Scholar
Fanfan Liu
Google Scholar ID: LPaXZEUAAAAJ
Researcher, Meituan
Computer vision
Multi-modal
Embodied AI
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
393
H-index
5
i10-index
4
Publications
9
Co-authors
4
list available
Contact
No contact links provided.
Publications
10 items
Flexible Entropy Control in RLVR with Gradient-Preserving Perspective
2026
Cited
0
TreeCUA: Efficiently Scaling GUI Automation with Tree-Structured Verifiable Evolution
2026
Cited
0
Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR
2026
Cited
0
Learning When to Look: A Disentangled Curriculum for Strategic Perception in Multimodal Reasoning
2025
Cited
0
Context Cascade Compression: Exploring the Upper Limits of Text Compression
2025
Cited
0
Metis-HOME: Hybrid Optimized Mixture-of-Experts for Multimodal Reasoning
2025
Cited
0
Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning
2025
Cited
0
DataPlatter: Boosting Robotic Manipulation Generalization with Minimal Costly Data
2025
Cited
0
Load more
Resume (English only)
Co-authors
4 total
Lin Ma
Meituan
Feng yan
meituan
Chengjian Feng
Meituan
Haoran Wei
Researcher, DeepSeek
