arXiv subjects

Tao Huang

Publications and source records attributed to Tao Huang.

At least 91 records · Page 5Linked to original sources

arXiv2026

A Mutual-Structure Weighted Sub-Pixel Multimodal Optical Remote Sensing Image Matching Method

Sub-pixel matching of multimodal optical images is a critical step in combined application of multiple sensors. However structural noise and inconsistencies arising from variations in multimodal image responses usually limit the accuracy of matching. Phase congruency mutual-structure weighted least absolute deviation (PCWLAD) is developed as a coarse-to-fine framework. In the coarse matching stage, we preserve the complete structure and use an enhanced cross-modal similarity criterion to mitigate structural information loss by PC noise filtering. In the fine matching stage, a mutual-structure filtering and weighted least absolute deviation-based is introduced to enhance inter-modal structural consistency and accurately estimate sub-pixel displacements adaptively. Experiments on three multimodal datasets-Landsat visible-infrared, short-range visible-near-infrared, and UAV optical image pairs demonstrate that PCWLAD consistently outperforms eight state-of-the-art methods, achieving an average matching accuracy of approximately 0.4 pixels. The software and datasets are publicly available at https://github.com/huangtaocsu/PCWLAD.

cs.CV↗

arXiv2026

ShadowGS: Shadow-Aware 3D Gaussian Splatting for Satellite Imagery

3D Gaussian Splatting (3DGS) has emerged as a novel paradigm for 3D reconstruction from satellite imagery. However, in multi-temporal satellite images, prevalent shadows exhibit significant inconsistencies due to varying illumination conditions. To address this, we propose ShadowGS, a novel framework based on 3DGS. It leverages a physics-based rendering equation from remote sensing, combined with an efficient ray marching technique, to precisely model geometrically consistent shadows while maintaining efficient rendering. Additionally, it effectively disentangles different illumination components and apparent attributes in the scene. Furthermore, we introduce a shadow consistency constraint that significantly enhances the geometric accuracy of 3D reconstruction. We also incorporate a novel shadow map prior to improve performance with sparse-view inputs. Extensive experiments demonstrate that ShadowGS outperforms current state-of-the-art methods in shadow decoupling accuracy, 3D reconstruction precision, and novel view synthesis quality, with only a few minutes of training. ShadowGS exhibits robust performance across various settings, including RGB, pansharpened, and sparse-view satellite inputs.

cs.CV↗

arXiv2025

Liquid Handling of the JUNO Experiment

The Filling, Overflow, and Circulation (FOC) system is a critical subsystem of the Jiangmen Underground Neutrino Observatory (JUNO), responsible for the safe handling of the Liquid Scintillator (LS) and water throughout the detector's commissioning and operational lifetime. This paper details the design and operation of the FOC system, which accomplished the filling of the world's largest LS detector--taking 45 days for water (6.4*10^4 m^3) and 200 days for LS (2.3*10^4 m^3). Throughout water filling, the liquid level difference between the Central Detector and Water Pool was rigorously maintained within safety limits. During LS filling, level control achieved +/-2 cm precision with flow regulation within +/-0.5% of setpoints. An automated control system based on Programmable Logic Controllers and the Experimental Physics and Industrial Control System framework ensured reliable operation. The system preserved LS radiopurity, maintaining 222Rn below 1 mBq/m^3 during filling and achieving 238U/232Th concentrations below 10^-16 g/g. The successful commissioning and operation of the FOC system have established it as an indispensable foundation for the stable long-term operation of the JUNO detector.

physics.ins-det↗

arXiv2025

GuangMing-Explorer: A Four-Legged Robot Platform for Autonomous Exploration in General Environments

Autonomous exploration is a fundamental capability that tightly integrates perception, planning, control, and motion execution. It plays a critical role in a wide range of applications, including indoor target search, mapping of extreme environments, resource exploration, etc. Despite significant progress in individual components, a holistic and practical description of a completely autonomous exploration system, encompassing both hardware and software, remains scarce. In this paper, we present GuangMing-Explorer, a fully integrated autonomous exploration platform designed for robust operation across diverse environments. We provide a comprehensive overview of the system architecture, including hardware design, software stack, algorithm deployment, and experimental configuration. Extensive real-world experiments demonstrate the platform's effectiveness and efficiency in executing autonomous exploration tasks, highlighting its potential for practical deployment in complex and unstructured environments.

cs.RO↗

arXiv2025

Learning to Control Physically-simulated 3D Characters via Generating and Mimicking 2D Motions

