arXiv subjects

Liang Xu

Publications and source records attributed to Liang Xu.

At least 37 records · Page 2Linked to original sources

arXiv2026

AR Forcing: Towards Long-Horizon Robot Navigation World Model

The diffusion based robot navigation world models are typically trained using parallel supervision, while autoregressive inference is employed during path planning. This results in a distribution shift between training and inference, which destabilizes the performance over long-horizon prediction. We propose AR Forcing, an autoregressive training strategy, which integrates the standard diffusion loss into the autoregressive training loop. At each step, the model uses its own predictions to update the context and optimize the single step noise prediction objective, thereby explicitly exposing the model to the inference state distribution during training. Our method does not require additional discriminators or distribution-matching losses, retains the original diffusion framework and sampler, and is easy to integrate. Experiments on multi-domain navigation datasets (RECON, SCAND, HuRoN, TartanDrive) show that compared with strong baselines, AR Forcing improved the consistency of generated images during long-horizon navigation and the accuracy of predicted trajectories, enhancing robustness of the model in complex known and unknown environments. We will release the code soon.

cs.RO↗

arXiv2026

G-DRAGON: Geospatial Reasoning and Dynamic Planning for Retrieval-Augmented Outdoor Navigation

Autonomous ground robots operating in large-scale outdoor environments require both robust long-range navigation and fine-grained ''last-mile'' exploration. Current advances in visual-language navigation (VLN) work well at short-range tasks, lacking geospatial grounding for long-distance missions. Some OpenStreetMap (OSM)-based methods relying on cloud-based Large Language Models (LLMs) are prone to factual hallucination and cannot conduct ''last-mile'' exploration based on human instruction. To address these challenges, we present G-DRAGON, a retrieval-augmented framework for outdoor, open-world navigation. This framework maps natural-language commands to versioned, local OSM entities via generative retrieval based on lightweight LLM, yielding accurate coordinates for global route planning. A high-level planning module bridges global topological routes with the SLAM system, projecting geospatial waypoints into the robot's navigable frame. For the ''last mile," the framework transitions to frontier-based exploration and open-set semantic voxel mapping to localize open-vocabulary targets. Experimental results in simulation demonstrate our framework outperforms state-of-the-art baselines. Furthermore, we validate the system in unseen real-world urban environments on an Unmanned Ground Vehicle (UGV), successfully completing person-search missions with trajectories of up to 500m.

cs.RO↗

arXiv2026

Robust One-step Speech Enhancement via Consistency Distillation

Diffusion models have shown strong performance in speech enhancement, but their real-time applicability has been limited by multi-step iterative sampling. Consistency distillation has recently emerged as a promising alternative by distilling a one-step consistency model from a multi-step diffusion-based teacher model. However, distilled consistency models are inherently biased towards the sampling trajectory of the teacher model, making them less robust to noise and prone to inheriting inaccuracies from the teacher model. To address this limitation, we propose ROSE-CD: Robust One-step Speech Enhancement via Consistency Distillation, a novel approach for distilling a one-step consistency model. Specifically, we introduce a randomized learning trajectory to improve the model's robustness to noise. Furthermore, we jointly optimize the one-step model with two time-domain auxiliary losses, enabling it to recover from teacher-induced errors and surpass the teacher model in overall performance. This is the first pure one-step consistency distillation model for diffusion-based speech enhancement, achieving 54 times faster inference speed and superior performance compared to its 30-step teacher model. Experiments on the VoiceBank-DEMAND dataset demonstrate that the proposed model achieves state-of-the-art performance in terms of speech quality. Moreover, its generalization ability is validated on both an out-of-domain dataset and real-world noisy recordings.

eess.AS↗

arXiv2026

Efficient Verification of Neural Control Barrier Functions with Smooth Nonlinear Activations

Formal verification of neural control barrier functions (NCBFs) remains challenging, especially for neural networks with nonlinear activations like $\tanh$. Existing CROWN-based methods rely on conservative linear relaxations for Jacobian bounds, limiting scalability. We propose LightCROWN, which computes tighter Jacobian bounds by exploiting the analytical properties of activation functions. Experiments on nonlinear control systems including the inverted pendulum, Dubins car, and planar quadrotor demonstrate that LightCROWN improves verification success rates up to 100\%, while enhancing speed and scalability. Our approach provides a generalizable improvement for CROWN-based frameworks, enabling more efficient verification of complex NCBFs. The code can be found at github.com/Autonomous-Systems-and-Control-Lab/verify-neural-CBF.

