centric defenses, which primarily operate by suppressing noise or enhancing signal, tend to exhibit diminishing effectiveness against increasingly adaptive attacks. In contrast, system-level safeguards that constrain authorized information flow and agent behavior impose stronger limits on adversarial impact by reducing effective bandwidth. To operationalize this insight, our framework maps attacks and defenses onto information-theoretic axes, effectively organizing and reducing the defense search space. Using a proposed Defense Coverage Index (DCI) to evaluate 15 representative defenses, we observe that system-level bandwidth constraints provide stronger and more consistent protection across attack classes than brittle model-level mechanisms. Finally, we formalize an MFM ``self-destruction threshold'' that specifies when termination should be triggered, offering a concrete activation rule for circuit-breaker safeguards in multimodal systems.

cs.CR↗
arXiv2026

Glyph-Based Multiscale Visualization of Turbulent Multi-Physics Statistics

Many scientific and engineering problems involving multi-physics span a wide range of scales. Understanding the interactions across these scales is essential for fully comprehending such complex problems. However, visualizing multivariate, multiscale data within an integrated view where correlations across space, scales, and fields are easily perceived remains challenging. To address this, we introduce a novel local spatial statistical visualization of flow fields across multiple fields and turbulence scales. Our method leverages the curvelet transform for scale decomposition of fields of interest, a level-set-restricted centroidal Voronoi tessellation to partition the spatial domain into local regions for statistical aggregation, and a set of glyph designs that combines information across scales and fields into a single, or reduced set of perceivable visual representations. Each glyph represents data aggregated within a Voronoi region and is positioned at the Voronoi site for direct visualization in a 3D view centered around flow features of interest. We implement and integrate our method into an interactive visualization system where the glyph-based technique operates in tandem with linked 3D spatial views and 2D statistical views, supporting a holistic analysis. We demonstrate with case studies visualizing turbulent combustion data--multi-scalar compressible flows--and turbulent incompressible channel flow data. This new capability enables scientists to better understand the interactions between multiple fields and length scales in turbulent flows.

cs.GR↗
arXiv2026

ALIEN: Analytic Latent Watermarking for Controllable Generation

Watermarking is a technical alternative to safeguarding intellectual property and reducing misuse. Existing methods focus on optimizing watermarked latent variables to balance watermark robustness and fidelity, as Latent diffusion models (LDMs) are considered a powerful tool for generative tasks. However, reliance on computationally intensive heuristic optimization for iterative signal refinement results in high training overhead and local optima entrapment.To address these issues, we propose an \underline{A}na\underline{l}ytical Watermark\underline{i}ng Framework for Controllabl\underline{e} Generatio\underline{n} (ALIEN). We develop the first analytical derivation of the time-dependent modulation coefficient that guides the diffusion of watermark residuals to achieve controllable watermark embedding pattern.Experimental results show that ALIEN-Q outperforms the state-of-the-art by 33.1\% across 5 quality metrics, and ALIEN-R demonstrates 14.0\% improved robustness against generative variant and stability threats compared to the state-of-the-art across 15 distinct conditions. Code can be available at https://anonymous.4open.science/r/ALIEN/.

eess.IV↗
arXiv2026

User-Feedback-Driven Adaptation for Vision-and-Language Navigation

Real-world deployment of Vision-and-Language Navigation (VLN) agents is constrained by the scarcity of reliable supervision after offline training. While recent adaptation methods attempt to mitigate distribution shifts via environment-driven self-supervision (e.g., entropy minimization), these signals are often noisy and can cause the agent to amplify its own mistakes during long-horizon sequential decision-making. In this paper, we propose a paradigm shift that positions user feedback, specifically episode-level success confirmations and goal-level corrections, as a primary and general-purpose supervision signal for VLN. Unlike internal confidence scores, user feedback is intent-aligned and in-situ consistent, directly correcting the agent's decoupling from user instructions. To effectively leverage this supervision, we introduce a user-feedback-driven learning framework featuring a topology-aware trajectory construction pipeline. This mechanism lifts sparse, goal-level corrections into dense path-level supervision by generating feasible paths on the agent's incrementally built topological graph, enabling sample-efficient imitation learning without requiring step-by-step human demonstrations. Furthermore, we develop a persistent memory bank mechanism for warm-start initialization, supporting the reuse of previously acquired topology and cached representations across navigation sessions. Extensive experiments on the GSA-R2R benchmark demonstrate that our approach transforms sparse interaction into robust supervision, consistently outperforming environment-driven baselines while exhibiting strong adaptability across diverse instruction styles.

cs.AI↗
arXiv2026

ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas

Large language models (LLMs) have revolutionized automated code generation, yet the evaluation of their real-world effectiveness remains limited by static benchmarks and simplistic metrics. We present ProxyWar, a novel framework that systematically assesses code generation quality by embedding LLM-generated agents within diverse, competitive game environments. Unlike existing approaches, ProxyWar evaluates not only functional correctness but also the operational characteristics of generated programs, combining automated testing, iterative code repair, and multi-agent tournaments to provide a holistic view of program behavior. Applied to a range of state-of-the-art coders and games, our approach uncovers notable discrepancies between benchmark scores and actual performance in dynamic settings, revealing overlooked limitations and opportunities for improvement. These findings highlight the need for richer, competition-based evaluation of code generation. Looking forward, ProxyWar lays a foundation for research into LLM-driven algorithm discovery, adaptive problem solving, and the study of practical efficiency and robustness, including the potential for models to outperform hand-crafted agents. The project is available at https://github.com/xinke-wang/ProxyWar.

