Portrait of Ronghao Dang
Ronghao Dang 党荣浩
AI Researcher · JD Explore Academy
drh1710013267@163.com

About

I am an AI Researcher at JD Explore Academy in Shanghai. My research focuses on Embodied AI, Multimodal Foundation Models, 3D Vision, and Reinforcement Learning. I am interested in building intelligent agents that can perceive, reason, plan, and act in complex physical environments.

I received my M.Eng. in Control Science and Engineering and B.Eng. in Automation from Tongji University. I am always open to research discussions and collaboration. Feel free to drop me an email.

Research Interests

  • Embodied AIEmbodied cognition · navigation · planning
  • Multimodal Foundation ModelsVision-language models · video understanding
  • 3D VisionSpatial perception · localization · physical reasoning
  • Reinforcement LearningSequential decision-making · policy learning

Education

Tongji University
  • M.Eng in Control Science and Engineering, Sep. 2021 - Jun. 2024
  • Mentor: Prof. Chengju Liu (Google Scholar) and Prof. Qijun Chen (Google Scholar)
  • National Scholarship, Ministry of Education of China, 2023
Tongji University
  • B.Eng in Automation, Sep. 2017 - Jun. 2021

Experiences

JD Explore AcademyMay 2026 – Present
AI Researcher @ JD Explore Academy

Focus on Embodied AI and Physical World Pretraining.

Alibaba DAMO AcademyMay 2024 – May 2026
AI Researcher @ Alibaba DAMO Academy

Focus on Embodied AI and spatial intelligence.

SenseTimeMay 2023 – Sept. 2023
Research Intern @ SenseTime

Focus on MLLM and multimodal generalization.

CASIAJan. 2020 – June 2020
Research Intern @ CASIA

Focus on neural architecture search (NAS).