cs.LG↗

arXiv2026

ADEPT: An Entropy-Driven Dual-Strategy Agent for Interactive Video Retrieval

This research aims to solve the challenge of video retrieval from massive datasets, caused by ambiguous user queries. Prevailing single-round retrieval paradigms face a performance bottleneck, as they lack effective feedback mechanisms to handle complex search intentions. The root cause is the "Intent-Query Gap", where users' intent cannot be captured by a simple text query. To solve this, we propose the ADEPT framework: a training-free agent that pioneers an entropy-driven decision engine to efficiently guide dialogue by dynamically selecting between ASK and REFINE strategies. Experiments on two challenging datasets demonstrate that ADEPT significantly outperforms all non-interactive, heuristic, and Video-LLM baselines. The core contribution of this work is an efficient and interpretable entropy-driven interactive strategy that sets a new performance benchmark for the field of interactive video retrieval.

cs.IR↗

arXiv2026

PhysiGen: Integrating Collision-Aware Physical Constraints for High-Fidelity Human-Human Interaction Generation

Despite substantial progress in text-driven 3D human motion synthesis, generating realistic multi-person interaction sequences remains challenging. Notably, body inter-penetration is a pervasive issue from both data acquisition to the generated results, which significantly undermines the realism and usability. Previous generative models either ignored this issue or introduced computationally expensive mesh-level loss functions to alleviate inter-body collisions. In this paper, we propose a general-purpose and computationally efficient optimization strategy named PhysiGen to explicitly integrate collision-aware physical constraints for human-human interaction generation. Specifically, we simplify the high-resolution human body mesh into geometric primitives to greatly reduce the cost of inter-person collision detection. Moreover, we identify the collision regions as the guidance of the optimization directions. PhysiGen is plug-and-play and can be readily integrated into existing human interaction generation models. Extensive cross-dataset and cross-model experiments show that our method can effectively reduce interpenetration and significantly improve visual coherence and physical plausibility compared to the state-of-the-art methods.

cs.CV↗

arXiv2026

Cramér-Rao Bound Optimization for Near-Field ISAC with Extended Targets

Near-field integrated sensing and communication (ISAC) requires target models beyond the point-target abstraction when the target has a non-negligible spatial extent. In this letter, a geometry-aware transmit design is developed for a parametric extended target (ET) described by its center, orientation, and size under spherical-wave propagation. The CRB for the geometric parameters is formulated around a nominal ET state, an exact ET-aware reduced subspace is identified for the lifted covariance formulation, and a reduced-dimensional semidefinite relaxation (SDR) is developed under signal-to-interference-plus-noise ratio (SINR) and power constraints. Simulation results show lower CRB values than point-target and geometry-agnostic baselines together with substantially reduced runtime for large arrays.

eess.SP↗

arXiv2026

FeedbackSTS-Det: Sparse Frames-Based Spatio-Temporal Semantic Feedback Network for Moving Infrared Small Target Detection

Infrared small target detection (ISTD) has been a critical technology in defense and civilian applications over the past several decades, such as missile warning, maritime surveillance, and disaster monitoring. Nevertheless, moving infrared small target detection still faces considerable challenges: existing models suffer from insufficient spatio-temporal semantic correlation and are not lightweight-friendly, while algorithms with strong scene generalization capability are in great demand for real-world applications. To address these issues, we propose FeedbackSTS-Det, a sparse frames-based spatio-temporal semantic feedback network. Our approach introduces a closed-loop spatio-temporal semantic feedback strategy with paired forward and backward refinement modules that work cooperatively across the encoder and decoder to enhance information exchange between consecutive frames, effectively improving detection accuracy and reducing false alarms. Moreover, we introduce an embedded sparse semantic module (SSM), which operates by strategically grouping frames by interval, propagating semantics within each group, and reassembling the sequence to efficiently capture long-range temporal dependencies with low computational overhead. Extensive experiments on many widely adopted multi-frame infrared small target datasets demonstrate the generalization ability and scene adaptability of our proposed network. Code and models are available at: https://github.com/IDIP-Lab/FeedbackSTS-Det.

