Shengyi Qian
Scholar

Shengyi Qian

Google Scholar ID: PwKfQq0AAAAJ
Research Scientist, Meta FAIR
Computer VisionVision Language ModelRobotics
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
637
 
H-index
13
 
i10-index
14
 
Publications
20
 
Co-authors
36
list available
Contact
No contact links provided.
Publications
8 items
Beyond Language Modeling: An Exploration of Multimodal Pretraining
2026
Cited
0
Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking
2026
Cited
0
Learning Personalized Agents from Human Feedback
2026
Cited
0
DigiData: Training and Evaluating General-Purpose Mobile Control Agents
2025
Cited
0
DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data
2025
Cited
0
3D-MVP: 3D Multiview Pretraining for Robotic Manipulation
2024
Cited
1
Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning
2024
Cited
2
3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination
arXiv.org · 2024
Cited
6
Resume (English only)
Co-authors
36 total
David Fouhey
David Fouhey
New York University
Jianing (Jed) Yang
Jianing (Jed) Yang
Ph.D. Student, University of Michigan
Weifeng Chen
Weifeng Chen
Research Scientist, GenAI @ Meta Superintelligence Labs
Xuweiyi Chen
Xuweiyi Chen
University of Virginia
Co-author 5
Co-author 5
Jing Zhu
Jing Zhu
University of Michigan
Yuhang Zhou
Yuhang Zhou
Research Scientist, Meta
Linyi Jin
Linyi Jin
University of Michigan