Publications

RynnBrain
RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model
Core Contributor · Team Leader
RynnBrain 1.1 evolves embodied models and builds cross-robot VLA. It tops benchmarks and beats mainstream VLAs in real robot tests.
DAMO Technical Report
InternVL-Search
InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
Bohan Hou∗, Jiuning Gu∗, Jiayan Guo, Ronghao Dang, Sicong Leng, Xin Li, Xuemeng Song, Jianfei Yang
Existing benchmarks overlook iterative visual evidence in search trajectories. We propose InterLV-Search with InterLV-Agent; top multimodal agents score under 50% on this interleaved multimodal search task.
Arxiv 2026
RynnBrain
Rynnbrain: Open embodied foundation models
First Contributor · Team Leader
A unified embodied foundation model integrating comprehensive egocentric understanding, diverse spatiotemporal localization, physically grounded reasoning, and physics-aware planning.
DAMO Technical Report
RynnEC
RynnEC: Bringing mllms into embodied world
First Contributor · Team Leader
A region-centric video paradigm for embodied-agent cognition, enabling fine-grained perception and more precise physical interactions.
DAMO Technical Report
Chain of Idea
Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents
Long Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xinxuan Li, Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin , Ronghao Dang, Yu Rong, Deli Zhao, Tian Feng, Lidong Bing
Existing idea-generation LLM methods lack structured literature utilization. We propose Chain-of-Ideas agent and Idea Arena; it surpasses baselines and achieves human-level ideas with low cost.
EMNLP 2025
ECBench
ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark
Ronghao Dang, Yuqian Yuan, Wenqi Zhang, Yifei Xin, Boqiang Zhang, Long Li, Liuyi Wang, Qinyang Zeng, Xin Li, Lidong Bing
We build ECBench benchmark with 30 embodied cognition dimensions plus ECEval system. Evaluations reveal its value for advancing egocentric LVLMs.
CVPR 2025
EOC-Bench
EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
Yuqian Yuan, Ronghao Dang, Long Li, Wentong Li, Dian Jiao, Xin Li, Deli Zhao, Fan Wang, Wenqiao Zhang, Jun Xiao, Yueting Zhuang
We propose EOC-Bench to assess dynamic object-centric embodied cognition with temporal QA and new temporal metric. Evaluations validate its utility for benchmarking MLLMs.
NeurlPS 2025
MoTE
MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
Minghao Zhu, Zhengpu Wang, Mengxian Hu, Ronghao Dang, Xiao Lin, Xun Zhou, Chengju Liu, Qijun Chen
We propose MoTE with mixture temporal experts, weight merging regularization and temporal modulation. It balances zero-shot and close-set video recognition performance.
NeurlPS 2024
Vision-and-Language Navigation via Causal Learning
Vision-and-Language Navigation via Causal Learning
Liuyi Wang, Zongtao He, Ronghao Dang, Mengjiao Shen, Chengju Liu, Qijun Chen
We propose GOAT equipped with BACL, FACL and CFP modules to alleviate dataset bias via causal inference and contrastive learning, and outperforms prior arts across diverse VLN benchmarks.
CVPR 2024
InstructDet
INSTRUCTDET: DIVERSIFYING REFERRING OBJECT DETECTION WITH GENERALIZED INSTRUCTIONS
Ronghao Dang, Jiangyan Feng, Haodong Zhang, Chongjian GE, Lin Song, Lijun Gong, Chengju Liu, Qijun Chen, Feng Zhu, Rui Zhao, Yibing Song
We propose InstructDET, leveraging foundation models to construct InDET with diverse instructions for referring object detection. The pipeline enables automatic data expansion from any images equipped with bounding boxes.
ICLR 2024
DAT
Search for or Navigate to? Dual Adaptive Thinking for Object Navigation
Ronghao Dang, Liuyi Wang, Zongtao He, Shuai Su, Chengju Liu, Qijun Chen
We propose DAT, a dual adaptive reasoning paradigm distinguishing searching and navigating stages in object navigation. It dynamically switches strategies leveraging object association and target location awareness.
ICCV 2023
MT
Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation
Ronghao Dang, Lu Chen, Liuyi Wang, Zongtao He, Chengju Liu, Qijun Chen
We propose a meta-ability decoupling paradigm to integrate object navigation methods. Based on it, the multiple thinking model decouples meta-abilities and adopts a collaboration module, establishing new interpretability for object navigation.
ICML 2023
DSRG
A Dual Semantic-Aware Recurrent Global-Adaptive Network for Vision-and-Language Navigation
Liuyi Wang, Zongtao He, Jiagui Tang, Ronghao Dang, Naijia Wang, Chengju Liu, Qijun Chen
Vision-and-Language Navigation suffers from insufficient cross-modal semantic mining and inadequate differentiated visual memory, so we construct a dual semantic-aware recurrent global-adaptive network equipped with dual semantic modules and innovative memory mechanisms.
IJCAI 2023
DOA
Unbiased Directed Object Attention Graph for Object Navigation
Dang Ronghao, Zhuofan Shi, Liuyi Wang, Zongtao He, Chengju Liu, Qijun Chen
We propose a directed object attention graph to alleviate attention bias for object navigation. We introduce two unbiased adaptive attention mechanisms and a compact adaptive branch energy distribution module for feature distinction.
ACMMM 2023

● Selected Honors & Awards

  • DAMO Academy's Excellence Award, Alibaba DAMO Academy, 2025.
  • National Scholarship, Ministry of Education of China, 2023.
  • Excellent Graduation Project, Tongji University (Quota: 2 recipients per year), 2021.
  • Champion, Home League, RoboCup China Open, 2021.
  • National Second Award, Artificial Intelligence Challenge Track, China Computer Design Competition, 2020.
  • First Class Scholarship, Tongji University, 2018, 2020, 2022.

● Academic Services

Conference Reviewer:
Conference on Computer Vision and Pattern Recognition (CVPR)
International Conference on Computer Vision (ICCV)
European Conference on Computer Vision (ECCV)
Conference on Neural Information Processing Systems (NeurIPS)
International Conference on Learning Representations (ICLR)
International Conference on Machine Learning (ICML)
International Conference on Robotics and Automation (ICRA)
International Conference on Intelligent Robots and Systems (IROS)
Journal Reviewer:
Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
Transactions on Neural Networks and Learning Systems (TNNLS)
Transactions on Circuits and Systems for Video Technology (TCSVT)
Transactions on Multimedia (TMM)

● Contact

Emaildrh1710013267@163.com
Phone+86 173 1781 3949
WeChatdrh1710013267
LocationShanghai, China