Jo-Ku Cheng

Orcid: 0009-0004-4165-1384

According to our database1, Jo-Ku Cheng authored at least 7 papers between 2024 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2025
SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding.
CoRR, May, 2025

GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutions.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

SwapTalk: Audio-Driven Talking Face Generation with One-Shot Customization in Latent Space.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Diagram Formalization Enhanced Multi-Modal Geometry Problem Solver.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Enhancing Large Language Models on Domain-specific Tasks: A Novel Training Strategy via Domain Adaptation and Preference Alignment.
Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Beyond Binary Preferences: Semi-Online Label-Free GRACE-KTO with Group-Wise Adaptive Calibration for High-Quality Long-Text Generation.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024
A Fusion Framework of Whitespace Smear Cutting and Swin Transformer for Document Layout Analysis.
Proceedings of the Advanced Intelligent Computing Technology and Applications, 2024


  Loading...