arXiv subjects

Wei Liang

Publications and source records attributed to Wei Liang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Floor Plan-Guided Visual Navigation Incorporating Depth and Directional Cues

Current visual navigation strategies mainly follow an exploration-first and then goal-directed navigation paradigm. This exploratory phase inevitably compromises the overall efficiency of navigation. Recent studies propose leveraging floor plans alongside RGB inputs to guide agents, aiming for rapid navigation without prior exploration or mapping. Key issues persist despite early successes. The modal gap and content misalignment between floor plans and RGB images necessitate an efficient approach to extract the most salient and complementary features from both for reliable navigation. Here, we propose GlocDiff, a novel framework that employs a diffusion-based policy to continuously predict future waypoints. This policy is conditioned on two complementary information streams: (1) local depth cues derived from the current RGB observation, and (2) global directional guidance extracted from the floor plan. The former handles immediate navigation safety by capturing surrounding geometry, while the latter ensures goal-directed efficiency by offering definitive directional cues. Extensive evaluations on the FloNa benchmark demonstrate that GlocDiff achieves superior efficiency and effectiveness. Furthermore, its successful deployment in real-world scenarios underscores its strong potential for broad practical application.

cs.RO↗

arXiv2025

The Wiener Path Integral Interpretation of the 3:1 Combat Rule

The Wiener path integral framework is proposed to model military combat dynamics by incorporating the neglected stochastic effects to the Lanchester's square law. This framework is applied to evaluate the empirical 3:1 combat rule, which posits that an attacker requires a threefold force superiority to achieve victory. Specifically, the attacker's winning probability is computed utilizing a semi-analytical Rayleigh-Ritz method. Numerical results demonstrate that the validity of the rule critically depends on specific parameter regimes, primarily contingent upon the relative combat effectiveness ratio between the opposing forces and the tolerance for attrition. This work establishes a physics-informed theoretical bridge between statistical mechanics and military operations research for analyzing uncertain combat systems.

physics.soc-ph↗

arXiv2025

Human Motion Estimation with Everyday Wearables

While on-body device-based human motion estimation is crucial for applications such as XR interaction, existing methods often suffer from poor wearability, expensive hardware, and cumbersome calibration, which hinder their adoption in daily life. To address these challenges, we present EveryWear, a lightweight and practical human motion capture approach based entirely on everyday wearables: a smartphone, smartwatch, earbuds, and smart glasses equipped with one forward-facing and two downward-facing cameras, requiring no explicit calibration before use. We introduce Ego-Elec, a 9-hour real-world dataset covering 56 daily activities across 17 diverse indoor and outdoor environments, with ground-truth 3D annotations provided by the motion capture (MoCap), to facilitate robust research and benchmarking in this direction. Our approach employs a multimodal teacher-student framework that integrates visual cues from egocentric cameras with inertial signals from consumer devices. By training directly on real-world data rather than synthetic data, our model effectively eliminates the sim-to-real gap that constrains prior work. Experiments demonstrate that our method outperforms baseline models, validating its effectiveness for practical full-body motion estimation.

cs.CV↗

arXiv2025

The Least Action-Augmented Lanchester Model

The principle of least action, a fundamental principle in variational mechanics with broad applicability to classical physical systems, is employed to formulate a novel attrition model for combat dynamics. This formulation extends the Lanchester's square law through second-order temporal derivatives by requiring the resultant Euler-Lagrange equation to coincide with the classical Lanchester's equation. Initial conditions at a specified temporal point enable determination of subsequent system evolution through action minimization, while terminal boundary conditions permit backward reconstruction of combat trajectories. The model's validity is examined through historical analysis of WWII engagements: the Battle of Kursk and the Battle of Iwo Jima. Comparative studies with conventional Lanchester's square models demonstrate marked improvements in predictive accuracy regarding force strength progression, particularly in capturing non-linear attrition patterns characteristic of prolonged engagements.

