Xuchuan Huang | 黄叙川

ManiLadder: Benchmarking Manipulation Intelligence Frontier via a Categorized and Multi-Level Task Ladder

Xuchuan Huang*, Chongkai Gao*, Jieao Shi*, Zhaoyu Mu*, Boren Zheng, Zhuoran Li, Nga Teng Chan, Lin Shao

Project Page

We introduce ManiLadder, a large-scale simulation benchmark designed to quantitatively assess progress in robotic manipulation intelligence and capacity. It turns "How difficult a task can my algorithm solve?" into a measurable ladder to climb.

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective

Yifan Zhong*, Fengshuo Bai*, Shaofei Cai, Xuchuan Huang, Zhang Chen, Xiaowei Zhang, Yuanfei Wang, Shaoyang Guo, Tianrui Guan, Ka Nam Lui, Zhiquan Qi, Yitao Liang, Yuanpei Chen, Yaodong Yang

Project Page / Paper

We observe that current VLA models can be unified under a single framework: vision and language inputs are processed by a series of VLA modules, producing a chain of action tokens that progressively encode more grounded and actionable information, ultimately generating executable actions.

DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping

Yifan Zhong*, Xuchuan Huang*, Ruochong Li, Ceyao Zhang, Yitao Liang, Yaodong Yang, Yuanpei Chen

AAAI'2026 Oral Presentation.
Project Page / Paper / Code / Video

DexGraspVLA is a hierarchical framework for general-purpose dexterous grasping, which achieves over 90% zero-shot success in diverse real-world scenarios.

TerraX: Visual Terrain Classification Enhanced by Vision-Language Models

Hongze Li*, Xuchuan Huang*, Xinhai Chang*, Jun Zhou, Huijing Zhao

IROS'2025 Oral Presentation.
Project Page

TerraX is a vision-language framework for terrain classification, featuring the TerraData dataset, TerraBench benchmark, and TerraCLIP model.

ProgressGym: Alignment with a Millennium of Moral Progress

Tianyi Qiu*, Yang Zhang*, Xuchuan Huang, Jasmine Xinze Li, Jiaming Ji, Yaodong Yang

NeurIPS'2024 Spotlight, Dataset & Benchmark Track.
Paper / Code / Documentation / Hugging Face

To empower progress alignment, ProgressGym is a benchmark for training AI to track, predict, and co-evolve with human moral progress.

When Chinese Social Media Meet the Israeli Palestinian Conflict: Opinion Leaders, Moral Emotions, and Cultural Distance

Cheng Tan, Xuchuan Huang, Zijie Yu, Yanjun Liu

NCA 2025.
Grand Prize in 32nd Challenge Cup of PKU.

We analyze over 130,000 Weibo comments on the 2023 Israel-Palestine conflict to examine how public opinion forms and spreads in Chinese social media. It reveals how factors like verified accounts, moral framing, and cultural similarity shape sentiment dynamics in Chinese online discourse.

Global Emotions and Imaginations around Black Myth: Wukong: A Multilingual Analysis of Over 90, 000 Tweets

Cheng Tan, Xuchuan Huang, Zijie Yu, Yanjun Liu

We analyze 92,000+ multilingual tweets about Black Myth: Wukong to uncover how cultural, political, and emotional interpretations vary across linguistic communities. Using sentiment analysis and topic modeling, it highlights the complexities of global cultural exchange and digital geopolitics.