Publications (66)
DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving
Chenxu Dang, Sining Ang, Yongkang Li +7
Vision-Language-Action (VLA) models for autonomous driving increasingly adopt generative planners trained with imitation learning followed by reinforcement learning. Diffusion-base…
Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation
Hong Chen, Daqi Liu, Zehan Zhang +10
Existing world model-based planners for visual navigation typically follow a verification-centric paradigm, decoupling goal intent from trajectory synthesis. This approach suffers…
Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning
Xiangxiang Chu, Hangjun Ye
Deep reinforcement learning for multi-agent cooperation and competition has been a hot topic recently. This paper focuses on cooperative multi-agent problem based on actor-critic m…
DSBench: A Comprehensive Benchmark for Evaluating External and In-Cabin Risks
Xianhui Meng, Yuchen Zhang, Zhijian Huang +12
Vision-Language Models (VLMs) show great promise for autonomous driving, but their suitability for safety-critical scenarios is largely unexplored, raising safety concerns. This is…
The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms
Lingdong Kong, Shaoyuan Xie, Zeying Gong +135
Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under…
SEF-MAP: Subspace-Decomposed Expert Fusion for Robust Multimodal HD Map Prediction
Haoxiang Fu, Lingfeng Zhang, Hao Li +7
High-definition (HD) maps are essential for autonomous driving, yet multi-modal fusion often suffers from inconsistency between camera and LiDAR modalities, leading to performance…
MindDrive: A Vision-Language-Action Model for Autonomous Driving via Online Reinforcement Learning
Haoyu Fu, Diankun Zhang, Zongchuang Zhao +7
Current Vision-Language-Action (VLA) paradigms in autonomous driving primarily rely on Imitation Learning (IL), which introduces inherent challenges such as distribution shift and…
Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation
Jinkun Liu, Haohan Chi, Lingfeng Zhang +6
Long-horizon robotic manipulation requires plans that are both logically coherent and geometrically grounded. Existing Vision-Language-Action policies usually hide planning in late…
RoboAfford++: A Generative AI-Enhanced Dataset for Multimodal Affordance Learning in Robotic Manipulation and Navigation
Xiaoshuai Hao, Yingbo Tang, Lingfeng Zhang +6
Robotic manipulation and navigation are fundamental capabilities of embodied intelligence, enabling effective robot interactions with the physical world. Achieving these capabiliti…
Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
Xiaomi Robotics Team, Jun Guo, Piaopiao Jin +31
We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse language instructions to perform a wide range of mobile manipulatio…
CausalDrive: Real-time Causal World Models for Autonomous Driving
Tianyi Yan, Huan Zheng, Dubing Chen +10
World models have emerged as a promising paradigm for scaling autonomous driving (AD) data, yet existing video generative models fall short as interactive simulators. Layout-condit…
OneVLA: A Unified Framework for Embodied Tasks
Lingfeng Zhang, Xiaoshuai Hao, Yingbo Tang +10
Navigation and manipulation are fundamental capabilities of embodied intelligence, enabling robots to interpret natural language commands and interact physically with their surroun…
VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving
Jie Wang, Guang Li, Zhijian Huang +4
The significance of cross-view 3D geometric modeling capabilities for autonomous driving is self-evident, yet existing Vision-Language Models (VLMs) inherently lack this capability…
Toward Physically Consistent Driving Video World Models under Challenging Trajectories
Jiawei Zhou, Zhenxin Zhu, Lingyi Du +10
Video generation models have shown strong potential as world models for autonomous driving simulation. However, existing approaches are primarily trained on real-world driving data…
ReWorld: Learning Better Representations for World Action Models
Tianze Xia, Lijun Zhou, Kaixin Xiong +9
World Action Models (WAMs) model future environment evolution under action conditioning, offering a scalable paradigm for autonomous driving. However, existing approaches focus lar…
MiMo-Embodied: X-Embodied Foundation Model Technical Report
Xiaoshuai Hao, Lei Zhou, Zhijian Huang +41
We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied A…
TrajMoE: Scene-Adaptive Trajectory Planning with Mixture of Experts and Reinforcement Learning
Zebin Xing, Pengxuan Yang, Linbo Wang +12
Current autonomous driving systems often favor end-to-end frameworks, which take sensor inputs like images and learn to map them into trajectory space via neural networks. Previous…
