arXiv subjects

Lei Yang

Publications and source records attributed to Lei Yang.

At least 163 records · Page 9Linked to original sources

arXiv2025

Collaborative Assembly Policy Learning of a Sightless Robot

This paper explores a physical human-robot collaboration (pHRC) task involving the joint insertion of a board into a frame by a sightless robot and a human operator. While admittance control is commonly used in pHRC tasks, it can be challenging to measure the force/torque applied by the human for accurate human intent estimation, limiting the robot's ability to assist in the collaborative task. Other methods that attempt to solve pHRC tasks using reinforcement learning (RL) are also unsuitable for the board-insertion task due to its safety constraints and sparse rewards. Therefore, we propose a novel RL approach that utilizes a human-designed admittance controller to facilitate more active robot behavior and reduce human effort. Through simulation and real-world experiments, we demonstrate that our approach outperforms admittance control in terms of success rate and task completion time. Additionally, we observed a significant reduction in measured force/torque when using our proposed approach compared to admittance control. The video of the experiments is available at https://youtu.be/va07Gw6YIog.

cs.RO↗

arXiv2025

CrossRay3D: Geometry and Distribution Guidance for Efficient Multimodal 3D Detection

The sparse cross-modality detector offers more advantages than its counterpart, the Bird's-Eye-View (BEV) detector, particularly in terms of adaptability for downstream tasks and computational cost savings. However, existing sparse detectors overlook the quality of token representation, leaving it with a sub-optimal foreground quality and limited performance. In this paper, we identify that the geometric structure preserved and the class distribution are the key to improving the performance of the sparse detector, and propose a Sparse Selector (SS). The core module of SS is Ray-Aware Supervision (RAS), which preserves rich geometric information during the training stage, and Class-Balanced Supervision, which adaptively reweights the salience of class semantics, ensuring that tokens associated with small objects are retained during token sampling. Thereby, outperforming other sparse multi-modal detectors in the representation of tokens. Additionally, we design Ray Positional Encoding (Ray PE) to address the distribution differences between the LiDAR modality and the image. Finally, we integrate the aforementioned module into an end-to-end sparse multi-modality detector, dubbed CrossRay3D. Experiments show that, on the challenging nuScenes benchmark, CrossRay3D achieves state-of-the-art performance with 72.4 mAP and 74.7 NDS, while running 1.84 faster than other leading methods. Moreover, CrossRay3D demonstrates strong robustness even in scenarios where LiDAR or camera data are partially or entirely missing.

cs.CV↗

arXiv2025

Diffusion Models are Efficient Data Generators for Human Mesh Recovery

Despite remarkable progress having been made on the problem of 3D human pose and shape estimation (HPS), current state-of-the-art methods rely heavily on either confined indoor mocap datasets or datasets generated by a rendering engine using computer graphics (CG). Both categories of datasets exhibit inadequacies in furnishing adequate human identities and authentic in-the-wild background scenes, which are crucial for accurately simulating real-world distributions. In this work, we show that synthetic data created by generative models is complementary to CG-rendered data for achieving remarkable generalization performance on diverse real-world scenes. We propose an effective data generation pipeline based on recent diffusion models, termed HumanWild, which can effortlessly generate human images and corresponding 3D mesh annotations. Specifically, we first collect a large-scale human-centric dataset with comprehensive annotations, e.g, text captions, the depth map, and surface normal images. To generate a wide variety of human images with initial labels, we train a customized, multi-condition ControlNet model. The key to this process is using a 3D parametric model, e.g, SMPL-X, to create various condition inputs easily. Our data generation pipeline is both flexible and customizable, making it adaptable to multiple real-world tasks, such as human interaction in complex scenes and humans captured by wide-angle lenses. By relying solely on generative models, we can produce large-scale, in-the-wild human images with high-quality annotations, significantly reducing the need for manual image collection and annotation. The generated dataset encompasses a wide range of viewpoints, environments, and human identities, ensuring its versatility across different scenarios. We hope that our work could pave the way for scaling up 3D human recovery to in-the-wild scenes.

cs.CV↗

arXiv2025

Highly efficient norm preserving numerical schemes for micromagnetic energy minimization based on SAV method

