8 papers
Hierarchical Denoising For Multi-Step Visual Reasoning
Zezhong Qian, Xiaowei Chi, Chak-Wing Mak +9
Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in…
MV-WAM: Manifold-Aware World Action Model with Value Augmentation
Jintao Chen, Peidong Jia, Qingpo Wuwu +13
Achieving robust and generalizable manipulation across diverse environments remains a fundamental challenge in embodied robotics. Recent world action models achieve strong in-domai…
WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT
Zezhong Qian, Xiaowei Chi, Yu Qi +3
Recent World-Action (WA) models demonstrate strong generalization ability and data efficiency, but they typically rely on expert trajectories for training. This reliance limits the…
HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models
Qiuxuan Feng, Jiale Yu, Jiaming Liu +8
World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current WAMs generally follow two paradigms: the "Imagine-then-Exec…
Mask World Model: Predicting What Matters for Robust Robot Policy Learning
Yunfan Lou, Xiaowei Chi, Xiaojie Zhang +9
World models derived from large-scale video generative pre-training have emerged as a promising paradigm for generalist robot policy learning. However, standard approaches often fo…
OmniForcing: Unleashing Real-time Joint Audio-Visual Generation
Yaofeng Su, Yuming Li, Zeyue Xue +7
Recent joint audio-visual diffusion models achieve remarkable generation quality but suffer from high latency due to their bidirectional attention dependencies, hindering real-time…
WoW: Towards a World omniscient World model Through Embodied Interaction
Xiaowei Chi, Peidong Jia, Chun-Kai Fan +33
Humans develop an understanding of intuitive physics through active interaction with the world. This approach is in stark contrast to current video models, such as Sora, which rely…
WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation
Zezhong Qian, Xiaowei Chi, Yuming Li +5
Wrist-view observations are crucial for VLA models as they capture fine-grained hand-object interactions that directly enhance manipulation performance. Yet large-scale datasets ra…