cs.SE↗
arXiv2026

CD-PIM: A High-Bandwidth and Compute-Efficient LPDDR5-Based PIM for Low-Batch LLM Acceleration on Edge-Device

Edge deployment of low-batch large language models (LLMs) faces critical memory bandwidth bottlenecks when executing memory-intensive general matrix-vector multiplications (GEMV) operations. While digital processing-in-memory (PIM) architectures promise to accelerate GEMV operations, existing PIM-equipped edge devices still suffer from three key limitations: limited bandwidth improvement, component under-utilization in mixed workloads, and low compute capacity of computing units (CUs). In this paper, we propose CD-PIM to address these challenges through three key innovations. First, we introduce a high-bandwidth compute-efficient mode (HBCEM) that enhances bandwidth by dividing each bank into four pseudo-banks through segmented global bitlines. Second, we propose a low-batch interleaving mode (LBIM) to improve component utilization by overlapping GEMV operations with GEMM operations. Third, we design a compute-efficient CU that performs enhanced GEMV operations in a pipelined manner by serially feeding weight data into the computing core. Forth, we adopt a column-wise mapping for the key-cache matrix and row-wise mapping for the value-cache matrix, which fully utilizes CU resources. Our evaluation shows that compared to a GPU-only baseline and state-of-the-art PIM designs, our CD-PIM achieves 11.42x and 4.25x speedup on average within a single batch in HBCEM mode, respectively. Moreover, for low-batch sizes, the CD-PIM achieves an average speedup of 1.12x in LBIM compared to HBCEM.

cs.AR↗
arXiv2026

Dipion transitions from $X(3872)$ to $χ_{cJ}\ (J=0,1,2)$

In this work, we investigate the dipion transition processes $X(3872)\to ππχ_{cJ} (J=0,1,2)$ within the framework of heavy hadron chiral perturbation theory, treating $X(3872)$ as a molecular state composed of $D\bar{D}^*$+ H.c. components. By analyzing the box and triangle loop diagrams with the nonrelativistic effective field theory power-counting rule, we demonstrate that box diagrams dominate these dipion transition processes. Branching ratios are calculated as functions of the mixing angle $θ$, which parametrizes the neutral and charged meson compositions of the $X(3872)$. Our results indicate that the branching fractions for $X(3872)\toππχ_{c0}$, $X(3872)\to ππχ_{c1}$, and $X(3872)\to ππχ_{c2}$ are of the orders of $10^{-4}$, $10^{-3}$, and $10^{-5}$, respectively. We also predict the ratios ${\mathcal{B}[X(3872)\rightarrow ππχ_{c0/2}]}/{\mathcal{B}[X(3872)\rightarrow ππχ_{c1}]}$ and ${\mathcal{B}[X(3872)\rightarrow π^+π^-χ_{cJ}]}/{\mathcal{B}[X(3872)\rightarrow π^0π^0χ_{cJ}]}$. The latter deviates from isospin-symmetry expectations, revealing various degrees of isospin violation. By studying the $π^+π^-$ and $π^+χ_{cJ}$ invariant mass spectra, we find a double-bump structure in the $π^ + π^-$ invariant mass distributions of the process $X(3872)\to π^+π^-χ_{c1}$ and $π^+χ_{c0}$ invariant mass distribution of the process $X(3872)\to π^+π^-χ_{c0}$, which could be tested by future experimental measurements.

hep-ph↗
arXiv2026

SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation

Although learning-based vision-and-language navigation (VLN) agents can learn spatial knowledge implicitly from large-scale training data, zero-shot VLN agents lack this process, relying primarily on local observations for navigation, which leads to inefficient exploration and a significant performance gap. To deal with the problem, we consider a zero-shot VLN setting that agents are allowed to fully explore the environment before task execution. Then, we construct the Spatial Scene Graph (SSG) to explicitly capture global spatial structure and semantics in the explored environment. Based on the SSG, we introduce SpatialNav, a zero-shot VLN agent that integrates an agent-centric spatial map, a compass-aligned visual representation, and a remote object localization strategy for efficient navigation. Comprehensive experiments in both discrete and continuous environments demonstrate that SpatialNav significantly outperforms existing zero-shot agents and clearly narrows the gap with state-of-the-art learning-based methods. Such results highlight the importance of global spatial representations for generalizable navigation.

cs.CV↗
arXiv2026

A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems

Mixture-of-Experts (MoE) models facilitate edge deployment by decoupling model capacity from active computation, yet their large memory footprint drives the need for GPU systems with near-data processing (NDP) capabilities that offload experts to dedicated processing units. However, deploying MoE models on such edge-based GPU-NDP systems faces three critical challenges: 1) severe load imbalance across NDP units due to non-uniform expert selection and expert parallelism, 2) insufficient GPU utilization during expert computation within NDP units, and 3) extensive data pre-profiling necessitated by unpredictable expert activation patterns for pre-fetching. To address these challenges, this paper proposes an efficient inference framework featuring three key optimizations. First, the underexplored tensor parallelism in MoE inference is exploited to partition and compute large expert parameters across multiple NDP units simultaneously towards edge low-batch scenarios. Second, a load-balancing-aware scheduling algorithm distributes expert computations across NDP units and GPU to maximize resource utilization. Third, a dataset-free pre-fetching strategy proactively loads frequently accessed experts to minimize activation delays. Experimental results show that our framework enables GPU-NDP systems to achieve 2.41x on average and up to 2.56x speedup in end-to-end latency compared to state-of-the-art approaches, significantly enhancing MoE inference efficiency in resource-constrained environments.

cs.DC↗