Wanting Xu

Xinyue Zhang, Liangzu Peng, Wanting Xu et al.

Branch-and-bound-based consensus maximization stands out due to its important ability of retrieving the globally optimal solution to outlier-affected geometric problems. However, while the discovery of such solutions caries high scientific value, its application in practical scenarios is often prohibited by its computational complexity growing exponentially as a function of the dimensionality of the problem at hand. In this work, we convey a novel, general technique that allows us to branch over an n-1 dimensional space for an n-dimensional problem. The remaining degree of freedom can be solved globally optimally within each bound calculation by applying the efficient interval stabbing technique. While each individual bound derivation is harder to compute owing to the additional need for solving a sorting problem, the reduced number of intervals and tighter bounds in practice lead to a significant reduction in the overall number of required iterations. Besides an abstract introduction of the approach, we present applications to four fundamental geometric computer vision problems: camera resectioning, relative camera pose estimation, point set registration, and rotation and focal length estimation. Through our exhaustive tests, we demonstrate significant speed-up factors at times exceeding two orders of magnitude, thereby increasing the viability of globally optimal consensus maximizers in online application scenarios.

Tianle Zhang, Zhihao Yuan, Dafeng Chi et al.

Robotic autonomy in open-world environments is fundamentally limited by insufficient data diversity and poor cross-embodiment generalization. Existing robotic datasets are often limited in scale and task coverage, while relatively large differences across robot embodiments impede effective behavior knowledge transfer. To address these challenges, we propose JoyAI-RA, a vision-language-action (VLA) embodied foundation model tailored for generalizable robotic manipulation. JoyAI-RA presents a multi-source multi-level pretraining framework that integrates web data, large-scale egocentric human manipulation videos, simulation-generated trajectories, and real-robot data. Through training on heterogeneous multi-source data with explicit action-space unification, JoyAI-RA effectively bridges embodiment gaps, particularly between human manipulation and robotic control, thereby enhancing cross-embodiment behavior learning. JoyAI-RA outperforms state-of-the-art methods in both simulation and real-world benchmarks, especially on diverse tasks with generalization demands.

Jiaxin Liu, Min Li, Wanting Xu et al.

Accurate state estimation for flexible robotic systems poses significant challenges, particularly for platforms with dynamically deforming structures that invalidate rigid-body assumptions. This paper addresses this problem and enables the extension of existing rigid-body pose estimation methods to non-rigid systems. Our approach integrates two core components: first, we capture elastic properties using a deformation-force model, efficiently learned via a Multi-Layer Perceptron; second, we resolve the platform's inherently smooth motion using continuous-time B-spline kinematic models. By continuously applying Newton's Second Law, our method formulates the relationship between visually-derived trajectory acceleration and predicted deformation-induced acceleration. We demonstrate that our approach not only enables robust and accurate pose estimation on non-rigid platforms, but also shows that the properly modeled platform physics allow for the recovery of inertial sensing properties. We validate this feasibility on a simple spring-camera system, showing how it robustly resolves the typically ill-posed problem of metric scale and gravity recovery in monocular visual odometry.

Chen Zhou, Haoran Sun, Hedan Yang et al.

Embodied intelligence is a key step towards Artificial General Intelligence (AGI), yet its development faces multiple challenges including data, frameworks, infrastructure, and evaluation systems. To address these issues, we have, for the first time in the industry, launched a cloud-based, thousand-GPU distributed training platform for embodied intelligence, built upon the widely adopted LeRobot framework, and have systematically overcome bottlenecks across the entire pipeline. At the data layer, we have restructured the data pipeline to optimize the flow of embodied training data. In terms of training, for the GR00T-N1.5 model, utilizing thousand-GPU clusters and data at the scale of hundreds of millions, the single-round training time has been reduced from 15 hours to just 22 minutes, achieving a 40-fold speedup. At the model layer, by combining variable-length FlashAttention and Data Packing, we have moved from sample redundancy to sequence integration, resulting in a 188% speed increase; π-0.5 attention optimization has accelerated training by 165%; and FP8 quantization has delivered a 140% speedup. On the infrastructure side, relying on high-performance storage, a 3.2T RDMA network, and a Ray-driven elastic AI data lake, we have achieved deep synergy among data, storage, communication, and computation. We have also built an end-to-end evaluation system, creating a closed loop from training to simulation to assessment. This framework has already been fully validated on thousand-GPU clusters, laying a crucial technical foundation for the development and application of next-generation autonomous intelligent robots, and is expected to accelerate the arrival of the era of human-machine integration.

Zhong Guan, Haoran Sun, Yongjian Guo et al.