physics.soc-ph↗

arXiv2025

RadarMP: Motion Perception for 4D mmWave Radar in Autonomous Driving

Accurate 3D scene motion perception significantly enhances the safety and reliability of an autonomous driving system. Benefiting from its all-weather operational capability and unique perceptual properties, 4D mmWave radar has emerged as an essential component in advanced autonomous driving. However, sparse and noisy radar points often lead to imprecise motion perception, leaving autonomous vehicles with limited sensing capabilities when optical sensors degrade under adverse weather conditions. In this paper, we propose RadarMP, a novel method for precise 3D scene motion perception using low-level radar echo signals from two consecutive frames. Unlike existing methods that separate radar target detection and motion estimation, RadarMP jointly models both tasks in a unified architecture, enabling consistent radar point cloud generation and pointwise 3D scene flow prediction. Tailored to radar characteristics, we design specialized self-supervised loss functions guided by Doppler shifts and echo intensity, effectively supervising spatial and motion consistency without explicit annotations. Extensive experiments on the public dataset demonstrate that RadarMP achieves reliable motion perception across diverse weather and illumination conditions, outperforming radar-based decoupled motion perception pipelines and enhancing perception capabilities for full-scenario autonomous driving systems.

cs.CV↗

arXiv2025

M^3Detection: Multi-Frame Multi-Level Feature Fusion for Multi-Modal 3D Object Detection with Camera and 4D Imaging Radar

Recent advances in 4D imaging radar have enabled robust perception in adverse weather, while camera sensors provide dense semantic information. Fusing the these complementary modalities has great potential for cost-effective 3D perception. However, most existing camera-radar fusion methods are limited to single-frame inputs, capturing only a partial view of the scene. The incomplete scene information, compounded by image degradation and 4D radar sparsity, hinders overall detection performance. In contrast, multi-frame fusion offers richer spatiotemporal information but faces two challenges: achieving robust and effective object feature fusion across frames and modalities, and mitigating the computational cost of redundant feature extraction. Consequently, we propose M^3Detection, a unified multi-frame 3D object detection framework that performs multi-level feature fusion on multi-modal data from camera and 4D imaging radar. Our framework leverages intermediate features from the baseline detector and employs the tracker to produce reference trajectories, improving computational efficiency and providing richer information for second-stage. In the second stage, we design a global-level inter-object feature aggregation module guided by radar information to align global features across candidate proposals and a local-level inter-grid feature aggregation module that expands local features along the reference trajectories to enhance fine-grained object representation. The aggregated features are then processed by a trajectory-level multi-frame spatiotemporal reasoning module to encode cross-frame interactions and enhance temporal representation. Extensive experiments on the VoD and TJ4DRadSet datasets demonstrate that M^3Detection achieves state-of-the-art 3D detection performance, validating its effectiveness in multi-frame detection with camera-4D imaging radar fusion.

cs.CV↗

arXiv2025

DogMo: A Large-Scale Multi-View RGB-D Dataset for 4D Canine Motion Recovery

We present DogMo, a large-scale multi-view RGB-D video dataset capturing diverse canine movements for the task of motion recovery from images. DogMo comprises 1.2k motion sequences collected from 10 unique dogs, offering rich variation in both motion and breed. It addresses key limitations of existing dog motion datasets, including the lack of multi-view and real 3D data, as well as limited scale and diversity. Leveraging DogMo, we establish four motion recovery benchmark settings that support systematic evaluation across monocular and multi-view, RGB and RGB-D inputs. To facilitate accurate motion recovery, we further introduce a three-stage, instance-specific optimization pipeline that fits the SMAL model to the motion sequences. Our method progressively refines body shape and pose through coarse alignment, dense correspondence supervision, and temporal regularization. Our dataset and method provide a principled foundation for advancing research in dog motion recovery and open up new directions at the intersection of computer vision, computer graphics, and animal behavior modeling.

cs.CV↗

arXiv2025

SFGFusion: Surface Fitting Guided 3D Object Detection with 4D Radar and Camera Fusion

