2026

TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation

arXiv (2026) · Yuanzhi Liang et al.

中文解读 Project arXiv PDF

Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances

AI Flow (2026) · Yuanzhi Liang et al.

中文解读 Project Paper arXiv

Seeing What Matters: Visual Preference Policy Optimization for Visual Generation

CVPR (2026) · Ziqi Ni, Yuanzhi Liang, et al.

中文解读 Paper arXiv PDF

Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation

CVPR (2026) · Ruiying Liu, Yuanzhi Liang, et al.

中文解读 Paper arXiv PDF

Rethinking Reward Signals in Video GRPO: When Scores Become Targets

ECCV (2026) · Rui Li, Yuanzhi Liang, et al.

中文解读 arXiv PDF

LaxMotion: Rethinking Supervision Granularity for 3D Human Motion Generation

ECCV (2026) · Sheng Liu, Yuanzhi Liang, et al.

中文解读 arXiv PDF

2025

TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World Model

arXiv (2025) · Yabo Chen, Yuanzhi Liang, et al.

中文解读 arXiv PDF

Uni-Inter: Unifying 3D Human Motion Synthesis Across Diverse Interaction Contexts

SIGGRAPH Asia (2025) · Sheng Liu, Yuanzhi Liang, et al.

中文解读 Paper

InterSyn: Interleaved Learning for Dynamic Motion Synthesis in the Wild

ICCV (2025) · Yiyi Ma, Yuanzhi Liang, et al.

中文解读 Project Paper arXiv

2024

FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention

NeurIPS (2024) · Yu Lu, Yuanzhi Liang, et al.

中文解读 Project arXiv PDF

VAST 1.0: A Unified Framework for Controllable and Consistent Video Generation

arXiv (2024) · Chi Zhang, Yuanzhi Liang, et al.

中文解读 arXiv PDF

AntEval: Quantitatively Evaluating Informativeness and Expressiveness of Agent Social Interactions

arXiv (2024) · Yuanzhi Liang et al.

中文解读 arXiv

2023

MAAL: Multimodality-Aware Autoencoder-based Affordance Learning for 3D Articulated Objects

ICCV (2023) · Yuanzhi Liang et al.

中文解读 Paper

IcoCap: Improving Video Captioning by Compounding Images

TMM (2023) · Yuanzhi Liang et al.

中文解读 Paper

2022

A Simple Episodic Linear Probe Improves Visual Recognition in the Wild

CVPR (2022) · Yuanzhi Liang et al.

中文解读 Paper

SEEG: Semantic Energized Co-Speech Gesture Generation

CVPR (2022) · Yuanzhi Liang et al.

中文解读 Paper

Penalizing the Hard Example But Not Too Much: A Strong Baseline for Fine-Grained Visual Classification

TNNLS (2022) · Yuanzhi Liang et al.

中文解读 Paper

2021

Removing Raindrops and Rain Streaks in One Go

CVPR (2021) · Ruijie Quan, Yuanzhi Liang, et al.

中文解读 Paper

Food and Ingredient Joint Learning for Fine-Grained Recognition

TCSVT (2021) · Chengxu Liu, Yuanzhi Liang, et al.

中文解读 Paper

2019

VrR-VG: Refocusing Visually-Relevant Relationships

ICCV (2019) · Yuanzhi Liang et al.

中文解读 Paper