Scholar
Wujian Peng
Google Scholar ID: GTuWk9YAAAAJ
Fudan University, Shanghai Innovation Institute
Computer Vision
Large Multimodal Models
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
76
H-index
3
i10-index
2
Publications
6
Co-authors
0
Contact
GitHub
Open ↗
Publications
5 items
LIBERO-Agent: Evaluating General-Purpose Agents for Direct Embodied Manipulation
2026
Cited
0
Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification
2026
Cited
0
Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments
2026
Cited
0
Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
2026
Cited
0
CoMP: Continual Multimodal Pre-training for Vision Foundation Models
arXiv.org · 2025
Cited
0