3D object detection is essential for autonomous driving. As an emerging sensor, 4D imaging radar offers advantages as low cost, long-range detection, and accurate velocity measurement, making it highly suitable for object detection. However, its sparse point clouds and low resolution limit object geometric representation and hinder multi-modal fusion. In this study, we introduce SFGFusion, a novel camera-4D imaging radar detection network guided by surface fitting. By estimating quadratic surface parameters of objects from image and radar data, the explicit surface fitting model enhances spatial representation and cross-modal interaction, enabling more reliable prediction of fine-grained dense depth. The predicted depth serves two purposes: 1) in an image branch to guide the transformation of image features from perspective view (PV) to a unified bird's-eye view (BEV) for multi-modal fusion, improving spatial mapping accuracy; and 2) in a surface pseudo-point branch to generate dense pseudo-point cloud, mitigating the radar point sparsity. The original radar point cloud is also encoded in a separate radar branch. These two point cloud branches adopt a pillar-based method and subsequently transform the features into the BEV space. Finally, a standard 2D backbone and detection head are used to predict object labels and bounding boxes from BEV features. Experimental results show that SFGFusion effectively fuses camera and 4D radar features, achieving superior performance on the TJ4DRadSet and view-of-delft (VoD) object detection benchmarks.

cs.CV↗

arXiv2025

Heterogeneous Adversarial Play in Interactive Environments

Self-play constitutes a fundamental paradigm for autonomous skill acquisition, whereby agents iteratively enhance their capabilities through self-directed environmental exploration. Conventional self-play frameworks exploit agent symmetry within zero-sum competitive settings, yet this approach proves inadequate for open-ended learning scenarios characterized by inherent asymmetry. Human pedagogical systems exemplify asymmetric instructional frameworks wherein educators systematically construct challenges calibrated to individual learners' developmental trajectories. The principal challenge resides in operationalizing these asymmetric, adaptive pedagogical mechanisms within artificial systems capable of autonomously synthesizing appropriate curricula without predetermined task hierarchies. Here we present Heterogeneous Adversarial Play (HAP), an adversarial Automatic Curriculum Learning framework that formalizes teacher-student interactions as a minimax optimization wherein task-generating instructor and problem-solving learner co-evolve through adversarial dynamics. In contrast to prevailing ACL methodologies that employ static curricula or unidirectional task selection mechanisms, HAP establishes a bidirectional feedback system wherein instructors continuously recalibrate task complexity in response to real-time learner performance metrics. Experimental validation across multi-task learning domains demonstrates that our framework achieves performance parity with SOTA baselines while generating curricula that enhance learning efficacy in both artificial agents and human subjects.

cs.AI↗

arXiv2025

Learning Human-Humanoid Coordination for Collaborative Object Carrying

Human-humanoid collaboration shows significant promise for applications in healthcare, domestic assistance, and manufacturing. While compliant robot-human collaboration has been extensively developed for robotic arms, enabling compliant human-humanoid collaboration remains largely unexplored due to humanoids' complex whole-body dynamics. In this paper, we propose a proprioception-only reinforcement learning approach, COLA, that combines leader and follower behaviors within a single policy. The model is trained in a closed-loop environment with dynamic object interactions to predict object motion patterns and human intentions implicitly, enabling compliant collaboration to maintain load balance through coordinated trajectory planning. We evaluate our approach through comprehensive simulator and real-world experiments on collaborative carrying tasks, demonstrating the effectiveness, generalization, and robustness of our model across various terrains and objects. Simulation experiments demonstrate that our model reduces human effort by 24.7%. compared to baseline approaches while maintaining object stability. Real-world experiments validate robust collaborative carrying across different object types (boxes, desks, stretchers, etc.) and movement patterns (straight-line, turning, slope climbing). Human user studies with 23 participants confirm an average improvement of 27.4% compared to baseline models. Our method enables compliant human-humanoid collaborative carrying without requiring external sensors or complex interaction models, offering a practical solution for real-world deployment.

cs.RO↗

arXiv2025

Nonparametric Bounds in Causal Mediation Analysis in the Presence of Unmeasured Confounding and Imperfect Compliance

The average causal mediation effect (ACME) and the natural direct effect (NDE) are two parameters of primary interest in causal mediation analysis. However, the two causal parameters are not identifiable from randomized experimental data in the presence of outcome-mediator confounding and treatment-assignment noncompliance. Sjölander (2009) addressed the partial identification issue and derived nonparametric bounds of the NDE in randomized controlled trials under a set of monotonicity assumptions based on the Balke-Pearl algorithm. These bounds provide partial information on the parameters and can be used for sensitivity analysis. In this paper, we extend Sjölander's bounds on the NDE as well as the ACME to randomized controlled trials in the presence of noncompliance when the treatment assignment serves as an instrumental variable. Nonparametric sharp bounds for the local causal parameters defined on the subpopulation of treatment-assignment compliers are also established. We demonstrate the practical usefulness of the proposed upper and lower bounds through an application to the randomized experimental dataset on Job Search Intervention Study.

