Pre-Print

Visual Distraction Undermines Moral Reasoning in Vision-Language Models
Moral reasoning is fundamental to safe Artificial Intelligence (AI), yet ensuring its consistency across modalities becomes critical as …
Xinyi Yang, Chenheng Xu, Weijun Hong, Ce Mo, Qian Wang, Fang Fang, Yixin Zhu
PDF Cite Code Video
Visual Distraction Undermines Moral Reasoning in Vision-Language Models
OmniClone: Engineering a Robust, All-Rounder Whole-Body Humanoid Teleoperation System
Whole-body humanoid teleoperation enables humans to remotely control humanoid robots, serving as both a real-time operational tool and …
Yixuan Li, Le Ma, Yutang Lin, Yushi Du, Mengya Liu, Kaizhe Hu, Jieming Cui, Yixin Zhu, Baoxiong Jia, Wei Liang, Siyuan Huang
PDF Cite Code Video
OmniClone: Engineering a Robust, All-Rounder Whole-Body Humanoid Teleoperation System
LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations
Humanoid robots that autonomously interact with physical environments over extended horizons represent a central goal of embodied …
Yutang Lin, Jieming Cui, Yixuan Li, Baoxiong Jia, Yixin Zhu, Siyuan Huang
PDF Cite Video
LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations
UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots
A long-standing objective in humanoid robotics is the realization of versatile agents capable of following diverse multimodal …
Nan Jiang, Zimo He, Wanhe Yu, Lexi Pang, Yunhao Li, Hongjie Li, Jieming Cui, Yuhan Li, Yizhou Wang, Yixin Zhu, Siyuan Huang
PDF Cite Code Dataset Video
UniAct: Unified Motion Generation and Action Streaming for Humanoid Robots
Cross-Scenario Unified Modeling of User Interests at Billion Scale
User interests on content platforms are inherently diverse, manifesting through complex behavioral patterns across heterogeneous …
Manjie Xu, Xin Jia, Cheng Chen, Jingyi Zhou, Chi Zhang, Yongji Wu, Zejian Wang, Kai Zuo, Yibo Chen, Xu Tang, Yao Hu, Yixin Zhu
PDF Cite Code Dataset
Cross-Scenario Unified Modeling of User Interests at Billion Scale
Multivariate Long-term Time Series Forecasting with Fourier Neural Filter
Multivariate long-term time series forecasting has been suffering from the challenge of capturing both temporal dependencies within …
Chenheng Xu, Dan Wu, Yixin Zhu, Ying Nian Wu
PDF Cite Code Web
Multivariate Long-term Time Series Forecasting with Fourier Neural Filter
AffordX: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation
Object affordance reasoning, the ability to infer object functionalities based on physical properties, is fundamental for task-oriented …
Xiaomeng Zhu, Yuyang Li, Leiyao Cui, Pengfei Li, Huang-Ang Gao, Yixin Zhu, Hao Zhao
PDF Cite Code Dataset Video Web
AffordX: Generalizable and Slim Affordance Reasoning for Task-oriented Manipulation
Learning to Plan with Personalized Preferences
Effective integration of AI agents into daily life requires them to understand and adapt to individual human preferences, particularly …
Manjie Xu, Xinyi Yang, Wei Liang, Chi Zhang, Yixin Zhu
PDF Cite Code Video Web
Learning to Plan with Personalized Preferences
Dexterous Functional Pre-Grasp Manipulation with Diffusion Policy
In real-world scenarios, objects often require repositioning and reorientation before they can be grasped, a process known as pre-grasp …
Tianhao Wu, Yunchong Gan, Mingdong Wu, Jingbo Cheng, Yaodong Yang, Yixin Zhu, Hao Dong
PDF Cite Video Web
Dexterous Functional Pre-Grasp Manipulation with Diffusion Policy
STRAP: Structured Transformer for Affordance Segmentation with Point Supervision
With significant annotation savings, point supervision has been proven effective for numerous 2D and 3D scene understanding problems. …
Leiyao Cui, Xiaoxue Chen, Hao Zhao, Guyue Zhou, Yixin Zhu
PDF Cite Code
STRAP: Structured Transformer for Affordance Segmentation with Point Supervision