Fangxun Shu
Scholar

Fangxun Shu

Google Scholar ID: 8Fq3EFkAAAAJ
Bytedance
Multimodal
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
280
 
H-index
9
 
i10-index
8
 
Publications
17
 
Co-authors
4
list available
Contact
GitHubOpen ↗
Publications
7 items
SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning
2025
Cited
0
SAIL-VL2 Technical Report
2025
Cited
0
Fast-Slow Thinking for Large Vision-Language Model Reasoning
2025
Cited
0
CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation
2025
Cited
0
MINT: Multi-modal Chain of Thought in Unified Generative Models for Enhanced Image Generation
2025
Cited
0
Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
2025
Cited
0
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts
arXiv.org · 2024
Cited
4
Resume (English only)
Academic Achievements
  • May 2025: 1 paper accepted to ACL'25 (T2I-FactualBench)
  • Jan. 2025: 3 papers accepted to ICLR'25 (LLaVA-MoD, ReKV, ARM)
  • Dec. 2024: 2 papers accepted to AAAI'25 (MARS, HSA-DPO)
  • May 2024: 1 paper accepted to TMM'24 (MAC)
  • Reviewer for CVPR, ICLR, NeurIPS, and ICML
Co-authors
4 total
Cihang Xie
Cihang Xie
Assistant Professor, University of California, Santa Cruz
si liu
si liu
Beihang University
Jinqiao Wang 王金桥
Jinqiao Wang 王金桥
Professor, Institute of Automation,Chinese Academy of Science
Hongsheng Li (李鸿升)
Hongsheng Li (李鸿升)
The Chinese University of Hong Kong