In this paper, two efficient and magnetization norm preserving numerical schemes based on the scalar auxiliary variable (SAV) method are developed for calculating the ground state in micromagnetic structures. The first SAV scheme is based on the original SAV method for the gradient flow model, while the second scheme features an updated scalar auxiliary variable to better align with the associated energy. To address the challenging constraint of pointwise constant magnetization length, an implicit projection method is designed, and verified by both SAV schemes. Both proposed SAV schemes partially preserve energy dissipation and exhibit exceptional efficiency, requiring two linear systems with constant coefficients to be solved. The computational efficiency is further enhanced by applying the Discrete Cosine Transform during the solving process. Numerical experiments demonstrate that our SAV schemes outperform commonly used numerical methods in terms of both efficiency and stability.

math.NA↗

arXiv2025

Diffusion-Based, Data-Assimilation-Enabled Super-Resolution of Hub-height Winds

High-quality observations of hub-height winds are valuable but sparse in space and time. Simulations are widely available on regular grids but are generally biased and too coarse to inform wind-farm siting or to assess extreme-weather-related risks (e.g., gusts) at infrastructure scales. To fully utilize both data types for generating high-quality, high-resolution hub-height wind speeds (tens to ~100m above ground), this study introduces WindSR, a diffusion model with data assimilation for super-resolution downscaling of hub-height winds. WindSR integrates sparse observational data with simulation fields during downscaling using state-of-the-art diffusion models. A dynamic-radius blending method is introduced to merge observations with simulations, providing conditioning for the diffusion process. Terrain information is incorporated during both training and inference to account for its role as a key driver of winds. Evaluated against convolutional-neural-network and generative-adversarial-network baselines, WindSR outperforms them in both downscaling efficiency and accuracy. Our data assimilation reduces WindSR's model bias by approximately 20% relative to independent observations.

cs.LG↗

arXiv2025

Outflow-cloud interaction as the possible origin of the peculiar radio emission in the tidal disruption event AT2018cqh

AT2018cqh is a unique optical tidal disruption event (TDE) discovered in a dwarf galaxy exhibiting delayed X-ray and radio flares. We present the results from high-resolution VLBA and e-MERLIN radio observations of AT2018cqh extending to $δ$t $\sim$ 2250 days post discovery, which reveal a compact radio emission, unresolved at a scale of <~ 0.13 pc at 7.6 GHz, with a high brightness temperature of $T_b$ ~> 4.03 $\times$ 10$^{9}$ K. The radio spectral energy distribution (SED) is found to gradually shift towards a higher peak flux density and frequency over a period of $\sim$1000 days. An equipartition analysis suggests that there is a little change in the radio emitting region over this period, while the electron density increases by a factor of 3. The radio light curve at 0.89 GHz continues to rise, with a bump feature lasting for 240 days. These properties are in contrast to the predictions of standard shockwave model from a diffuse circumnuclear medium, but could be explained if dense clouds exist in the circumnuclear environment. The latter scenario is supported by our hydrodynamic simulations of the interaction of TDE outflow with a cloud, which can reproduce the temporal evolution in the radio SED. This work highlights the importance of the outflow-cloud interaction in explaining the delayed, fast-rising radio emission observed in some TDEs, especially those occurring in galaxies with pre-existing AGN activity.

astro-ph.HE↗

arXiv2025

NeuVAS: Neural Implicit Surfaces for Variational Shape Modeling

Neural implicit shape representation has drawn significant attention in recent years due to its smoothness, differentiability, and topological flexibility. However, directly modeling the shape of a neural implicit surface, especially as the zero-level set of a neural signed distance function (SDF), with sparse geometric control is still a challenging task. Sparse input shape control typically includes 3D curve networks or, more generally, 3D curve sketches, which are unstructured and cannot be connected to form a curve network, and therefore more difficult to deal with. While 3D curve networks or curve sketches provide intuitive shape control, their sparsity and varied topology pose challenges in generating high-quality surfaces to meet such curve constraints. In this paper, we propose NeuVAS, a variational approach to shape modeling using neural implicit surfaces constrained under sparse input shape control, including unstructured 3D curve sketches as well as connected 3D curve networks. Specifically, we introduce a smoothness term based on a functional of surface curvatures to minimize shape variation of the zero-level set surface of a neural SDF. We also develop a new technique to faithfully model G0 sharp feature curves as specified in the input curve sketches. Comprehensive comparisons with the state-of-the-art methods demonstrate the significant advantages of our method.

