12 papers
Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning
Yuxiao Yang, Weitong Zhang
Conditioned Sequence Models (CSMs) learn policies by treating return-to-go (RTG) as a control signal. However, existing CSMs often treat the RTGs as simple numerical inputs rather…
AnyID: Ultra-Fidelity Universal Identity-Preserving Video Generation from Any Visual References
Jiahao Wang, Hualian Sheng, Sijia Cai +5
Identity-preserving video generation offers powerful tools for creative expression, allowing users to customize videos featuring their beloved characters. However, prevailing metho…
UniPR: Unified Object-level Real-to-Sim Perception and Reconstruction from a Single Stereo Pair
Chuanrui Zhang, Yingshuang Zou, ZhengXian Wu +3
Perceiving and reconstructing objects from images are critical for real-to-sim transfer tasks, which are widely used in the robotics community. Existing methods rely on multiple su…
Provable and Practical In-Context Policy Optimization for Self-Improvement
Tianrun Yu, Yuxiao Yang, Zhaoyang Wang +6
We study test-time scaling, where a model improves its answer through multi-round self-reflection at inference. We introduce In-Context Policy Optimization (ICPO), in which an agen…
EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer
Yuxiao Yang, Hualian Sheng, Sijia Cai +6
Video generation models have advanced significantly, yet they still struggle to synthesize complex human movements due to the high degrees of freedom in human articulation. This li…
Wonder3D++: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image
Yuxiao Yang, Xiao-Xiao Long, Zhiyang Dou +7
In this work, we introduce \textbf{Wonder3D++}, a novel method for efficiently generating high-fidelity textured meshes from single-view images. Recent methods based on Score Disti…