35 citations · 48 across the 13 of their papers we have counts for
14 papers
G0.5: One Autoregressive Stream for Robot Reasoning and Action
Yicheng Liu, Zibin Dong, Baijun Ye +24
The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert. This makes the VLM a context encoder r…
Fast-WAM: Do World Action Models Need Test-time Future Imagination?
Tianyuan Yuan, Zibin Dong, Yicheng Liu +1
World Action Models (WAMs) have emerged as a promising alternative to Vision-Language-Action (VLA) models for embodied control because they explicitly model how visual observations…
VolumeDP: Modeling Volumetric Representation for Manipulation Policy Learning
Tianxing Zhou, Feiyang Xue, Zhangchen Ye +3
Imitation learning is a prominent paradigm for robotic manipulation. However, existing visual imitation methods map 2D image observations directly to 3D action outputs, imposing a…
FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization
Yicheng Liu, Shiduo Zhang, Zibin Dong +12
Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often…
DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning
Tianyuan Yuan, Yicheng Liu, Chenhao Lu +3
Vision-Language-Action (VLA) models have recently shown impressive generalization and language-guided manipulation capabilities. However, their performance degrades on tasks requir…
Galaxea Open-World Dataset and G0 Dual-System VLA Model
Tao Jiang, Tianyuan Yuan, Yicheng Liu +7
We present Galaxea Open-World Dataset, a large-scale, diverse collection of robot behaviors recorded in authentic human living and working environments. All demonstrations are gath…
LONG3R: Long Sequence Streaming 3D Reconstruction
Zhuoguang Chen, Minghui Qin, Tianyuan Yuan +2
Recent advancements in multi-view scene reconstruction have been significant, yet existing methods face limitations when processing streams of input images. These methods either re…
Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous Driving
Yunshen Wang, Yicheng Liu, Tianyuan Yuan +4
Accurately predicting 3D occupancy grids from visual inputs is critical for autonomous driving, but current discriminative methods struggle with noisy data, incomplete observations…
P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priors
Zhou Jiang, Zhenxin Zhu, Pengfei Li +5
Autonomous vehicles are gradually entering city roads today, with the help of high-definition maps (HDMaps). However, the reliance on HDMaps prevents autonomous vehicles from stepp…
PreSight: Enhancing Autonomous Vehicle Perception with City-Scale NeRF Priors
Tianyuan Yuan, Yucheng Mao, Jiawei Yang +3
Autonomous vehicles rely extensively on perception systems to navigate and interpret their surroundings. Despite significant advancements in these systems recently, challenges pers…
StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction
Tianyuan Yuan, Yicheng Liu, Yue Wang +2
High-Definition (HD) maps are essential for the safety of autonomous driving systems. While existing techniques employ camera images and onboard sensors to generate vectorized high…
On Uni-Modal Feature Learning in Supervised Multi-Modal Learning
Chenzhuang Du, Jiaye Teng, Tingle Li +5
We abstract the features (i.e. learned representations) of multi-modal data into 1) uni-modal features, which can be learned from uni-modal training, and 2) paired features, which…
Neural Map Prior for Autonomous Driving
Xuan Xiong, Yicheng Liu, Tianyuan Yuan +3
High-definition (HD) semantic maps are crucial in enabling autonomous vehicles to navigate urban environments. The traditional method of creating offline HD maps involves labor-int…
VectorMapNet: End-to-end Vectorized HD Map Learning
Yicheng Liu, Tianyuan Yuan, Yue Wang +2
Autonomous driving systems require High-Definition (HD) semantic maps to navigate around urban roads. Existing solutions approach the semantic mapping problem by offline manual ann…