cs.CV↗

arXiv2026

Cooperative Control of Parallel Actuators for Linear Robust Output Regulation of Uncertain Linear Minimum-phase Plants

This paper investigates the robust output regulation problem for an uncertain linear minimum-phase plant with cooperative parallel operation of multiple actuators. Building on the internal model approach, we first propose a dynamic output feedback control law to solve the robust output regulation problem with a single actuator. Then, we construct a distributed dynamic output feedback control law that is nearly independent of the number of actuators and incorporates coupling terms to address the linear robust output regulation problem with cooperative parallel operation of multiple actuators over undirected communication networks. We reveal the connection in the design of parameters between the dynamic output feedback control law under single actuator operation and the distributed dynamic output feedback control law under cooperative parallel operation with multiple actuators. Moreover, we remove the existing assumption that the actuator dynamics must be Hurwitz stable, thereby enabling the incorporation of unstable actuators in our framework. Finally, two numerical examples are provided to validate the effectiveness of the proposed control laws.

eess.SY↗

arXiv2026

Emission-line Variable Active Galactic Nuclei at Cosmic Noon from HETDEX

We present the first statistical census of emission-line variable active galactic nuclei (EVA) at cosmic noon by combining untargeted and deep HETDEX spectroscopy with multi-epoch spectra from SDSS, DESI, and LAMOST. Anchoring all candidates to a HETDEX spectroscopic epoch and requiring AGN classification in either the HETDEX or the external epoch(s), we identify a homogeneous sample of 100 EVA at z~1.5, including 98 newly identified. Emission-line variability is selected primarily through statistically significant line-flux changes, supplemented by extensive visual inspections using contemporaneous photometric light curves. The resulting incidence fraction is $f_{\rm EVA} \approx 0.9\%$. The rest-frame intervals between spectroscopic epochs span $\sim$1--10 yr, with brightening and dimming events exhibiting statistically indistinguishable characteristic timescales ($ΔT\sim2.2$ and $\sim2.6$ yr, respectively). A key result is the characterization of the Baldwin effect in the time domain: while many EVA follow the ensemble Baldwin effect (eBeff) between two epochs, a substantial fraction exhibit apparent anti-eBeff responses. Time-resolved spectroscopy of an individual source reveals that the intrinsic EW--luminosity relation is non-stationary, with the line-to-continuum responsivity systematically evolving from stronger to weaker across successive variability cycles; sparse two-epoch sampling of this evolving intrinsic Baldwin evolution (iBeff) naturally produces both eBeff-like and anti-eBeff behaviors. Finally, EVA show no strong preference for extreme Eddington ratios but exhibit a mild tendency toward lower $λ_{\rm Edd}$ values relative to matched control samples, driven primarily by sources observed in their dim states. Together, these results establish a coherent framework for interpreting emission-line variability in AGN at the peak epoch of cosmic black hole growth.

astro-ph.GA↗

arXiv2026

From Geometric Mimicry to Comprehensive Generation: A Context-Informed Multimodal Diffusion Model for Urban Morphology Synthesis

Urban morphology is fundamental to determining urban functionality and vitality. Prevailing simulation methods, however, often oversimplify morphological generation as a geometric problem, lacking a profound understanding of urban semantics and geographical context. To address this limitation, this study proposes ControlCity, a diffusion model that achieves comprehensive urban morphology generation through multimodal information fusion. We first constructed a quadruple dataset comprising ``image-text-metadata-building footprints" from 22 cities worldwide. ControlCity utilizes these multidimensional information as joint control conditions, where an enhanced ControlNet architecture encodes spatial constraints from images, while text and metadata provide semantic guidance and geographical priors respectively, collectively directing the generation process. Experimental results demonstrate that compared to unimodal baselines, this method achieves significant advantages in morphological fidelity, with visual error (FID) reduced by 71.01%, reaching 50.94, and spatial overlap (MIoU) improved by 38.46%, reaching 0.36. Furthermore, the model demonstrates robust knowledge generalization and controllability, enabling cross-city style transfer and zero-shot generation for unknown cities. Ablation studies further reveal the distinct roles of images, text, and metadata in the generation process. This study confirms that multimodal fusion is crucial for achieving the transition from ``geometric mimicry" to ``understanding-based comprehensive generation," providing a novel paradigm for urban morphology research and applications.

