3 citations · 9 across the 23 of their papers we have counts for
23 papers
On-Policy Distillation for Vision-Language Model Adaptation, an Effective Paradigm on Low-Quality Multimodal Data
Hongyuan Zhang, Xianda Guo, Yanlun Peng +6
Knowledge distillation offers an efficient route to transfer a task-adapted vision-language teacher to a compact student. The training target in current vision-language distillatio…
DriveCache: Action-Aware Caching for Driving World Model Inference
Jianchun Yang, Jian Liang, Xianda Guo +5
Driving video generation models support autonomous-driving development by predicting controllable future scenes for simulation, planning evaluation, and offline data generation. Di…
DreamWAM: Beyond RGB Future Prediction for World Action Models
Shanglin Yuan, Weiheng Zhao, Xin Shi +6
World Action Models (WAMs) learn action-relevant representations by predicting how the observed world will evolve. Most existing WAMs define this future in RGB space, where task-re…
EA-Nav: Learning Safe Visual Navigation Policies with Embodiment Awareness
Jialu Zhang, Yong Du, Xianda Guo +6
Cross-embodiment navigation is a key challenge in embodied intelligence. Due to differences in embodiment, the same visual observation may imply different actions for different age…
SkillNav: Score-Level Skill Intervention for Zero-Shot Object Goal Navigation
Ruijie Sang, Yiqun Duan, Pinhan Fu +3
Vision-Language Model (VLM) agents have advanced zero-shot object-goal navigation, yet single-frame reasoning leaves them without the cross-step behavioral awareness an embodied na…
TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors
Pinhan Fu, Xianda Guo, Xuetao Li +5
Vision-Language-Action (VLA) models are deployed through pipelines that end users cannot audit, and a poisoned VLA can behave normally on clean observations while a small visual tr…
Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AI
Xianda Guo, Bohao Zhang, Chenwei Huang +6
Occupancy prediction at voxel-level granularity is essential for safe robotic navigation and interaction in complex environments. Existing occupancy datasets, however, are predomin…
StereoFactory: A Unified Merging Framework for Robust Stereo Matching
Xianda Guo, Pinhan Fu, Ruilin Wang +3
Stereo matching has advanced through foundation models trained on large-scale datasets, yet this paradigm suffers from a scalability bottleneck: incorporating new data requires cos…
ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving
Zhiyuan Zhang, Yanlun Peng, Jianing Zhang +7
Reactive capability is a key property of data-driven behavior world model simulators for autonomous driving simulation systems. With this capability, simulated world agents can res…
MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model
Shanglin Yuan, Weiheng Zhao, Xianda Guo +4
Vision-language-action (VLA) models increasingly condition robot policies on history, depth, or 4D features to resolve ambiguity in long-horizon manipulation. However, more spatiot…
Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations
Zhiyuan Zhang, Zhenghao Jin, Yanlun Peng +8
Robustness is a critical requirement for deploying autonomous driving systems in the real world. Existing robustness benchmarks for autonomous driving have made important progress…
R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation
Yuhao Zhang, Wanxi Dong, Yue Shi +13
Embodied manipulation requires accurate 3D understanding of objects and their spatial relations to plan and execute contact-rich actions. While large-scale 3D vision models provide…
UniVTAC: A Unified Simulation Platform for Visuo-Tactile Manipulation Data Generation, Learning, and Benchmarking
Baijun Chen, Weijie Wan, Tianxing Chen +13
Robotic manipulation has seen rapid progress with vision-language-action (VLA) policies. However, visuo-tactile perception is critical for contact-rich manipulation, as tasks such…
StereoCarla: A High-Fidelity Driving Dataset for Generalizable Stereo
Xianda Guo, Chenming Zhang, Ruilin Wang +6
Stereo matching plays a crucial role in enabling depth perception for autonomous driving and robotics. While recent years have witnessed remarkable progress in stereo matching algo…
ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Driving
Xianda Guo, Ruijun Zhang, Yiqun Duan +9
Depth estimation is a fundamental component of spatial perception for autonomous driving and other unmanned systems operating in open urban environments. Existing depth datasets su…
InsightDrive: Insight Scene Representation for End-to-End Autonomous Driving
Ruiqi Song, Xianda Guo, Yanlun Peng +3
Conventional end-to-end autonomous driving methods often rely on explicit global scene representations, which typically consist of 3D object detection, online mapping, and motion p…
WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation
Dujun Nie, Xianda Guo, Yiqun Duan +2
Object Goal Navigation-requiring an agent to locate a specific object in an unseen environment-remains a core challenge in embodied AI. Although recent progress in Vision-Language…
Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Data
Xianda Guo, Chenming Zhang, Youmin Zhang +8
Stereo matching serves as a cornerstone in 3D vision, aiming to establish pixel-wise correspondences between stereo image pairs for depth recovery. Despite remarkable progress driv…
SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models
Xianda Guo, Ruijun Zhang, Yiqun Duan +7
Accurate spatial reasoning in outdoor environments - covering geometry, object pose, and inter-object relationships - is fundamental to downstream tasks such as mapping, motion for…
AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusion
Yuting Xie, Xianda Guo, Cong Wang +2
Safety-critical scenarios are infrequent in natural driving environments but hold significant importance for the training and testing of autonomous driving systems. The prevailing…
Instruct Large Language Models to Drive like Humans
Ruijun Zhang, Xianda Guo, Wenzhao Zheng +3
Motion planning in complex scenarios is the core challenge in autonomous driving. Conventional methods apply predefined rules or learn from driving data to plan the future trajecto…
LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregation
Xianda Guo, Chenming Zhang, Youmin Zhang +4
We present LightStereo, a cutting-edge stereo-matching network crafted to accelerate the matching process. Departing from conventional methodologies that rely on aggregating comput…
GenAD: Generative End-to-End Autonomous Driving
Wenzhao Zheng, Ruiqi Song, Xianda Guo +2
Directly producing planning results from raw sensors has been a long-desired solution for autonomous driving and has attracted increasing attention recently. Most existing end-to-e…