Jingsong (Jason) Liang

Ph.D. Student at Nanyang Technological University

jingsong.jpg

Jingsong Liang is a PhD student in Robotics and AI at Nanyang Technological University, supervised by Prof. Chen Lv and Prof. Wanhua Li. He is a recipient of the IGP Artificial Intelligence-X Scholarship.

His research centers on Multimodal Embodied Generalist Agents (MEGA), aiming to build general-purpose agents that integrate multimodal perception, embodied reasoning, autonomous planning, and continual self-improvement in the physical world. He also works closely with Sharpa on visual-tactile manipulation.

News 🎉

Aug 10, 2026 Our paper on human-vehicle interactive world model has been accepted by STEAI at ECCV 2026!
Aug 04, 2026 Organizing committee of the EIR 2026.
May 22, 2026 Best Poster Award at SRISS 2026 🏆
May 05, 2026 Our paper on cooperative multi-agent navigation (ORION) has been accepted by RA-L!
Jan 31, 2026 Our paper GRATE has been accepted by ICRA 2026!
Dec 05, 2025 Invited speaker at IEEE MRS 2025!
Nov 06, 2025 Happy to receive the prestigious IGP-AI-X Research Award! 🎉
Oct 20, 2025 Best paper award at Active Perception Workshop, IROS 2025 ! 🏆
Aug 02, 2025 Two papers on (1) inpainting-aware exploration and navigation (CogniPlan) and (2) multimodal GTSP have been accepted by CoRL 2025! See you in Seoul, Korea!
Jan 28, 2025 Our paper on diffusion-based exploration (DARE) has been accepted by ICRA 2025! See you in Atlanta, USA!
Nov 05, 2024 Our paper on hierarchical planning for navigation and exploration (HDPlanner) has been accepted by RA-L!
Jul 01, 2024 Our paper on information sharing for multi-robot exploration has been accepted for oral presentation by DARS 2024!
Jun 30, 2024 Our paper on multi-robot exploration and rendezvous under limited communication range (IR2) has been accepted for oral presentation by IROS 2024!
Apr 22, 2024 Invited talk on “hierarchical planning for multi-agent systems.” Thanks to Prof. Guillaume Sartoretti and Prof. Harold Soh for hosting 🎉
Aug 31, 2023 Our paper on mapless navigation has been accepted by CoRL 2023! See you in Atlanta, USA!

Selected Publications 🎉

  1. RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents
    Jingsong Liang, Shuhao Liao, Shizhe Zhang, and 15 more authors
    arXiv preprint, 2026
    PDF Website Code GitHub stars
  2. orion_ros.gif
    ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation
    Shizhe Zhang*, Jingsong Liang*, Zhitao Zhou, and 6 more authors
    IEEE Robotics and Automation Letters (RA-L), 2026
    PDF Code GitHub stars
  3. cogniplan_preview.webp
    CogniPlan: Uncertainty-Guided Path Planning with Conditional Generative Layout Prediction
    Yizhuo Wang, Haodong He, Jingsong Liang, and 3 more authors
    Conference on Robot Learning (CoRL), 2025
    PDF Website Code GitHub stars
  4. mmfl.webp
    Multimodal Fused Learning for Solving the Generalized Traveling Salesman Problem in Robotic Task Planning
    Jiaqi Cheng, Mingfeng Fan, Xuefeng Zhang, and 4 more authors
    Conference on Robot Learning (CoRL), 2025
    PDF
  5. dare.webp
    DARE: Diffusion Policy for Autonomous Robot Exploration
    Yuhong Cao, Jeric Lew, Jingsong Liang, and 2 more authors
    IEEE International Conference on Robotics and Automation (ICRA), 2025
    PDF Code GitHub stars
  6. hdplanner.webp
    HDPlanner: Advancing Autonomous Deployments in Unknown Environments through Hierarchical Decision Networks
    Jingsong Liang, Yuhong Cao, Yixiao Ma, and 2 more authors
    IEEE Robotics and Automation Letters (RA-L), 2025
    PDF Code GitHub stars
  7. ir2.gif
    IR2: Implicit Rendezvous for Robotic Exploration Teams under Sparse Intermittent Connectivity
    Derek Tan, Yixiao Ma, Jingsong Liang, and 3 more authors
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
    Oral Presentation
    PDF Website Code GitHub stars
  8. corl23.png
    Context-Aware Deep Reinforcement Learning for Autonomous Robotic Navigation in Unknown Area
    Jingsong Liang, Zhichen Wang, Yuhong Cao, and 3 more authors
    Conference on Robot Learning (CoRL), 2023
    PDF Code GitHub stars

Community Service

  • Conference Reviewer: ICLR, NeurIPS, ICRA, IROS, ECCV, AAAI.
  • Journal Reviewer: RA-L, T-ASE.
  • Workshop Reviewer: CL4FMAgents@ICLR2027, DexHAND@ECCV2026.