Video data is more cost-effective than motion capture data for learning 3D character motion controllers, yet synthesizing realistic and diverse behaviors directly from videos remains challenging. Previous approaches typically rely on off-the-shelf motion reconstruction techniques to obtain 3D trajectories for physics-based imitation. These reconstruction methods struggle with generalizability, as they either require 3D training data (potentially scarce) or fail to produce physically plausible poses, hindering their application to challenging scenarios like human-object interaction (HOI) or non-human characters. We tackle this challenge by introducing Mimic2DM, a novel motion imitation framework that learns the control policy directly and solely from widely available 2D keypoint trajectories extracted from videos. By minimizing the reprojection error, we train a general single-view 2D motion tracking policy capable of following arbitrary 2D reference motions in physics simulation, using only 2D motion data. The policy, when trained on diverse 2D motions captured from different or slightly different viewpoints, can further acquire 3D motion tracking capabilities by aggregating multiple views. Moreover, we develop a transformer-based autoregressive 2D motion generator and integrate it into a hierarchical control framework, where the generator produces high-quality 2D reference trajectories to guide the tracking policy. We show that the proposed approach is versatile and can effectively learn to synthesize physically plausible and diverse motions across a range of domains, including dancing, soccer dribbling, and animal movements, without any reliance on explicit 3D motion data. Project Website: https://jiann-li.github.io/mimic2dm/

cs.GR↗

arXiv2025

Affordance Field Intervention: Enabling VLAs to Escape Memory Traps in Robotic Manipulation

Vision-Language-Action (VLA) models have shown great performance in robotic manipulation by mapping visual observations and language instructions directly to actions. However, they remain brittle under distribution shifts: when test scenarios change, VLAs often reproduce memorized trajectories instead of adapting to the updated scene, which is a failure mode we refer to as the "Memory Trap". This limitation stems from the end-to-end design, which lacks explicit 3D spatial reasoning and prevents reliable identification of actionable regions in unfamiliar environments. To compensate for this missing spatial understanding, 3D Spatial Affordance Fields (SAFs) can provide a geometric representation that highlights where interactions are physically feasible, offering explicit cues about regions the robot should approach or avoid. We therefore introduce Affordance Field Intervention (AFI), a lightweight hybrid framework that uses SAFs as an on-demand plug-in to guide VLA behavior. Our system detects memory traps through proprioception, repositions the robot to recent high-affordance regions, and proposes affordance-driven waypoints that anchor VLA-generated actions. A SAF-based scorer then selects trajectories with the highest cumulative affordance. Extensive experiments demonstrate that our method achieves an average improvement of 23.5% across different VLA backbones ($π_{0}$ and $π_{0.5}$) under out-of-distribution scenarios on real-world robotic platforms, and 20.2% on the LIBERO-Pro benchmark, validating its effectiveness in enhancing VLA robustness to distribution shifts.

cs.RO↗

arXiv2025

AerialMind: Towards Referring Multi-Object Tracking in UAV Scenarios

Referring Multi-Object Tracking (RMOT) aims to achieve precise object detection and tracking through natural language instructions, representing a fundamental capability for intelligent robotic systems. However, current RMOT research remains mostly confined to ground-level scenarios, which constrains their ability to capture broad-scale scene contexts and perform comprehensive tracking and path planning. In contrast, Unmanned Aerial Vehicles (UAVs) leverage their expansive aerial perspectives and superior maneuverability to enable wide-area surveillance. Moreover, UAVs have emerged as critical platforms for Embodied Intelligence, which has given rise to an unprecedented demand for intelligent aerial systems capable of natural language interaction. To this end, we introduce AerialMind, the first large-scale RMOT benchmark in UAV scenarios, which aims to bridge this research gap. To facilitate its construction, we develop an innovative semi-automated collaborative agent-based labeling assistant (COALA) framework that significantly reduces labor costs while maintaining annotation quality. Furthermore, we propose HawkEyeTrack (HETrack), a novel method that collaboratively enhances vision-language representation learning and improves the perception of UAV scenarios. Comprehensive experiments validated the challenging nature of our dataset and the effectiveness of our method.

