13 papers
Rethinking Representations for World-Action Modeling
Haoyi Jiang, Liu Liu, Xinjiang Wang +12
World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design o…
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…
Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models
Weiheng Zhao, Haoyi Jiang, Xin Shi +5
World Action Models (WAMs) improve robot manipulation by learning how the environment evolves beyond the current observation. However, existing approaches face a fundamental dilemm…
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…
3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image
Ze-Xin Yin, Liu Liu, Xinjie Wang +4
Compositional 3D scene generation from a single view requires the simultaneous recovery of scene layout and 3D assets. Existing approaches mainly fall into two categories: feed-for…
IRIS-SLAM: Unified Geo-Instance Representations for Robust Semantic Localization and Mapping
Tingyang Xiao, Liu Liu, Wei Feng +6
Geometry foundation models have significantly advanced dense geometric SLAM, yet existing systems often lack deep semantic understanding and robust loop closure capabilities. Meanw…
Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning
Haoyi Jiang, Liu Liu, Xinjie Wang +5
Vision-language models excel at 2D visual understanding but remain limited in 3D spatial reasoning. Existing approaches either depend on explicit 3D modalities, which limits scalab…
FSR-VLN: Fast and Slow Reasoning for Vision-Language Navigation with Hierarchical Multi-modal Scene Graph
Xiaolin Zhou, Tingyang Xiao, Liu Liu +7
Visual-Language Navigation (VLN) is a fundamental challenge in robotic systems, with broad applications for the deployment of embodied agents in real-world environments. Despite re…
DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation
Ze-Xin Yin, Jiaxiong Qiu, Liu Liu +5
The labor- and experience-intensive creation of 3D assets with physically based rendering (PBR) materials demands an autonomous 3D asset creation pipeline. However, most existing 3…
Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images
Xiangyu Sun, Haoyi Jiang, Liu Liu +8
Reconstructing and semantically interpreting 3D scenes from sparse 2D views remains a fundamental challenge in computer vision. Conventional methods often decouple semantic underst…
EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence
Xinjie Wang, Liu Liu, Yu Cao +5
Constructing a physically realistic and accurately scaled simulated 3D world is crucial for the training and evaluation of embodied intelligence tasks. The diversity, realism, low…
GeoFlow-SLAM: A Robust Tightly-Coupled RGBD-Inertial and Legged Odometry Fusion SLAM for Dynamic Legged Robotics
Tingyang Xiao, Xiaolin Zhou, Liu Liu +5
This paper presents GeoFlow-SLAM, a robust and effective Tightly-Coupled RGBD-inertial SLAM for legged robotics undergoing aggressive and high-frequency motions.By integrating geom…
GLS: Geometry-aware 3D Language Gaussian Splatting
Jiaxiong Qiu, Liu Liu, Xinjie Wang +3
Recently, 3D Gaussian Splatting (3DGS) has achieved impressive performance on indoor surface reconstruction and 3D open-vocabulary segmentation. This paper presents GLS, a unified…