Xiaojian Ma

North China Electric Power University — China

Computer Science · Physical Sciences

16h-index1.5kcitations83works2.42yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Multimodal Machine Learning Applications(19), Biofuel production and bioconversion(13), Natural Language Processing Techniques(9), Human Pose and Action Recognition(8), Catalysis for Biomass Conversion(7)

Publications82 total

Adaptive Relay Hindsight Experience Replay for Sequential Manipulation Tasks with Sparse Rewards
2025
Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation
arXiv (Cornell University)·2025Open Access
SOC-SOH estimation method for lithium iron phosphate battery considering energy storage operating conditions and current mutation detection
Ionics·2025
ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting
2025· 1 cited
FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation
arXiv (Cornell University)·2025Open Access
TongUI: Internet-Scale Trajectories from Multimodal Web Tutorials for Generalized GUI Agents
arXiv (Cornell University)·2025Open Access
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse
arXiv (Cornell University)·2025Open Access
An Enhanced Belief Divergence Measure Based on Belief Interval And its Applications in Multi-Sensor Information Fusion
SSRN Electronic Journal·2025Open Access
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse
2025· 2 citedOpen Access
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding
arXiv (Cornell University)·2024Open Access
Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
arXiv (Cornell University)·2024Open Access
GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents
arXiv (Cornell University)·2024Open Access
<b>JARVIS</b>-1: Open-World Multi-Task Agents With Memory-Augmented Multimodal Language Models
IEEE Transactions on Pattern Analysis and Machine Intelligence·2024· 12 cited
ROCKET-1: Mastering Open-World Interaction with Visual-Temporal Context Prompting
arXiv (Cornell University)·2024Open Access
Multi-modal Situated Reasoning in 3D Scenes
arXiv (Cornell University)·2024· 3 citedOpen Access
Conflict Management Method Based on a New Belief Divergence in Evidence Theory
IEICE Transactions on Information and Systems·2024· 3 citedOpen Access
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
arXiv (Cornell University)·2024Open Access
Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting
arXiv (Cornell University)·2024· 1 citedOpen Access
VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding
arXiv (Cornell University)·2024· 2 citedOpen Access
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
arXiv (Cornell University)·2024· 9 citedOpen Access
page 1 of 5Next →

Frequent Co-authors

Shaofei Cai(8), Siyuan Huang(7), Song‐Chun Zhu(7), Xiuli Han(6), Qing Li(6), Anji Liu(6), Baoxiong Jia(5), Zihao Wang(5), Yitao Liang(5), Chun Chang(4), Chun Chang(4), Jiangyong Huang(4), Haowei Lin(4), Peilin Cen(3), Shuqi Fang(3), Anji Liu(3), Yitao Liang(3), Zilong Zheng(3), Yitao Liang(3), Xiongkun Linghu(3)