ZH
Zhi Hou
cs.CVcs.ROcs.AIcs.LG
On Valency
published · living versionsW_jav7dcru·v1 · currentpublished
ACE-Brain-0.6: Scaling Spatial Grounding for Physical Foundation Models
with Yinhe Wang, Tao Tao, Zexin He, Shuang Luo +9
1 version
Preprints & journals
13 papers in the corpus · 2020–2026ACE-Brain-0.6: Scaling Spatial Grounding for Physical Foundation Models2610.27040v1 · Yinhe Wang, Tao Tao, Zexin He et al.2026 · 0 citationsarXivon Valency
Atomic-WAM: Execution-Grounded Atomic-Motion Reasoning for World Action Models2610.20157v1 · Shijun Shi, Zhe Liu, Zhi Hou et al.2026 · 0 citationsarXiv
ReAP: From Visual Failure Recognition to Action-Conditioned Risk Prediction for Runtime Failure Monitoring2610.16309v1 · Jingyuan Liu, Yunpeng Qing, Changxu Wei et al.2026 · 0 citationsarXiv
StateSkill-Agent: An Effective and Efficient Embodied Agent via State-conditioned Skill2610.14601v1 · Changxu Wei, Jingyi Zhang, Zhiyu Zheng et al.2026 · 0 citationsarXiv
PF-RL: Progress Field Reinforcement Learning via Goal-Conditioned Value Geometry for Vision-Language-Action Models2609.32634v1 · Yunpeng Qing, Yilun Kong, Sixu Lin et al.2026 · 0 citationsarXiv
Learning to Explore Sample Relationships.40063428 · Hou, Zhi, Yu, Baosheng, Wang, Chaoyue et al.2025 · 4 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(7):5445-5459
Compositional 3D Human-Object Neural Animation2304.14070v1 · Zhi Hou, Baosheng Yu, Dacheng Tao2023 · 1 citationarXiv
BatchFormerV2: Exploring Sample Relationships for Dense Representation Learning2204.01254v1 · Zhi Hou, Baosheng Yu, Chaoyue Wang et al.2022 · 10 citationsarXiv
Discovering Human-Object Interaction Concepts via Self-Compositional Learning2203.14272v2 · Zhi Hou, Baosheng Yu, Dacheng Tao2022 · 15 citationsarXiv
BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning2203.01522v2 · Zhi Hou, Baosheng Yu, Dacheng Tao2022 · 104 citationsarXiv
Affordance Transfer Learning for Human-Object Interaction Detection2104.02867v2 · Zhi Hou, Baosheng Yu, Yu Qiao et al.2021 · 130 citationsarXiv
Detecting Human-Object Interaction via Fabricated Compositional Learning2103.08214v2 · Zhi Hou, Baosheng Yu, Yu Qiao et al.2021 · 117 citationsarXiv
Visual Compositional Learning for Human-Object Interaction Detection2007.12407v2 · Zhi Hou, Xiaojiang Peng, Yu Qiao et al.2020 · 186 citationsarXiv
Career total: 38 works. 13 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.