Hao Jiang

Hao Jiang | 姜昊

I am a second-year PhD student in Computer Science at the University of Southern California, advised by Prof. Daniel Seita. I completed my undergraduate studies at USC, double majoring in Computer Science and Applied & Computational Mathematics (ACMA).

I work on multi-functional, contact-rich dexterous manipulation and the multi-modal sensing it requires. My methods impose explicit task structure on learned policies, drawing on model-based estimation and control where reliable state or safe execution is needed, and I validate them on real robots.

Selected Publications

(* indicates equal contribution, † indicates equal advising)

	When Does Touch Matter? Charting the Vision–Interaction Gap in Cluttered Dexterous Grasping Hao Jiang, Luis Dominguez, Daniel Seita In submission, 2026 project page / arXiv A controlled study of when vision alone stops being enough for dexterous grasping in clutter. Sweeping five scene conditions of increasing occlusion and confinement charts a widening vision–interaction gap, and shows contact wrench and taxel sensing to be complementary rather than redundant.
	Concurrent Prehensile and Nonprehensile Manipulation: A Practical Approach to Multi-Stage Dexterous Tasks Hao Jiang, Yue Wu, Yue Wang, Gaurav S. Sukhatme, Daniel Seita IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026 project page / arXiv / code / dataset Sample-efficient dexterous manipulation via retrieve-align-execute over object-centric skills. Achieves 66% success on concurrent multi-stage tasks with 3–4 demos per object, outperforming diffusion policy baselines by 2–3×.
	Learning to Singulate Objects in Packed Environments using a Dexterous Hand Hao Jiang, Yuhai Wang, Hanyang Zhou, Daniel Seita International Symposium of Robotics Research (ISRR), 2024 project page / arXiv / code / presentation / blog Multi-phase RL with a displacement-based state representation for singulating target objects in clutter using a 16-DOF Allegro Hand. Demonstrates strong sim-to-real transfer and outperforms baselines in packed-environment tasks.

Other Publications

HANDFUL: Sequential Grasp-Conditioned Dexterous Manipulation with Resource Awareness

Ethan Foong*, Yunshuang Li*, Hao Jiang, Gaurav S. Sukhatme, Daniel Seita

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026 project page / arXiv

UniLatent: Cross-Embodiment Transfer via Latent Observation Alignment

Yufei Ding*, Yi Du*, Weiduo Yuan, Hao Jiang, Dylan Goetting, Lawrence Yunliang Chen, Daniel Seita, Yue Wang

Conference on Robot Learning (CoRL), 2026 OpenReview

ENVISION: Embodied Visual Planning via Goal-Imagery Video Diffusion

Yuming Gu, Yizhi Wang, Yining Hong, Yipeng Gao, Hao Jiang, Angtian Wang, Bo Liu, Nathaniel S. Dennler, Zhengfei Kuang, Hao Li, Gordon Wetzstein, Chongyang Ma

arXiv, 2025 project page / arXiv

Open-Source

In-Hand Cube Rotation with LEAP Hand (MjLab)

Reinforcement learning pipeline for sim-to-real in-hand cube rotation using a LEAP Hand. Features asymmetric actor-critic training, curriculum learning, and domain randomization for robust real-world transfer.

GitHub

Award

USC Viterbi School of Engineering Fellowship : University of Southern California, 2025 - 2026
CRA Outstanding Researcher : Honorable Mention 2025
Provost Research Fellowship : University of Southern California, 2023 - 2024
Academic Achievement Award : University of Southern California, 2023

Service

Conference reviewer : ICRA 2027, IROS 2026
Journal reviewer : IEEE Robotics and Automation Letters (RA-L), 2025
Workshop reviewer : Agile Robotics Workshop @ICRA 2024
Course Producer : CSCI 170, CSCI 270 at USC

Website designed and implemented with Claude Code.