Fanhu Zeng
Scholar

Fanhu Zeng

Google Scholar ID: YSp1cH0AAAAJ
Institute of Automation, Chinese Academy of Sciences
Multimodal LLMTrustworthy AIEfficient Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
158
 
H-index
7
 
i10-index
4
 
Publications
18
 
Co-authors
3
list available
Contact
Emailchallengezengfh@gmail.comGitHubOpen ↗LinkedInOpen ↗
Publications
19 items
CL-VISTA: Benchmarking Continual Learning in Video Large Language Models
2026
Cited
0
Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients
2026
Cited
0
Imagination Helps Visual Reasoning, But Not Yet in Latent Space
2026
Cited
0
HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation
2026
Cited
0
VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?
2025
Cited
0
MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark
2025
Cited
0
A Comprehensive Survey on Continual Learning in Generative Models
2025
Cited
0
Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration
2025
Cited
0
Resume (English only)
Academic Achievements
  • NeurIPS 2025 Spotlight paper: 'RobustMerge' (acceptance rate: 3.1%)
  • EMNLP 2025 accepted paper: 'ModalPrompt'
  • ICCV 2025 accepted paper: 'FCIT'
  • Two ACL 2025 accepted papers: 'HiDe-LLaVA' and 'ChartEdit'
  • CVPR 2025 accepted paper: 'MambaIC'
  • ICLR 2025 accepted paper: 'Local-Prompt'
  • Contributed to MCITlib: a Multimodal Continual Instruction Tuning Library and Benchmark
Co-authors
3 total
Fei Zhu
Fei Zhu
Institute of Automation, CAS; Hong Kong Institute of Science & Innovation, CAS
Hao Tang
Hao Tang
Peking University | CMU | ETH Zurich | University of Oxford | University of Trento | NEU | IIAI
Cheng-Lin Liu
Cheng-Lin Liu
Institute of Automation, Chinese Academy of Sciences