cs.RO↗

arXiv2025

Distilling Cross-Modal Knowledge via Feature Disentanglement

Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation, where inconsistencies in representation across modalities lead to difficult knowledge transfer. To address this challenge, we propose frequency-decoupled cross-modal knowledge distillation, a method designed to decouple and balance knowledge transfer across modalities by leveraging frequency-domain features. We observed that low-frequency features exhibit high consistency across different modalities, whereas high-frequency features demonstrate extremely low cross-modal similarity. Accordingly, we apply distinct losses to these features: enforcing strong alignment in the low-frequency domain and introducing relaxed alignment for high-frequency features. We also propose a scale consistency loss to address distributional shifts between modalities, and employ a shared classifier to unify feature spaces. Extensive experiments across multiple benchmark datasets show our method substantially outperforms traditional KD and state-of-the-art cross-modal KD approaches. Code is available at https://github.com/Johumliu/FD-CMKD.

cs.CV↗

arXiv2025

Quantum Vacuum Self-Consistency as the Dynamical Origin of Spacetime and Particle Physics

We propose a framework based on the postulate of quantum vacuum self-consistency, where classical backgrounds -- spacetime, gauge fields, and the Higgs condensate -- are macroscopic order parameters of a single quantum state, sustained by the vacuum expectation values of the fluctuations they support. Using a background-field, heat-kernel approach, we derive the coupled low-energy effective equations for the metric, gauge, and Higgs fields as vacuum equations of state. This recovers the Einstein, Yang--Mills, and Higgs equations, augmented by the higher-derivative operators required for quantum consistency, with all couplings running coherently under a single RG flow. The framework is embedded in a UV-complete theory of higher-derivative gravity (quantized with the fakeon prescription for unitarity) coupled to the Standard Model (SM). We assume the combined system flows to an asymptotically safe fixed point in the UV, rendering the theory predictive. A solvable O(N) model is used to explicitly demonstrate how the vacuum gap equations constrain both the condensate and curvature. The framework yields robust phenomenological predictions: (1) The loop-induced $R^2$ term drives Starobinsky-type inflation, with $n_s \simeq 1 - 2/N_e$ and $r \simeq 12/N_e^2$. (2) Short-distance corrections to gravity are quantified and satisfy laboratory bounds. (3) The speed of gravitational waves is luminal, consistent with GW170817. The combination of asymptotic safety with the vacuum gap equations correlates IR observables in gravity and particle physics, constraining SM parameters from the properties of the UV fixed point. The theory is testable across cosmology and precision gravity, reducing to General Relativity and the SM at low energies with controlled corrections.

physics.gen-ph↗

arXiv2025

ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better

Recent advances in multimodal reasoning models have demonstrated impressive capabilities across text and vision. However, even leading models exhibit redundant self-reflection when generating lengthy reasoning chains. While training-free CoT compression methods have emerged in the LLMs domain, they rely on static visual references and thus provide limited gains for multimodal reasoning. Therefore, we propose ChainV, a framework that dynamically integrates visual hints into the reasoning process, thereby making multimodal reasoning shorter and better. Specifically, ChainV first performs a coarse visual patch selection based on the previous reasoning step, then refines it by identifying the most representative atomic visual hint according to the averaged attention intensity. Additionally, ChainV introduces a consistency-based evaluation mechanism to assess the reliability of the chosen hint, guiding the model to adaptively adjust its level of self-reflection. Eventually, the pixel coordinates of the selected visual hint and its reliability are incorporated into thinking with a Bernoulli stochastic process. Experiments indicate that our method significantly improves reasoning accuracy and efficiency, especially on math-intensive benchmarks where visual hints are crucial for multi-step symbolic reasoning. For example, ChainV achieves $2.3\%$ improvement on the MathVista within MIMO-VL-RL, while reducing inference latency by $51.4\%$ and shortening output token length by $24.5\%$.

cs.CV↗

arXiv2025

Learning to Expand Images for Efficient Visual Autoregressive Modeling

Autoregressive models have recently shown great promise in visual generation by leveraging discrete token sequences akin to language modeling. However, existing approaches often suffer from inefficiency, either due to token-by-token decoding or the complexity of multi-scale representations. In this work, we introduce Expanding Autoregressive Representation (EAR), a novel generation paradigm that emulates the human visual system's center-outward perception pattern. EAR unfolds image tokens in a spiral order from the center and progressively expands outward, preserving spatial continuity and enabling efficient parallel decoding. To further enhance flexibility and speed, we propose a length-adaptive decoding strategy that dynamically adjusts the number of tokens predicted at each step. This biologically inspired design not only reduces computational cost but also improves generation quality by aligning the generation order with perceptual relevance. Extensive experiments on ImageNet demonstrate that EAR achieves state-of-the-art trade-offs between fidelity and efficiency on single-scale autoregressive models, setting a new direction for scalable and cognitively aligned autoregressive image generation.

