24 papers
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…
IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer
Zhengyu Zou, Hao Li, Kuixuan Jiao +7
Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spa…
NoDrift3R: Raymap-Guided Coupling for Drift-Robust Unposed Feed-Forward 3D Reconstruction
Xiangyu Sun, Liu Liu, Seungkwon Yang +4
Pose-Free Feed-forward 3D Gaussian Splatting (3DGS) has recently emerged as a powerful paradigm for fast scene reconstruction. However, its performance degrades significantly in lo…
GeoFlow-SLAM++: A Robust Multi-Camera Visual-Inertial SLAM System with Relocalization
Wei Feng, Tingyang Xiao, Liu Liu +2
Monocular and RGB-D visual-inertial SLAM systems remain susceptible to limited field of view, sensor-specific failure modes, and unreliable cross-session relocalization. To address…
HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory
Xiaolin Zhou, Liu Liu, Tingyang Xiao +9
LLM agents follow a practical execution loop in digital environments: they reason over structured states, invoke tools, inspect feedback, and revise actions. Extending this loop to…
SimWeaver: Zero-Shot RGB Sim-to-Real for Deformable Manipulation
Wenkang Hu, Haoran Wang, Yitong Li +10
RGB sim-to-real for deformable manipulation has remained largely unsolved without real-world fine-tuning. We present SimWeaver, which trains zero-shot RGB VLA policies on 200 simul…