Yizhe Xiong
Scholar

Yizhe Xiong

Google Scholar ID: HptpkCYAAAAJ
Tsinghua University
Transfer LearningComputer VisionLarge Language Models
Citations & Impact
All-time
Citations
101
 
H-index
5
 
i10-index
3
 
Publications
19
 
Co-authors
11
list available
Resume (English only)
Academic Achievements
  • Three papers accepted by EMNLP 2025; 'Temporal Scaling Law for Large Language Models' selected for Oral Presentation.
  • Two papers accepted by NAACL 2025 main conference.
  • One paper accepted by ICASSP 2025 ('LBPE: Long-token-first Tokenization to Improve Large Language Models').
  • 'Scaffold-BPE' accepted by AAAI 2025.
  • One paper accepted by COLING 2025 ('Breaking the Stage Barrier...', equal contribution).
  • 'PYRA: Parallel Yielding Re-Activation...' accepted by ECCV 2024.
  • 'Confidence-based Visual Dispersal...' accepted by ICCV 2023.
  • Released a survey on the Next Token Prediction paradigm in December 2024 with public GitHub and arXiv links.
  • Multiple works on efficient LLM training/inference, tokenization optimization, long-context extension, and parameter-efficient fine-tuning (PEFT).