Scholar
Baohao Liao
Google Scholar ID: Fbys5c8AAAAJ
PhD at the Language Technology Lab, University of Amsterdam
Citations & Impact
Citations
279
H-index
9
i10-index
8
Publications
20
Co-authors
31
list available
Publications
Resume
Academic Achievements
- NeurIPS 2024: First author of “3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability”
- NeurIPS 2023: First author of “Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning”
- ICML 2025: Co-first author of “Reward-Guided Speculative Decoding for Efficient LLM Reasoning”
- ACL Findings 2025: Published “Unilogit” and “ClusComp”
- EMNLP 2024: First author of “Apiq: Finetuning of 2-bit quantized large language model”
- EMNLP Findings 2024: Contributed to “The SIFo Benchmark” and other papers
- ACL 2023: First author of “Parameter-Efficient Fine-Tuning without Introducing New Latency”
- EMNLP Findings 2022: First author of “Mask more and mask later”
- WMT 2024: Co-authored “IKUN for WMT24 General MT Task”, achieving 7 first places and 5 second places in the General Task
- Multiple papers accepted at top-tier conferences including NeurIPS, ICML, ACL, and EMNLP