In recent years, Vision-Language-Action (VLA) models have emerged as a crucial pathway towards general embodied intelligence, yet their training efficiency has become a key bottleneck. Although existing reinforcement learning (RL)-based training frameworks like RLinf can enhance model generalization, they still rely on synchronous execution, leading to severe resource underutilization and throughput limitations during environment interaction, policy generation (rollout), and model update phases (actor). To overcome this challenge, this paper, for the first time, proposes and implements a fully-asynchronous policy training framework encompassing the entire pipeline from environment interaction, rollout generation, to actor policy updates. Systematically drawing inspiration from asynchronous optimization ideas in large model RL, our framework designs a multi-level decoupled architecture. This includes asynchronous parallelization of environment interaction and trajectory collection, streaming execution for policy generation, and decoupled scheduling for training updates. We validated the effectiveness of our method across diverse VLA models and environments. On the LIBERO benchmark, the framework achieves throughput improvements of up to 59.25\% compared to existing synchronous strategies. When deeply optimizing separation strategies, throughput can be increased by as much as 126.67\%. We verified the effectiveness of each asynchronous component via ablation studies. Scaling law validation across 8 to 256 GPUs demonstrates our method's excellent scalability under most conditions.

Yucheng Guo, Yongjian Guo, Zhong Guan et al.

In video generation models, particularly world models, training large-scale video diffusion Transformers (such as DiT and MMDiT) poses significant computational challenges due to the extreme variance in sequence lengths within mixed-mode datasets. Existing bucket-based data loading strategies typically rely on "equal token length" constraints. This approach fails to account for the quadratic complexity of self-attention mechanisms, leading to severe load imbalance and underutilization of GPU resources. This paper proposes \textit{AdaptiveLoad}, an integrated optimization framework consisting of two core components: (1) A dual-constraint adaptive load balancing system, which eliminates long-sequence bottlenecks by simultaneously limiting memory consumption and computational load ($B \times S^p \le M_{\text{comp}}$); (2) A fused LayerNorm-Modulate CUDA kernel, which utilizes a D-tile coalesced reduction strategy to increase throughput and alleviate memory pressure. Experimental results on the Wan 2.1 world model demonstrate that our method reduces the computational imbalance rate from 39\% to 18.9\%, improves peak VRAM utilization efficiency by 22.7\%, and achieves an overall training throughput increase of 27.2\%.

Wanting Xu, Yang Liu, Langping He et al.

We introduce Xmodel-VLM, a cutting-edge multimodal vision language model. It is designed for efficient deployment on consumer GPU servers. Our work directly confronts a pivotal industry issue by grappling with the prohibitive service costs that hinder the broad adoption of large-scale multimodal systems. Through rigorous training, we have developed a 1B-scale language model from the ground up, employing the LLaVA paradigm for modal alignment. The result, which we call Xmodel-VLM, is a lightweight yet powerful multimodal vision language model. Extensive testing across numerous classic multimodal benchmarks has revealed that despite its smaller size and faster execution, Xmodel-VLM delivers performance comparable to that of larger models. Our model checkpoints and code are publicly available on GitHub at https://github.com/XiaoduoAILab/XmodelVLM.

Wanting Xu, Si'ao Zhang, Li Cui et al.

Despite the promise of superior performance under challenging conditions, event-based motion estimation remains a hard problem owing to the difficulty of extracting and tracking stable features from event streams. In order to robustify the estimation, it is generally believed that fusion with other sensors is a requirement. In this work, we demonstrate reliable, purely event-based visual odometry on planar ground vehicles by employing the constrained non-holonomic motion model of Ackermann steering platforms. We extend single feature n-linearities for regular frame-based cameras to the case of quasi time-continuous event-tracks, and achieve a polynomial form via variable degree Taylor expansions. Robust averaging over multiple event tracks is simply achieved via histogram voting. As demonstrated on both simulated and real data, our algorithm achieves accurate and robust estimates of the vehicle's instantaneous rotational velocity, and thus results that are comparable to the delta rotations obtained by frame-based sensors under normal conditions. We furthermore significantly outperform the more traditional alternatives in challenging illumination scenarios. The code is available at \url{https://github.com/gowanting/NHEVO}.

