Zhijian Huang (黄志坚)

Jinghui Lu, Jiayi Guan, Zhijian Huang, Jinlong Li, Guang Li, Lingdong Kong, Yingyan Li, et al.

We present OneVL (One-step latent reasoning and planning with Vision-Language explanations), a unified VLA and World Model framework that routes reasoning through compact latent tokens supervised by dual auxiliary decoders.

Xiaoshuai Hao, Lei Zhou, Zhijian Huang, Zhiwen Hou, Yingbo Tang, Lingfeng Zhang, Guang Li, Zheng Lu, Shuhuai Ren, et al.

We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI.

Jie Wang, Guang Li, Zhijian Huang, Chenxu Dang, Hangjun Ye, Yahong Han, Long Chen

We propose a novel architecture, VGGDrive, which empowers Vision-language models with cross-view Geometric Grounding for autonomous Driving.

Hao Wang, Limeng Qiao, Zequn Jie, Zhijian Huang, Chengjian Feng, Qingfang Zheng, Lin Ma, Xiangyuan Lan, Xiaodan Liang

We present X-SAM, a streamlined Multimodal Large Language Model framework that extends the segmentation paradigm from Segment Anything to Any Segmentation.

Zhijian Huang, Chengjian Feng, Fen Yan, Baihui Xiao, Zequn Jie, Yujie Zhong, Xiaodan Liang, Lin Ma

A novel all-in-one large multimodal model robustly equipped with general capabilities and strong generalization for autonomous driving tasks.

Baihui Xiao, Chengjian Feng, Zhijian Huang, Feng Yan, Yujie Zhong, Lin Ma

We propose RoboTron-Sim that improves real-world driving in critical situations by utilizing simulated hard cases.

Zhijian Huang, Tao Tang, Shaoxiang Chen, Sihao Lin, Zequn Jie, Lin Ma, Guangrun Wang, Xiaodan Liang

We introduce RDA-Driver, a multimodal LLM decision-making model with reasoning-decision alignment for stronger autonomous driving planning.

Zhijian Huang, Sihao Lin, Guiyu Liu, Mukun Luo, Chaoqiang Ye, Hang Xu, Xiaojun Chang, Xiaodan Liang,

We introduce FULLER, a novel yet simple multi-level gradient calibration learning framework across tasks and modalities during optimization.

Minbin Huang Zhijian Huang, Changlin Li, Xin Chen, Hang Xu, Zhenguo Li, Xiaodan Liang,

We introduce Arch-Graph, a transferable NAS method that predicts task-specific optimal architectures with respect to given task embeddings.

Xianhui Meng, Yuchen Zhang, Zhijian Huang, Zheng Lu, Ziling Ji, Yaoyao Yin, Hongyuan Zhang, Guangfeng Jiang, Yandan Lin, Long Chen, Hangjun Ye, Li Zhang, Jun Liu, Xiaoshuai Hao, Xiaodan Liang,

We introduce DSBench, the first comprehensive Driving Safety Benchmark designed to assess a VLM's awareness of various safety risks in a unified manner.