cs.GR↗

arXiv2025

MeanSE: Efficient Generative Speech Enhancement with Mean Flows

Speech enhancement (SE) improves degraded speech's quality, with generative models like flow matching gaining attention for their outstanding perceptual quality. However, the flow-based model requires multiple numbers of function evaluations (NFEs) to achieve stable and satisfactory performance, leading to high computational load and poor 1-NFE performance. In this paper, we propose MeanSE, an efficient generative speech enhancement model using mean flows, which models the average velocity field to achieve high-quality 1-NFE enhancement. Experimental results demonstrate that our proposed MeanSE significantly outperforms the flow matching baseline with a single NFE, exhibiting extremely better out-of-domain generalization capabilities.

eess.AS↗

arXiv2025

CueGCL: Cluster-aware Personalized Self-Training for Unsupervised Graph Contrastive Learning

Recently, graph contrastive learning (GCL) has emerged as one of the optimal solutions for node-level and supervised tasks. However, for structure-related and unsupervised tasks such as graph clustering, current GCL algorithms face difficulties acquiring the necessary cluster-level information, resulting in poor performance. In addition, general unsupervised GCL improves the performance of downstream tasks by increasing the number of negative samples, which leads to severe class collision and unfairness of graph clustering. To address the above issues, we propose a Cluster-aware Graph Contrastive Learning Framework (CueGCL) to jointly learn clustering results and node representations. Specifically, we design a personalized self-training (PeST) strategy for unsupervised scenarios, which enables our model to capture precise cluster-level personalized information. With the benefit of the PeST, we alleviate class collision and unfairness without sacrificing the overall model performance. Furthermore, aligned graph clustering (AGC) is employed to obtain the cluster partition, where we align the clustering space of our downstream task with that in PeST to achieve more consistent node embeddings. Finally, we theoretically demonstrate the effectiveness of our model, showing it yields an embedding space with a significantly discernible cluster structure. Extensive experimental results also show our CueGCL exhibits state-of-the-art performance on five benchmark datasets with different scales.

cs.SI↗

arXiv2025

On the Design of Capacity-Achieving Distributions for Discrete-Time Poisson Channel with Low-Precision ADCs

This paper investigates the design of the capacity-achieving input distribution for the discrete-time Poisson channel (DTPC) under dark current effects with low-precision analog-to-digital converters (ADCs). This study introduces an efficient optimization algorithm that integrates the Newton-Raphson and Blahut-Arimoto (BA) methods to determine the capacity-achieving input distribution and the corresponding amplitudes of input mass points for the DTPC, subject to both peak and average power constraints. Additionally, the Karush-Kuhn-Tucker (KKT) conditions are established to provide necessary and sufficient conditions for the optimality of the obtained capacity-achieving distribution. Simulation results illustrate that the proposed algorithm attains $72\%$ and $83\%$ of the theoretical capacity at 5 dB for 1-bit and 2-bit quantized DTPC, respectively. Furthermore, for a finite-precision quantized DTPC (i.e., ${\log _2}K$ bits), the capacity can be achieved by a non-uniform discrete input distribution with support for $K$ mass points, under the given power constraints.

eess.SP↗

arXiv2025

AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving

While reasoning technology like Chain of Thought (CoT) has been widely adopted in Vision Language Action (VLA) models, it demonstrates promising capabilities in end to end autonomous driving. However, recent efforts to integrate CoT reasoning often fall short in simple scenarios, introducing unnecessary computational overhead without improving decision quality. To address this, we propose AdaThinkDrive, a novel VLA framework with a dual mode reasoning mechanism inspired by fast and slow thinking. First, our framework is pretrained on large scale autonomous driving (AD) scenarios using both question answering (QA) and trajectory datasets to acquire world knowledge and driving commonsense. During supervised fine tuning (SFT), we introduce a two mode dataset, fast answering (w/o CoT) and slow thinking (with CoT), enabling the model to distinguish between scenarios that require reasoning. Furthermore, an Adaptive Think Reward strategy is proposed in conjunction with the Group Relative Policy Optimization (GRPO), which rewards the model for selectively applying CoT by comparing trajectory quality across different reasoning modes. Extensive experiments on the Navsim benchmark show that AdaThinkDrive achieves a PDMS of 90.3, surpassing the best vision only baseline by 1.7 points. Moreover, ablations show that AdaThinkDrive surpasses both the never Think and always Think baselines, improving PDMS by 2.0 and 1.4, respectively. It also reduces inference time by 14% compared to the always Think baseline, demonstrating its ability to balance accuracy and efficiency through adaptive reasoning.

cs.CV↗

arXiv2025

Improving Muon Scattering Tomography Performance With A Muon Momentum Measurement Scheme