Wanting Xu, Xin Peng, Laurent Kneip

Traditional visual-inertial state estimation targets absolute camera poses and spatial landmark locations while first-order kinematics are typically resolved as an implicitly estimated sub-state. However, this poses a risk in velocity-based control scenarios, as the quality of the estimation of kinematics depends on the stability of absolute camera and landmark coordinates estimation. To address this issue, we propose a novel solution to tight visual-inertial fusion directly at the level of first-order kinematics by employing a dynamic vision sensor instead of a normal camera. More specifically, we leverage trifocal tensor geometry to establish an incidence relation that directly depends on events and camera velocity, and demonstrate how velocity estimates in highly dynamic situations can be obtained over short time intervals. Noise and outliers are dealt with using a nested two-layer RANSAC scheme. Additionally, smooth velocity signals are obtained from a tight fusion with pre-integrated inertial signals using a sliding window optimizer. Experiments on both simulated and real data demonstrate that the proposed tight event-inertial fusion leads to continuous and reliable velocity estimation in highly dynamic scenarios independently of absolute coordinates. Furthermore, in extreme cases, it achieves more stable and more accurate estimation of kinematics than traditional, point-position-based visual-inertial odometry.

Xinyue Zhang, Zijia Dai, Wanting Xu et al.

While automatically generated polynomial elimination templates have sparked great progress in the field of 3D computer vision, there remain many problems for which the degree of the constraints or the number of unknowns leads to intractability. In recent years, homotopy continuation has been introduced as a plausible alternative. However, the method currently depends on expensive parallel tracking of all possible solutions in the complex domain, or a classification network for starting problem-solution pairs trained over a limited set of real-world examples. Our innovation lies in a novel approach to finding solution-problem pairs, where we only need to predict a rough initial solution, with the corresponding problem generated by an online simulator. Subsequently, homotopy continuation is applied to track that single solution back to the original problem. We apply this elegant combination to generalized camera resectioning, and also introduce a new solution to the challenging generalized relative pose and scale problem. As demonstrated, the proposed method successfully compensates the raw error committed by the regressor alone, and leads to state-of-the-art efficiency and success rates.

Wanting Xu, Lan Hu, Manolis C. Tsakiris et al.

Over the past decade, the Gröbner basis theory and automatic solver generation have lead to a large number of solutions to geometric vision problems. In practically all cases, the derived solvers apply a fixed elimination template to calculate the Gröbner basis and thereby identify the zero-dimensional variety of the original polynomial constraints. However, it is clear that different variable or monomial orderings lead to different elimination templates, and we show that they may present a large variability in accuracy for a certain instance of a problem. The present paper has two contributions. We first show that for a common class of problems in geometric vision, variable reordering simply translates into a permutation of the columns of the initial coefficient matrix, and that -- as a result -- one and the same elimination template can be reused in different ways, each one leading to potentially different accuracy. We then prove that the original set of coefficients may contain sufficient information to train a classifier for online selection of a good solver, most notably at the cost of only a small computational overhead. We demonstrate wide applicability at the hand of generic dense polynomial problem solvers, as well as a concrete solver from geometric vision.

Yi-Fan Zuo, Wanting Xu, Xia Wang et al.

Vision-based localization is a cost-effective and thus attractive solution for many intelligent mobile platforms. However, its accuracy and especially robustness still suffer from low illumination conditions, illumination changes, and aggressive motion. Event-based cameras are bio-inspired visual sensors that perform well in HDR conditions and have high temporal resolution, and thus provide an interesting alternative in such challenging scenarios. While purely event-based solutions currently do not yet produce satisfying mapping results, the present work demonstrates the feasibility of purely event-based tracking if an alternative sensor is permitted for mapping. The method relies on geometric 3D-2D registration of semi-dense maps and events, and achieves highly reliable and accurate cross-modal tracking results. Practically relevant scenarios are given by depth camera-supported tracking or map-based localization with a semi-dense map prior created by a regular image-based visual SLAM or structure-from-motion system. Conventional edge-based 3D-2D alignment is extended by a novel polarity-aware registration that makes use of signed time-surface maps (STSM) obtained from event streams. We furthermore introduce a novel culling strategy for occluded points. Both modifications increase the speed of the tracker and its robustness against occlusions or large view-point variations. The approach is validated on many real datasets covering the above-mentioned challenging conditions, and compared against similar solutions realised with regular cameras.

Lan Hu, Wanting Xu, Kun Huang et al.

In an effort to increase the capabilities of SLAM systems and produce object-level representations, the community increasingly investigates the imposition of higher-level priors into the estimation process. One such example is given by employing object detectors to load and register full CAD models. Our work extends this idea to environments with unknown objects and imposes object priors by employing modern class-specific neural networks to generate complete model geometry proposals. The difficulty of using such predictions in a real SLAM scenario is that the prediction performance depends on the view-point and measurement quality, with even small changes of the input data sometimes leading to a large variability in the network output. We propose a discrete selection strategy that finds the best among multiple proposals from different registered views by re-enforcing the agreement with the online depth measurements. The result is an effective object-level RGBD SLAM system that produces compact, high-fidelity, and dense 3D maps with semantic annotations. It outperforms traditional fusion strategies in terms of map completeness and resilience against degrading measurement quality.