cs.CV↗

arXiv2026

ISAC-Enabled Multi-UAV Collaborative Target Sensing for Low-Altitude Economy

Integrated sensing and communication (ISAC) has attracted growing research interests to facilitate the large-scale development of the low-altitude economy (LAE). However, the high dynamics of low-altitude targets may overwhelm fixed ISAC systems, particularly at the edge of their coverage or in blind zones. Driven by high flexibility, unmanned aerial vehicle (UAV)-assisted ISAC can provide more freedom of design to enhance communication and sensing abilities. In this paper, we propose an ISAC-enabled multi-UAV dynamic collaborative target sensing scheme, where UAVs can dynamically adjust their flight and resource allocation for cooperative sensing of mobile target through communicating with the terrestrial cellular network with ISAC signals. To achieve the precise sensing of the dynamic target, the posterior Cramer-Rao bound (PCRB) for the target state is derived. Subsequently, the PCRB minimization problem is formulated by jointly optimizing the UAV-BS association, UAVs' trajectories and bandwidth allocation, subject to the communication requirements for the UAVs. However, the problem is challenging since it involves non-convex and implicit objective function with coupled optimization variables. For a fast implementation of sensing and tracking, we propose a low-complexity iterative algorithm that can efficiently obtain a sub-optimal solution to the problem. Specifically, the UAV-BS association is first determined by the communication-optimal solution. Then the UAVs' trajectories and bandwidth allocation are alternatively optimized based on the descent direction search algorithm. Finally, numerical results are provided to validate the superiority of our proposed designs as compared to various benchmarks.

eess.SY↗

arXiv2026

PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation

Multimodal large language models (MLLMs) have advanced zero-shot end-to-end Vision-Language Navigation (VLN), yet robust navigation requires not only semantic understanding but also predictive modeling of environment dynamics and spatial structure. We propose PROSPECT, a unified streaming navigation agent that couples a streaming Vision-Language-Action (VLA) policy with latent predictive representation learning. PROSPECT uses CUT3R as a streaming 3D foundation spatial encoder to produce long-context, absolute-scale spatial features, and fuses them with SigLIP semantic features via cross-attention. During training, we introduce learnable stream query tokens that query the streaming context and predict next-step 2D and 3D latent features (rather than pixels or explicit modalities), supervised in the latent spaces of frozen SigLIP and CUT3R teachers. The predictive branch shapes internal representations without inference overhead. Experiments on VLN-CE benchmarks and real-robot deployment demonstrate state-of-the-art performance and improved long-horizon robustness under diverse lighting. We will release code for the community soon.

cs.CV↗

arXiv2026

A DMD-Based Adaptive Modulation Method for High Dynamic Range Imaging in High-Glare Environments

Background The accuracy of photomechanics measurements critically relies on image quality,particularly under extreme illumination conditions such as welding arc monitoring and polished metallic surface analysis. High dynamic range (HDR) imaging above 120 dB is essential in these contexts. Conventional CCD/CMOS sensors, with dynamic ranges typically below 70 dB, are highly susceptible to saturation under glare, resulting in irreversible loss of detail and significant errors in digital image correlation (DIC). Methods This paper presents an HDR imaging system that leverages the spatial modulation capability of a digital micromirror device (DMD). The system architecture enables autonomous regional segmentation and adaptive exposure control for high-dynamic-range scenes through an integrated framework comprising two synergistic subsystems: a DMD-based optical modulation unit and an adaptive computational imaging pipeline. Results The system achieves a measurable dynamic range of 127 dB, effectively eliminating satu ration artifacts under high glare. Experimental results demonstrate a 78% reduction in strain error and improved DIC positioning accuracy, confirming reliable performance across extreme intensity variations. Conclusion The DMD-based system provides high fidelity adaptive HDR imaging, overcoming key limitations of conventional sensors. It exhibits strong potential for optical metrology and stress analysis in high-glare environments where traditional methods are inadequate.

cs.CV↗

arXiv2026

Curvature-Guided Safety Filters: State-Dependent Hessian-Weighted Projection with Provable Performance Bounds