stat.ME↗

arXiv2025

CLONE: Closed-Loop Whole-Body Humanoid Teleoperation for Long-Horizon Tasks

Humanoid teleoperation plays a vital role in demonstrating and collecting data for complex humanoid-scene interactions. However, current teleoperation systems face critical limitations: they decouple upper- and lower-body control to maintain stability, restricting natural coordination, and operate open-loop without real-time position feedback, leading to accumulated drift. The fundamental challenge is achieving precise, coordinated whole-body teleoperation over extended durations while maintaining accurate global positioning. Here we show that an MoE-based teleoperation system, CLONE, with closed-loop error correction enables unprecedented whole-body teleoperation fidelity, maintaining minimal positional drift over long-range trajectories using only head and hand tracking from an MR headset. Unlike previous methods that either sacrifice coordination for stability or suffer from unbounded drift, CLONE learns diverse motion skills while preventing tracking error accumulation through real-time feedback, enabling complex coordinated movements such as ``picking up objects from the ground.'' These results establish a new milestone for whole-body humanoid teleoperation for long-horizon humanoid-scene interaction tasks.

cs.RO↗

arXiv2025

Spatial-Temporal Multi-Scale Quantization for Flexible Motion Generation

Despite significant advancements in human motion generation, current motion representations, typically formulated as discrete frame sequences, still face two critical limitations: (i) they fail to capture motion from a multi-scale perspective, limiting the capability in complex patterns modeling; (ii) they lack compositional flexibility, which is crucial for model's generalization in diverse generation tasks. To address these challenges, we introduce MSQ, a novel quantization method that compresses the motion sequence into multi-scale discrete tokens across spatial and temporal dimensions. MSQ employs distinct encoders to capture body parts at varying spatial granularities and temporally interpolates the encoded features into multiple scales before quantizing them into discrete tokens. Building on this representation, we establish a generative mask modeling model to effectively support motion editing, motion control, and conditional motion generation. Through quantitative and qualitative analysis, we show that our quantization method enables the seamless composition of motion tokens without requiring specialized design or re-training. Furthermore, extensive evaluations demonstrate that our approach outperforms existing baseline methods on various benchmarks.

cs.CV↗

arXiv2025

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation

Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus on grounding objects in static observations from 3D reconstruction, such as meshes and point clouds, but lack the ability to actively perceive and explore their environment. To address this limitation, we introduce \underline{\textbf{M}}ove \underline{\textbf{t}}o \underline{\textbf{U}}nderstand (\textbf{\model}), a unified framework that integrates active perception with \underline{\textbf{3D}} vision-language learning, enabling embodied agents to effectively explore and understand their environment. This is achieved by three key innovations: 1) Online query-based representation learning, enabling direct spatial memory construction from RGB-D frames, eliminating the need for explicit 3D reconstruction. 2) A unified objective for grounding and exploring, which represents unexplored locations as frontier queries and jointly optimizes object grounding and frontier selection. 3) End-to-end trajectory learning that combines \textbf{V}ision-\textbf{L}anguage-\textbf{E}xploration pre-training over a million diverse trajectories collected from both simulated and real-world RGB-D sequences. Extensive evaluations across various embodied navigation and question-answering benchmarks show that MTU3D outperforms state-of-the-art reinforcement learning and modular navigation approaches by 14\%, 23\%, 9\%, and 2\% in success rate on HM3D-OVON, GOAT-Bench, SG3D, and A-EQA, respectively. \model's versatility enables navigation using diverse input modalities, including categories, language descriptions, and reference images. These findings highlight the importance of bridging visual grounding and exploration for embodied intelligence.

