Zaijing Li
Scholar

Zaijing Li

Google Scholar ID: TDBF2UoAAAAJ
Harbin Institute of Technology, Shenzhen
Open-World AgentMultimodal Large Language ModelMultimodal Sentiment Analysis
Citations & Impact
All-time
Citations
287
 
H-index
7
 
i10-index
5
 
Publications
11
 
Co-authors
6
list available
Resume (English only)
Academic Achievements
  • Optimus-3: Towards Generalist Multimodal Minecraft Agents with Scalable Task Experts, arXiv 2025
  • Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills, arXiv 2025
  • Optimus-2: Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy, CVPR 2025
  • Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks, NeurIPS 2024
  • HCQA @ Ego4D EgoSchema Challenge 2024, CVPRW 2024
  • ObjectNLQ@ Ego4D Episodic Memory Challenge 2024, CVPRW 2024
  • Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought, arXiv 2024
  • UniSA: Unified Generative Framework for Sentiment Analysis, ACM MM 2023
Research Experience
  • Currently exploring internship and collaboration opportunities in open-world agent research.
Background
  • Research Interests: Multimodal large language models, reinforcement learning, and open world agents. Currently a Ph.D. student at the School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen).
Miscellany
  • Currently seeking internship and collaboration opportunities in open-world agent research.