Safety filters provide a lightweight mechanism for enforcing state and input safety in learning-enabled control. However, common Euclidean projections onto the safe set disregard long-term performance, while directly optimizing the action-value function within the safe set can be nonconvex and computationally prohibitive. This paper proposes a state-dependent, Hessian-guided projection for safety filtering that preserves convexity while improving performance. The key idea is to select a weighted projection matrix from the curvature of the action-value function, thereby biasing the correction toward action directions with higher value sensitivity. We establish (i) a uniform bound on the performance gap between the weighted projection and the safe value-optimal action, and (ii) a condition under which the weighted projection outperforms the Euclidean projection in long-term value. To support black-box controllers, we further present a data-driven construction of the weighted projection matrix via an iterative Q-function learning algorithm with quadratic feature blocks and regularization that enforces curvature dominance and bounded higher-order terms. Simulations on a quadrotor tracking-and-avoidance task indicate that the proposed filter maintains safety while reducing value degradation relative to Euclidean projection, with computational overhead compatible with real-time operation.

eess.SY↗

arXiv2026

ReWorld: Multi-Dimensional Reward Modeling for Embodied World Models

Recently, video-based world models that learn to simulate the dynamics have gained increasing attention in robot learning. However, current approaches primarily emphasize visual generative quality while overlooking physical fidelity, dynamic consistency, and task logic, especially for contact-rich manipulation tasks, which limits their applicability to downstream tasks. To this end, we introduce ReWorld, a framework aimed to employ reinforcement learning to align the video-based embodied world models with physical realism, task completion capability, embodiment plausibility and visual quality. Specifically, we first construct a large-scale (~235K) video preference dataset and employ it to train a hierarchical reward model designed to capture multi-dimensional reward consistent with human preferences. We further propose a practical alignment algorithm that post-trains flow-based world models using this reward through a computationally efficient PPO-style algorithm. Comprehensive experiments and theoretical analysis demonstrate that ReWorld significantly improves the physical fidelity, logical coherence, embodiment and visual quality of generated rollouts, outperforming previous methods.

cs.RO↗

arXiv2026

Quantum tunnelling-integrated optoplasmonic nanotrap enables conductance visualisation of individual proteins

Biological electron transfer (ET) relies on quantum mechanical tunnelling through a dynamically folded protein. Yet, the spatiotemporal coupling between structural fluctuations and electron flux remains poorly understood, largely due to limitations in existing experimental techniques, such as ensemble averaging and non-physiological operating conditions. Here, we introduce a quantum tunnelling-integrated optoplasmonic nanotrap (QTOP-trap), an optoelectronic platform that combines plasmonic optical trapping with real-time quantum tunnelling measurements. This label-free approach enables single-molecule resolution of protein conductance in physiological electrolytes, achieving sub-3 nm spatial precision and 10-μs temporal resolution. By synchronising optoelectronic measurements, QTOP-trap resolves protein-specific conductance signatures and directly correlates tertiary structure dynamics with conductance using a "protein switch" strategy. This methodology establishes a universal framework for dissecting non-equilibrium ET mechanisms in individual conformational-active proteins, with broad implications for bioenergetics research and biomimetic quantum device design.

physics.bio-ph↗

arXiv2025

Trajectory Optimization for Unknown Maneuvering Target Tracking with Bearing-only Measurements

This paper studies trajectory optimization of an autonomous underwater vehicle (AUV) to track an unknown maneuvering target both in the 2D and 3D space. Due to the restrictions on sensing capabilities in the underwater scenario, the AUV is limited to collecting only bearing measurements to the target. A framework called {\it GP-based Bearing-only Tracking (GBT)} is proposed with integration of online learning and planning. First, a Gaussian process learning method is proposed for the AUV to handle unknown target motion, wherein pseudo linear transformation of bearing measurements is introduced to address nonlinearity of bearings. A probabilistic bearing-data-dependent bound on tracking error is then rigorously established. Based on it, optimal desired bearings that can reduce tracking uncertainty are obtained analytically. Finally, the trajectory optimization problem is formulated and transformed into an easily solved one with parametric transformation. Numerical examples and comparison with existing methods verify the feasibility and superior performance of our proposed framework.

eess.SY↗