Muon imaging, especially muon scattering tomography (MST), has recently garnered significant attention. MST measures the magnitude of muon scattering angles inside an object, which depends not only on the material properties but also on the muon momentum. Due to the difficulty of simultaneous measurement of momentum, it was neglected and taken as a constant in multiple MST reconstruction algorithms. Recently, an experimental measurement scheme has emerged that is feasible in engineering, but it requires many layers of detectors to approach the true momentum. From this, we proposed both an algorithm to incorporating momentum into MST, and a scheme to determine the thresholds of Cherenkov detectors. This novel scheme, termed the "equi-percentage scheme", sets momentum thresholds for Cherenkov detector layers based on cosmic muon momentum distribution. Results showed our approach delivers noticeable enhancement in reconstructed image quality even with only two detector layers, reaching near-saturation performance with four layers. This study proves that momentum measurement significantly enhances short-duration MST, and that substantial improvement can be achieved with relatively coarse momentum measurement using 2-4 layers of Cherenkov detectors.

physics.ins-det↗

arXiv2025

Step-Audio 2 Technical Report

This paper presents Step-Audio 2, an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation. By integrating a latent audio encoder and reasoning-centric reinforcement learning (RL), Step-Audio 2 achieves promising performance in automatic speech recognition (ASR) and audio understanding. To facilitate genuine end-to-end speech conversation, Step-Audio 2 incorporates the generation of discrete audio tokens into language modeling, significantly enhancing its responsiveness to paralinguistic information such as speaking styles and emotions. To effectively leverage the rich textual and acoustic knowledge in real-world data, Step-Audio 2 integrates retrieval-augmented generation (RAG) and is able to call external tools such as web search to mitigate hallucination and audio search to switch timbres. Trained on millions of hours of speech and audio data, Step-Audio 2 delivers intelligence and expressiveness across diverse conversational scenarios. Evaluation results demonstrate that Step-Audio 2 achieves state-of-the-art performance on various audio understanding and conversational benchmarks compared to other open-source and commercial solutions. Please visit https://github.com/stepfun-ai/Step-Audio2 for more information.

cs.CL↗

arXiv2025

ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detection

In the field of 3D object detection tasks, fusing heterogeneous features from LiDAR and camera sensors into a unified Bird's Eye View (BEV) representation is a widely adopted paradigm. However, existing methods often suffer from imprecise sensor calibration, leading to feature misalignment in LiDAR-camera BEV fusion. Moreover, such inaccuracies cause errors in depth estimation for the camera branch, aggravating misalignment between LiDAR and camera BEV features. In this work, we propose a novel ContrastAlign approach that utilizes contrastive learning to enhance the alignment of heterogeneous modalities, thereby improving the robustness of the fusion process. Specifically, our approach comprises three key components: (1) the L-Instance module, which extracts LiDAR instance features within the LiDAR BEV features; (2) the C-Instance module, which predicts camera instance features through Region of Interest (RoI) pooling on the camera BEV features; (3) the InstanceFusion module, which employs contrastive learning to generate consistent instance features across heFterogeneous modalities. Subsequently, we use graph matching to calculate the similarity between the neighboring camera instance features and the similarity instance features to complete the alignment of instance features. Our method achieves SOTA performance, with an mAP of 71.5%, surpassing GraphBEV by 1.4% on the nuScenes val set. Importantly, our method excels BEVFusion under conditions with spatial & temporal misalignment noise, improving mAP by 1.4% and 11.1% on nuScenes dataset. Notably, on the Argoverse2 dataset, ContrastAlign outperforms GraphBEV by 1.0% in mAP, indicating that the farther the distance, the more severe the feature misalignment and the more effective.

cs.CV↗

arXiv2025

Progressive Bird's Eye View Perception for Safety-Critical Autonomous Driving: A Comprehensive Survey

Bird's-Eye-View (BEV) perception has become a foundational paradigm in autonomous driving, enabling unified spatial representations that support robust multi-sensor fusion and multi-agent collaboration. As autonomous vehicles transition from controlled environments to real-world deployment, ensuring the safety and reliability of BEV perception in complex scenarios - such as occlusions, adverse weather, and dynamic traffic - remains a critical challenge. This survey provides the first comprehensive review of BEV perception from a safety-critical perspective, systematically analyzing state-of-the-art frameworks and implementation strategies across three progressive stages: single-modality vehicle-side, multimodal vehicle-side, and multi-agent collaborative perception. Furthermore, we examine public datasets encompassing vehicle-side, roadside, and collaborative settings, evaluating their relevance to safety and robustness. We also identify key open-world challenges - including open-set recognition, large-scale unlabeled data, sensor degradation, and inter-agent communication latency - and outline future research directions, such as integration with end-to-end autonomous driving systems, embodied intelligence, and large language models.