PerlAD: Towards Enhanced Closed-loop End-to-end Autonomous Driving with Pseudo-simulation-based Reinforcement Learning
Yinfeng Gao, Qichao Zhang, Deqing Liu +8
End-to-end autonomous driving policies based on Imitation Learning (IL) often struggle in closed-loop execution due to the misalignment between inadequate open-loop training object…
SparseOccVLA: Bridging Occupancy and Vision-Language Models via Sparse Queries for Unified 4D Scene Understanding and Planning
Chenxu Dang, Jie Wang, Guang Li +6
In autonomous driving, Vision Language Models (VLMs) excel at high-level reasoning , whereas semantic occupancy provides fine-grained details. Despite significant progress in indiv…
Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
Jinghui Lu, Jiayi Guan, Zhijian Huang +47
Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that is…
Walk With Me: Long-Horizon Social Navigation for Human-Centric Outdoor Assistance
Lingfeng Zhang, Xiaoshuai Hao, Xizhou Bu +11
Assisting humans in open-world outdoor environments requires robots to translate high-level natural-language intentions into safe, long-horizon, and socially compliant navigation b…
AutoMine Solution for AV2 2026 Scenario Mining Challenge
Songliang Cao, Jiele Zhao, Yuru Wang +10
With the development of autonomous driving systems, mining high-value, safety-critical, and planning-relevant scenarios from large-scale driving logs has become essential for data-…
DriveMRP: Enhancing Vision-Language Models with Synthetic Motion Data for Motion Risk Prediction
Zhiyi Hou, Enhui Ma, Fang Li +11
Autonomous driving has seen significant progress, driven by extensive real-world data. However, in long-tail scenarios, accurately predicting the safety of the ego vehicle's future…
DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
Xiaoxue Chen, Ziyi Xiong, Yuantao Chen +11
Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimiz…
Pixel-Perfect Visual Geometry Estimation
Gangwei Xu, Haotong Lin, Hongcheng Luo +6
Recovering clean and accurate geometry from images is essential for robotics and augmented reality. However, existing geometry foundation models still suffer severely from flying p…
ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
Yongkang Li, Kaixin Xiong, Xiangyu Guo +12
Recent studies have explored leveraging the world knowledge and cognitive capabilities of Vision-Language Models (VLMs) to address the long-tail problem in end-to-end autonomous dr…
Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency
Xiangyu Guo, Zhanqian Wu, Kaixin Xiong +10
We present Genesis, a unified framework for joint generation of multi-view driving videos and LiDAR sequences with spatio-temporal and cross-modal consistency. Genesis employs a tw…
DriveReward: A Comprehensive Dataset and Generative Vision-Language Reward Model for Autonomous Driving
Qimao Chen, Fang Li, Yuechen Luo +11
Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such rewards typically relies on ha…
GeoWorldAD: Geometry World Action Model for Autonomous Driving
Songyan Zhang, Jinyuan Tian, Hanbing Li +9
Autonomous driving requires both safe and efficient planning decisions in dynamic 3D environments. Although recent Vision/Video-Action models learn policies directly from visual ob…
SimScale: Learning to Drive via Real-World Simulation at Scale
Haochen Tian, Tianyu Li, Haochen Liu +11
Achieving fully autonomous driving systems requires learning rational decisions in a wide span of scenarios, including safety-critical and out-of-distribution ones. However, such c…
UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving
Yongkang Li, Lijun Zhou, Sixu Yan +11
Vision-Language-Action (VLA) models have recently emerged in autonomous driving, with the promise of leveraging rich world knowledge to improve the cognitive capabilities of drivin…
Learning to Navigate Socially Through Proactive Risk Perception
Erjia Xiao, Lingfeng Zhang, Yingbo Tang +7
In this report, we describe the technical details of our submission to the IROS 2025 RoboSense Challenge Social Navigation Track. This track focuses on developing RGBD-based percep…
L2D2-GS: Learning to Densify for Feedforward Dynamic Gaussian Scene Reconstruction
Zetian Song, Chenming Wu, Junnan Liu +6
High-fidelity reconstruction of dynamic urban environments is a cornerstone of autonomous driving simulation and large-scale world modeling. While 3D Gaussian Splatting (3DGS) has…
MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
Junli Wang, Yinan Zheng, Xueyi Liu +9
Generative models have shown great potential in trajectory planning. Recent studies demonstrate that anchor-guided generative models are effective in modeling the uncertainty of dr…
Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks
Kai Zeng, Zhanqian Wu, Kaixin Xiong +12
Recent advancements in driving world models enable controllable generation of high-quality RGB videos or multimodal videos. Existing methods primarily focus on metrics related to g…
ViSE: A Systematic Approach to Vision-Only Street-View Extrapolation
Kaiyuan Tan, Yingying Shen, Haiyang Sun +3
Realistic view extrapolation is critical for closed-loop simulation in autonomous driving, yet it remains a significant challenge for current Novel View Synthesis (NVS) methods, wh…
FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation
Lingfeng Zhang, Zeying Gong, Xiaoshuai Hao +7
Vision-and-language navigation (VLN) in continuous environments requires an agent to ground instructions in egocentric observations while maintaining spatial understanding across l…
LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
Yuechen Luo, Fang Li, Shaoqing Xu +10
While Vision-Language-Action (VLA) models have revolutionized autonomous driving by unifying perception and planning, their reliance on explicit textual Chain-of-Thought (CoT) lead…
DriveVA: Video Action Models are Zero-Shot Drivers
Mengmeng Liu, Diankun Zhang, Jiuming Liu +7
Generalization is a central challenge in autonomous driving, as real-world deployment requires robust performance under unseen scenarios, sensor domains, and environmental conditio…
WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving
Ziyue Zhu, Zhanqian Wu, Zhenxin Zhu +8
Recent advances in driving-scene generation and reconstruction have demonstrated significant potential for enhancing autonomous driving systems by producing scalable and controllab…
Learning from Mistakes: Post-Training for Driving VLA with Takeover Data
Yinfeng Gao, Deqing Liu, Qichao Zhang +7
Current Vision-Language-Action (VLA) paradigms in end-to-end autonomous driving rely on offline training from static datasets, leaving them vulnerable to distribution shift. Recent…
Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers
Gangwei Xu, Haotong Lin, Hongcheng Luo +11
This paper presents Pixel-Perfect Depth, a monocular depth estimation model based on pixel-space diffusion generation that produces high-quality, flying-pixel-free point clouds fro…
LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model
Xiaodong Mei, Diankun Zhang, Hongwei Xie +3
Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving. However, existing VLAs typically rely on sparse action supervision, whi…
Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation
Lingfeng Zhang, Yuchen Zhang, Hongsheng Li +7
Vision-Language Models (VLMs), leveraging their powerful visual perception and reasoning capabilities, have been widely applied in Unmanned Aerial Vehicle (UAV) tasks. However, the…
Xiaomi Auto World Model: A Joint World Model Integrating Reconstruction and Generation for Autonomous Driving
Lijun Zhou, Hongcheng Luo, Zhenxin Zhu +34
This report presents a unified technical system addressing the two core capabilities of world models for autonomous driving: world representation and world generation. For world re…
UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
Mengmeng Liu, Diankun Zhang, Jiuming Liu +7
World Action Models (WAMs) have shown strong potential for improving action generalization in autonomous driving by using future video prediction as dense supervision for scene dyn…
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
Xianhui Meng, Zirui Song, Yuchen Zhang +10
Large Language Models (LLMs) have demonstrated remarkable capabilities in 3D indoor synthesis for Manhattan environments. However, existing methods often fail to capture plausible…
DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving
Feiyang jia, Lin Liu, Ziying Song +4
End-to-end (E2E) autonomous driving has recently attracted increasing interest in unifying Vision-Language-Action (VLA) with World Models to enhance decision-making and forward-loo…
Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning
Ziyang Yao, Haochen Liu, Yuncheng Jiang +10
Autonomous driving requires reasoning about how ego actions shape future world evolution, rather than merely mapping observations to actions. However, most end-to-end methods rely…
XEmbodied: A Foundation Model with Enhanced Geometric and Physical Cues for Large-Scale Embodied Environments
Kangan Qian, ChuChu Xie, Yang Zhong +13
Vision-Language-Action (VLA) models drive next-generation autonomous systems, but training them requires scalable, high-quality annotations from complex environments. Current cloud…
