activity
20242026
collaborators

12 papers

cs.LG2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.LG2026

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…

cs.CV2025

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…

cs.CV2025

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…