cs.CV↗

arXiv2025

Exploring bottom-charmed molecular tetraquarks with the complex scaling method

In this work, we adopt the one-boson exchange model to analyze the $D^{(*)}_{(s)}B^{(*)}_{(s)}$ interactions from a coupled-channel perspective. For the $I(J^{P})=1(1^{+})$ $DB^{*}/D^*B/D^*B^{*}$ system, employing the complex scaling method, we obtain a loosely bound state and two resonant states located below the $DB^{*}$, $D^*B$, and $D^*B^{*}$ thresholds, respectively. Assuming that the charmonium-like states $T_{c\bar{c}1}(3900)$ and $T_{c\bar{c}1}(4020)$, as well as the bottomonium-like states $T_{b\bar{b}1}(10610)$ and $T_{b\bar{b}1}(10650)$, are molecular states near their respective thresholds, we suggest that the predicted states in the $I(J^P)=1(1^+)$ $D^{(*)}_{(s)}B^{(*)}_{(s)}$ system could be their bottom-charmed analogues. In addition, we extend our analysis to other $D^{(*)}_{(s)}B^{(*)}_{(s)}$ combinations with various quantum numbers. Our results suggest that some exotic structures may exist in the bottom-charmed sector. Finally, we collect the possible decay channels for future experimental observations. The $B_c/B_c^*$ plus a light meson are the ideal final state to search for the bound states, while the $D_{(s)}^{(*)}B_{(s)}^{(*)}$ channels are suitable for the resonances. We highly recommend that the future experiments hunt for these bottom-charmed exotic particles.

hep-ph↗

arXiv2025

ILT-Iterative LoRA Training through Focus-Feedback-Fix for Multilingual Speech Recognition

The deep integration of large language models and automatic speech recognition systems has become a promising research direction with high practical value. To address the overfitting issue commonly observed in Low-Rank Adaptation (LoRA) during the supervised fine-tuning (SFT) stage, this work proposes an innovative training paradigm Iterative LoRA Training (ILT) in combination with an Iterative Pseudo Labeling strategy, effectively enhancing the theoretical upper bound of model performance. Based on Whisper-large-v3 and Qwen2-Audio, we conduct systematic experiments using a three-stage training process: Focus Training, Feed Back Training, and Fix Training. Experimental results demonstrate the effectiveness of the proposed method. Furthermore, the MegaAIS research team applied this technique in the Interspeech 2025 Multilingual Conversational Speech Language Modeling Challenge (MLC-SLM), achieving 4th in Track 1 (Multilingual ASR Task) and 1st place in Track 2 (Speech Separation and Recognition Task), showcasing the practical feasibility and strong application potential of our approach.

cs.CL↗

arXiv2025

Towards Diverse and Efficient Audio Captioning via Diffusion Models

We introduce Diffusion-based Audio Captioning (DAC), a non-autoregressive diffusion model tailored for diverse and efficient audio captioning. Although existing captioning models relying on language backbones have achieved remarkable success in various captioning tasks, their insufficient performance in terms of generation speed and diversity impede progress in audio understanding and multimedia applications. Our diffusion-based framework offers unique advantages stemming from its inherent stochasticity and holistic context modeling in captioning. Through rigorous evaluation, we demonstrate that DAC not only achieves SOTA performance levels compared to existing benchmarks in the caption quality, but also significantly outperforms them in terms of generation speed and diversity. The success of DAC illustrates that text generation can also be seamlessly integrated with audio and visual generation tasks using a diffusion backbone, paving the way for a unified, audio-related generative model across different modalities.

cs.CL↗

arXiv2025

Estimation of Treatment Harm Rate via Partitioning

In causal inference with binary outcomes, there is a growing interest in estimation of treatment harm rate (THR), which is a measure of treatment risk and reveals treatment effect heterogeneity in a subpopulation. The THR is generally non-identifiable even for randomized controlled trials (RCTs), and existing works focus primarily on the estimation of the THR under either untestable identification or ambiguous model assumptions. We develop a class of partitioning-based bounds for the THR based on data from RCTs with two distinct features: Our proposed bounds effectively use available auxiliary covariates information and the bounds can be consistently estimated without relying on any untestable or ambiguous model assumptions. Finite sample performances of our proposed interval estimators along with a conservatively extended confidence interval for the THR are evaluated through Monte Carlo simulation studies. An application of the proposed methods to the ACTG 175 data is presented. A Python package named partbte for the partitioning-based algorithm has been developed and is available on https://github.com/w62liang/partition-te.

stat.ME↗