Publications

2026

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

arXiv (2026) · Yuanzhi Liang et al.

2025

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

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

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

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

2023

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

ICCV (2023) · Yuanzhi Liang et al.

AntEval: Quantitatively Evaluating Informativeness and Expressiveness of Agent Social Interactions

Multi-agent evaluation · Yuanzhi Liang et al.

2022

A Simple Episodic Linear Probe Improves Visual Recognition in the Wild

CVPR (2022) · Yuanzhi Liang et al.

SEEG: Semantic Energized Co-Speech Gesture Generation

CVPR (2022) · Yuanzhi Liang et al.

Penalizing the Hard Example But Not Too Much (MHEM)

TNNLS (2022) · Yuanzhi Liang et al.

2021

IcoCap: Image-Video Compounding for Video Understanding

TMM (2022) · Yuanzhi Liang et al.

2019

VrR-VG: Refocusing Visually-Relevant Relationships

ICCV (2019) · Yuanzhi Liang et al.