1 citations · 1 across the 2 of their papers we have counts for
4 papers
Resource-Efficient Pruning for Transformer via Low-Rank Importance Estimation
Peng Liu, Huibing Zeng, Yiqun Zhang +2
With the rapid development of large-scale pre-trained language models based on Transformer architectures, their high computational and memory costs have become a major obstacle to…
High-Layer Attention Pruning with Rescaling
Songtao Liu, Peng Liu
Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured prunin…
Evaluating Molecule Synthesizability via Retrosynthetic Planning and Reaction Prediction
Songtao Liu, Dandan Zhang, Zhengkai Tu +2
A significant challenge in wet lab experiments with current drug design generative models is the trade-off between pharmacological properties and synthesizability. Molecules predic…
Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models
Songtao Liu, Hanjun Dai, Yue Zhao +1
Molecule synthesis through machine learning is one of the fundamental problems in drug discovery. Current data-driven strategies employ one-step retrosynthesis models and search al…