cs.CV↗

arXiv2025

On the Viability of Weak Energy Condition Violation in Parity-Violating Electrodynamics

Exotic spacetimes often require violations of the weak energy condition (WEC), a feat that is difficult to achieve with realistic matter. We explore a conservative route to WEC violation within an effective field theory (EFT) by adding a single dimension-eight, parity-violating operator, proportional to $(F_{αβ}F^{αβ})(F_{γδ}\tilde F^{γδ})$, to the Maxwell action. We derive the modified Einstein and Maxwell equations and find that the electromagnetic stress--energy tensor is multiplied by a background-dependent factor $Ω=1+ζ\mathcal P$, where $\mathcal P\propto\vec E\cdot\vec B$. This allows, in principle, for WEC violation ($Ω<0$) when electric and magnetic fields are sufficiently aligned. Phenomenologically, the same operator induces vacuum birefringence. By comparing its predicted effect to laboratory (PVLAS) and astrophysical (magnetar X-ray polarimetry) data, we place stringent constraints on the coupling $ζ$. These constraints reveal that the threshold for WEC violation requires field strengths many orders of magnitude beyond any plausible astrophysical values and close to the EFT's breakdown scale. We also construct an exact flat-space solution at the $Ω=0$ threshold. We conclude that within this simple extension of electrodynamics, negative effective energy densities are mathematically possible but physically unreachable.

gr-qc↗

arXiv2025

ActVAR: Activating Mixtures of Weights and Tokens for Efficient Visual Autoregressive Generation

Visual Autoregressive (VAR) models enable efficient image generation via next-scale prediction but face escalating computational costs as sequence length grows. Existing static pruning methods degrade performance by permanently removing weights or tokens, disrupting pretrained dependencies. To address this, we propose ActVAR, a dynamic activation framework that introduces dual sparsity across model weights and token sequences to enhance efficiency without sacrificing capacity. ActVAR decomposes feedforward networks (FFNs) into lightweight expert sub-networks and employs a learnable router to dynamically select token-specific expert subsets based on content. Simultaneously, a gated token selector identifies high-update-potential tokens for computation while reconstructing unselected tokens to preserve global context and sequence alignment. Training employs a two-stage knowledge distillation strategy, where the original VAR model supervises the learning of routing and gating policies to align with pretrained knowledge. Experiments on the ImageNet $256\times 256$ benchmark demonstrate that ActVAR achieves up to $21.2\%$ FLOPs reduction with minimal performance degradation.

cs.CV↗

arXiv2025

Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models

Federated learning synchronizes models through gradient transmission and aggregation. However, these gradients pose significant privacy risks, as sensitive training data is embedded within them. Existing gradient inversion attacks suffer from significantly degraded reconstruction performance when gradients are perturbed by noise-a common defense mechanism. In this paper, we introduce gradient-guided conditional diffusion models for reconstructing private images from leaked gradients, without prior knowledge of the target data distribution. Our approach leverages the inherent denoising capability of diffusion models to circumvent the partial protection offered by noise perturbation, thereby improving attack performance under such defenses. We further provide a theoretical analysis of the reconstruction error bounds and the convergence properties of the attack loss, characterizing the impact of key factors-such as noise magnitude and attacked model architecture-on reconstruction quality. Extensive experiments demonstrate our attack's superior reconstruction performance with Gaussian noise-perturbed gradients, and confirm our theoretical findings.

cs.CR↗

arXiv2025

MS-Occ: Multi-Stage LiDAR-Camera Fusion for 3D Semantic Occupancy Prediction

Accurate 3D semantic occupancy perception is essential for autonomous driving in complex environments with diverse and irregular objects. While vision-centric methods suffer from geometric inaccuracies, LiDAR-based approaches often lack rich semantic information. To address these limitations, MS-Occ, a novel multi-stage LiDAR-camera fusion framework which includes middle-stage fusion and late-stage fusion, is proposed, integrating LiDAR's geometric fidelity with camera-based semantic richness via hierarchical cross-modal fusion. The framework introduces innovations at two critical stages: (1) In the middle-stage feature fusion, the Gaussian-Geo module leverages Gaussian kernel rendering on sparse LiDAR depth maps to enhance 2D image features with dense geometric priors, and the Semantic-Aware module enriches LiDAR voxels with semantic context via deformable cross-attention; (2) In the late-stage voxel fusion, the Adaptive Fusion (AF) module dynamically balances voxel features across modalities, while the High Classification Confidence Voxel Fusion (HCCVF) module resolves semantic inconsistencies using self-attention-based refinement. Experiments on two large-scale benchmarks demonstrate state-of-the-art performance. On nuScenes-OpenOccupancy, MS-Occ achieves an Intersection over Union (IoU) of 32.1% and a mean IoU (mIoU) of 25.3%, surpassing the state-of-the-art by +0.7% IoU and +2.4% mIoU. Furthermore, on the SemanticKITTI benchmark, our method achieves a new state-of-the-art mIoU of 24.08%, robustly validating its generalization capabilities.Ablation studies further confirm the effectiveness of each individual module, highlighting substantial improvements in the perception of small objects and reinforcing the practical value of MS-Occ for safety-critical autonomous driving scenarios.

