|
Feishi Wang | 王非石 I'm a PhD student at Northwestern University advised by Prof. Ruohan Zhang. Before that, I received my B.S. and M.S. in Computer Science from Peking University, advised by Prof. Boxin Shi. I was a visiting student at UC Berkeley advised by Prof. Pieter Abbeel in 2025. Email / Google Scholar / Github / Twitter |
|
|
Kangrui Wang*§, Qineng Wang*§, Changhe Chen*§, Pingyue Zhang*§, Chi Gui*§, Feishi Wang*§, Canyu Chen*§, Wenli Xiao§, Xiaoyu Huang§, Tonghe Zhang§, Linjie Li§, Zihan Wang, Minyeong Kim, Yiyou Sun, Mingkai Deng, Jinyu Hou, Qi Zhu, Han Liu, Eric P. Xing, Huaxiu Yao, Zhiwen Fan, Yuejiang Liu, Dawn Song, Pieter Abbeel, Li Fei-Fei, Jiajun Wu, Yuke Zhu, Guanya Shi†, Ruohan Zhang†, Manling Li† CoRL, 2026, Late Breaking Results Project / Code Embodied First Exam is a comprehensive agent-native framework that evaluates any coding agent on diverse robots and tasks under different settings. Serving as a first exam for coding agents before they enter the physical world, it shows that even the strongest agents still fall far short under real-world constraints. |
|
Renhao Wang, Haoran Geng, Tingle Li, Feishi Wang, Gopala Anumanchipalli, Trevor Darrell, Boyi Li, Pieter Abbeel, Jitendra Malik, Alexei A. Efros CoRL, 2025 (Oral, Best Paper Finalist) Paper We integrate generative models with physics simulators to enable multisensory robot training, synthesizing audio from simulated video. Applied to robot pouring, it enables training without real data and achieves zero-shot transfer to real-world tasks, bridging the multimodal sim-to-real gap. |
|
Haoran Geng*, Feishi Wang*, Songlin Wei*, Yuyang Li*, Bangjun Wang*, Boshi An*, Charlie Tianyue Cheng*, Haozhe Lou, Peihao Li, Yen-Jen Wang, Yutong Liang, Dylan Goetting, Chaoyi Xu, Haozhe Chen, Yuxi Qian, Yiran Geng, Jiageng Mao, Weikang Wan, Mingtong Zhang, Jiangran Lyu, Siheng Zhao, Jiazhao Zhang, Jialiang Zhang, Chengyang Zhao, Haoran Lu, Yufei Ding, Ran Gong, Yuran Wang, Yuxuan Kuang, Ruihai Wu, Baoxiong Jia, Carlo Sferrazza, Hao Dong, Siyuan Huang†, Yue Wang†, Jitendra Malik†, Pieter Abbeel† RSS, 2025 (Oral) RoboGen Workshop @ IROS, 2025 (Oral, Best Open-Source) RoDGE Workshop @ IROS, 2025 (Best Poster) RGMC Workshop @ IROS, 2025 (Oral, Best Abstract) Paper / Project / Code RoboVerse is a comprehensive framework for advancing robotics through a simulation platform, synthetic dataset, and unified benchmarks. Its MetaSim infrastructure abstracts diverse simulators into a universal interface, ensuring interoperability and extensibility. RoboVerse improves sim-to-real transfer and enables consistent evaluation for imitation and reinforcement learning, addressing key challenges in scaling robotic data and benchmarking. |
|
Bohan Yu, Jieji Ren, Jin Han, Feishi Wang, Jinxiu Liang, Boxin Shi CVPR, 2024 (Oral, Best Paper Honorable Mention) Paper / Project / Code EventPS is a novel approach to real-time photometric stereo using an event camera, which significantly enhances data efficiency and ensures low latency compared to traditional frame-based photometric stereo. |
|
Heng Guo*, Jieji Ren*, Feishi Wang*, Boxin Shi† Mingjun Ren†, Yasuyuki Matsushita† CVPR, 2024 Paper / Project DiLiGenRT is the first real-world dataset for evaluating photometric stereo methods under quantified reflectances by manufacturing 54 hemispheres with varying degrees of two reflectance properties: Roughness and Translucency. |
|
Feishi Wang*, Jieji Ren*, Heng Guo*, Mingjun Ren†, Boxin Shi† ICCV, 2023 Paper / Project DiLiGenT-Pi is a novel real-world dataset for photometric stereo, consisting of 30 planar shapes with fine details, and present three key observations derived from benchmark results and subsequent experiments. |
|
Jieji Ren, Feishi Wang, Jiahao Zhang, Qian Zheng, Mingjun Ren†, Boxin Shi† CVPR, 2022 Paper / Project DiLiGenT102 is a new real-world dataset for photometric stereo with controlled shape and material variations. A 10×10 shape-material error distribution matrix is visualized to depict a "portrait" for each evaluated method. |
|
|
|
|