Scholar
Yongyuan Liang
Google Scholar ID: GQToORIAAAAJ
University of Maryland, College Park
Citations & Impact
Citations
715
H-index
13
i10-index
14
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Multiple papers accepted at top-tier conferences including NeurIPS 2025, CVPR 2025, ICLR 2025, and ICML 2024
- Awarded Dean's Fellowship in 2024
- Paper 'ACE' selected as a long oral presentation at ICML 2024
- Three papers accepted at ICLR 2024, including two spotlights
- Leads or contributes to open-source initiatives such as Awesome-Generalist-Agents, Magma, and Make-An-Agent
- Notable works include: ROVER (benchmark for multimodal reasoning), LEMON (3D multimodal model), Avocado (multi-objective alignment framework), and TraceVLA (embodied agent policy model)
Background
- Research focuses on developing foundation models and intelligent agents
- Actively explores both theoretical frameworks and empirical findings, with specific interests in:
- - Large Multimodal Models: Unified models for 2D/3D virtual and physical agentic tasks
- - Alignment: Human preference alignment and cross-modality alignment in post-training
- - Previous research includes Reinforcement Learning, Representations, and Robustness