cs.CV↗

arXiv2025

LoopExpose: An Unsupervised Framework for Arbitrary-Length Exposure Correction

Exposure correction is essential for enhancing image quality under challenging lighting conditions. While supervised learning has achieved significant progress in this area, it relies heavily on large-scale labeled datasets, which are difficult to obtain in practical scenarios. To address this limitation, we propose a pseudo label-based unsupervised method called LoopExpose for arbitrary-length exposure correction. A nested loop optimization strategy is proposed to address the exposure correction problem, where the correction model and pseudo-supervised information are jointly optimized in a two-level framework. Specifically, the upper-level trains a correction model using pseudo-labels generated through multi-exposure fusion at the lower level. A feedback mechanism is introduced where corrected images are fed back into the fusion process to refine the pseudo-labels, creating a self-reinforcing learning loop. Considering the dominant role of luminance calibration in exposure correction, a Luminance Ranking Loss is introduced to leverage the relative luminance ordering across the input sequence as a self-supervised constraint. Extensive experiments on different benchmark datasets demonstrate that LoopExpose achieves superior exposure correction and fusion performance, outperforming existing state-of-the-art unsupervised methods. Code is available at https://github.com/FALALAS/LoopExpose.

cs.CV↗

arXiv2025

VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching

Vision-Language-Action (VLA) models have demonstrated strong multi-modal reasoning capabilities, enabling direct action generation from visual perception and language instructions in an end-to-end manner. However, their substantial computational cost poses a challenge for real-time robotic control, where rapid decision-making is essential. This paper introduces VLA-Cache, a training-free inference acceleration method that reduces computational overhead by adaptively caching and reusing static visual tokens across frames. Exploiting the temporal continuity in robotic manipulation, VLA-Cache identifies minimally changed tokens between adjacent frames and reuses their cached key-value representations, thereby circumventing redundant computations. Additionally, to maintain action precision, VLA-Cache selectively re-computes task-relevant tokens that are environmentally sensitive, ensuring the fidelity of critical visual information. To further optimize efficiency, we introduce a layer adaptive token reusing strategy that dynamically adjusts the reuse ratio based on attention concentration across decoder layers, prioritizing critical tokens for recomputation. Extensive experiments on two simulation platforms (LIBERO and SIMPLER) and a real-world robotic system demonstrate that VLA-Cache achieves up to 1.7x speedup in CUDA latency and a 15% increase in control frequency, with negligible loss on task success rate. The code and videos can be found at our project page: https://vla-cache.github.io.

cs.RO↗

arXiv2025

From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance

Natural language offers a natural interface for humanoid robots, but existing language-guided humanoid locomotion pipelines remain cumbersome and untrustworthy. They typically decode human motion, retarget it to robot morphology, and then track it with a physics-based controller. However, this multi-stage process is prone to cumulative errors, introduces high latency, and yields weak coupling between semantics and control. These limitations call for a more direct pathway from language to action, one that eliminates fragile intermediate stages. Therefore, we present RoboGhost, a retargeting-free framework that directly conditions humanoid policies on language-grounded motion latents. By bypassing explicit motion decoding and retargeting, RoboGhost enables a diffusion-based policy to denoise executable actions directly from noise, preserving semantic intent and supporting fast, reactive control. A hybrid causal transformer-diffusion motion generator further ensures long-horizon consistency while maintaining stability and diversity, yielding rich latent representations for precise humanoid behavior. Extensive experiments demonstrate that RoboGhost substantially reduces deployment latency, improves success rates and tracking precision, and produces smooth, semantically aligned locomotion on real humanoids. Beyond text, the framework naturally extends to other modalities such as images, audio, and music, providing a universal foundation for vision-language-action humanoid systems.

cs.RO↗