Dichotomous Diffusion Policy Optimization
Ruiming Liang, Yinan Zheng, Kexin Zheng +9
Diffusion-based policies have gained growing popularity in solving a wide range of decision-making tasks due to their superior expressiveness and controllable generation during inf…
From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection
Yepeng Liu, Hao Li, Liwen Yang +8
Keypoint-based matching is a fundamental component of modern 3D vision systems, such as Structure-from-Motion (SfM) and SLAM. Most existing learning-based methods are trained on im…
UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling
Kaiyuan Tan, Yingying Shen, Mingfei Tu +5
Dynamic driving scene reconstruction is critical for autonomous driving simulation and closed-loop learning. While recent feed-forward methods have shown promise for 3D reconstruct…
Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution
Rui Cai, Jun Guo, Xinze He +20
In this report, we introduce Xiaomi-Robotics-0, an advanced vision-language-action (VLA) model optimized for high performance and fast and smooth real-time execution. The key to ou…
Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
Junli Wang, Zhihua Hua, Xueyi Liu +7
Existing imitation learning methods for end-to-end autonomous driving predominantly learn from successful demonstrations by minimizing geometric deviations from expert trajectories…
Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model
Xinghang Li, Jun Guo, Qiwei Li +21
The paper introduces Xiaomi-Robotics-U0, a 38‑billion‑parameter multimodal autoregressive model that extends foundation image and video generation to embodied robotics, enabling co…
SocialNav-Map: Dynamic Mapping with Human Trajectory Prediction for Zero-Shot Social Navigation
Lingfeng Zhang, Erjia Xiao, Xiaoshuai Hao +7
Social navigation in densely populated dynamic environments poses a significant challenge for autonomous mobile robots, requiring advanced strategies for safe interaction. Existing…
Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving
Yinan Zheng, Tianyi Tan, Bin Huang +11
Diffusion models have become a popular choice for decision-making tasks in robotics, and more recently, are also being considered for solving autonomous driving tasks. However, the…
Team Xiaomi EV-AD VLA: Caption-Guided Retrieval System for Cross-Modal Drone Navigation -- Technical Report for IROS 2025 RoboSense Challenge Track 4
Lingfeng Zhang, Erjia Xiao, Yuchen Zhang +7
Cross-modal drone navigation remains a challenging task in robotics, requiring efficient retrieval of relevant images from large-scale databases based on natural language descripti…
ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors
Kaiyuan Tan, Yingying Shen, Haohui Zhu +8
Synthesizing extrapolated views from recorded driving logs is critical for simulating driving scenes for autonomous driving vehicles, yet it remains a challenging task. Recent meth…
SpatioLM: Towards General Physical Spatial Intelligence in Vision-Language Models
Jing Wu, Jianhua Wu, Jiayi Guan +5
Vision-Language Models (VLMs) perform well on commonsense reasoning tasks but struggle with visual spatial reasoning. Most existing solutions introduce extra 3D prior inputs or ext…
DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
Tianze Xia, Yongkang Li, Lijun Zhou +9
World models have become crucial for autonomous driving, as they learn how scenarios evolve over time to address the long-tail challenges of the real world. However, current approa…
RotVLA: Rotational Latent Action for Vision-Language-Action Model
Qiwei Li, Xicheng Gong, Xinghang Li +5
Latent Action Models (LAMs) have emerged as an effective paradigm for handling heterogeneous datasets during Vision-Language-Action (VLA) model pretraining, offering a unified acti…
PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
Cheng Chi, Xianqi Wang, Hongcheng Luo +9
High-fidelity reconstruction of driving scenes is crucial for autonomous driving. While recent feedforward 3D Gaussian Splatting (3DGS) methods enable fast reconstruction, their pe…
ParkGaussian: Surround-view 3D Gaussian Splatting for Autonomous Parking
Xiaobao Wei, Zhangjie Ye, Yuxiang Gu +10
Parking is a critical task for autonomous driving systems (ADS), with unique challenges in crowded parking slots and GPS-denied environments. However, existing works focus on 2D pa…
Mirage: One-Step Video Diffusion for Photorealistic and Coherent Asset Editing in Driving Scenes
Shuyun Wang, Haiyang Sun, Bing Wang +2
Vision-centric autonomous driving systems rely on diverse and scalable training data to achieve robust performance. While video object editing offers a promising path for data augm…