cs.RO↗

arXiv2025

Landmark Guided Visual Feature Extractor for Visual Speech Recognition with Limited Resource

Visual speech recognition is a technique to identify spoken content in silent speech videos, which has raised significant attention in recent years. Advancements in data-driven deep learning methods have significantly improved both the speed and accuracy of recognition. However, these deep learning methods can be effected by visual disturbances, such as lightning conditions, skin texture and other user-specific features. Data-driven approaches could reduce the performance degradation caused by these visual disturbances using models pretrained on large-scale datasets. But these methods often require large amounts of training data and computational resources, making them costly. To reduce the influence of user-specific features and enhance performance with limited data, this paper proposed a landmark guided visual feature extractor. Facial landmarks are used as auxiliary information to aid in training the visual feature extractor. A spatio-temporal multi-graph convolutional network is designed to fully exploit the spatial locations and spatio-temporal features of facial landmarks. Additionally, a multi-level lip dynamic fusion framework is introduced to combine the spatio-temporal features of the landmarks with the visual features extracted from the raw video frames. Experimental results show that this approach performs well with limited data and also improves the model's accuracy on unseen speakers.

cs.CV↗

arXiv2025

Association between optically identified galaxy clusters and the underlying dark matter halos

Clusters of galaxies trace massive dark matter halos in the Universe, but they can include multiple halos projected along lines of sight. As a case study, we quantify the properties of halos contributing to clusters identified by the redMaPPer algorithm using the Cardinal simulation, which mimics the Dark Energy Survey data. For each cluster, we identify the halos hosting its member galaxies, and we define the main halo as the one contributing the most to the cluster's richness ($λ$, the estimated number of member galaxies). At $z=0.3$, for clusters with $λ> 60$, the main halo typically contributes to $92\%$ of the richness, and this fraction drops to $67\%$ for $λ\approx 20$. Defining "clean" clusters as those with $\geq50\%$ of the richness contributed by the main halo, we find that $100\%$ of the $λ> 60$ clusters are clean, while $73\%$ of the $λ\approx 20$ clusters are clean. Three halos can usually account for more than $80\%$ of the richness of a cluster. The main halos associated with redMaPPer clusters have a completeness ranging from $98\%$ at virial mass $10^{14.6}~h^{-1}M_{\odot}$ to $64\%$ at $10^{14}~h^{-1}M_{\odot}$. In addition, we compare the inferred cluster centers with true halo centers, finding that $30\%$ of the clusters are miscentered with a mean offset $40\%$ of the cluster radii, in agreement with recent X-ray studies. These systematics worsen as redshift increases, but we expect that upcoming surveys extending to longer wavelengths will improve the cluster finding at high redshifts. Our results affirm the robustness of the redMaPPer algorithm and provide a framework for benchmarking other cluster-finding strategies.

astro-ph.CO↗

arXiv2025

AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

We explore how scalable robot data can address real-world challenges for generalized robotic manipulation. Introducing AgiBot World, a large-scale platform comprising over 1 million trajectories across 217 tasks in five deployment scenarios, we achieve an order-of-magnitude increase in data scale compared to existing datasets. Accelerated by a standardized collection pipeline with human-in-the-loop verification, AgiBot World guarantees high-quality and diverse data distribution. It is extensible from grippers to dexterous hands and visuo-tactile sensors for fine-grained skill acquisition. Building on top of data, we introduce Genie Operator-1 (GO-1), a novel generalist policy that leverages latent action representations to maximize data utilization, demonstrating predictable performance scaling with increased data volume. Policies pre-trained on our dataset achieve an average performance improvement of 30% over those trained on Open X-Embodiment, both in in-domain and out-of-distribution scenarios. GO-1 exhibits exceptional capability in real-world dexterous and long-horizon tasks, achieving over 60% success rate on complex tasks and outperforming prior RDT approach by 32%. By open-sourcing the dataset, tools, and models, we aim to democratize access to large-scale, high-quality robot data, advancing the pursuit of scalable and general-purpose intelligence.

cs.RO↗