59 citations · 87 across the 9 of their papers we have counts for
9 papers
Steering Protein Language Models
Long-Kai Huang, Rongyi Zhu, Bing He +1
Protein Language Models (PLMs), pre-trained on extensive evolutionary data from natural proteins, have emerged as indispensable tools for protein design. While powerful, PLMs often…
Annotation-guided Protein Design with Multi-Level Domain Alignment
Chaohao Yuan, Songyou Li, Geyan Ye +6
The core challenge of de novo protein design lies in creating proteins with specific functions or properties, guided by certain conditions. Current models explore to generate prote…
Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model
Huan Ma, Yan Zhu, Changqing Zhang +5
Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, th…
Can Pre-trained Models Really Learn Better Molecular Representations for AI-aided Drug Discovery?
Ziqiao Zhang, Yatao Bian, Ailin Xie +3
Self-supervised pre-training is gaining increasingly more popularity in AI-aided drug discovery, leading to more and more pre-trained models with the promise that they can extract…
Learning to generate imaginary tasks for improving generalization in meta-learning
Yichen Wu, Long-Kai Huang, Ying Wei
The success of meta-learning on existing benchmarks is predicated on the assumption that the distribution of meta-training tasks covers meta-testing tasks. Frequent violation of th…
Fine-Tuning Graph Neural Networks via Graph Topology induced Optimal Transport
Jiying Zhang, Xi Xiao, Long-Kai Huang +2
Recently, the pretrain-finetuning paradigm has attracted tons of attention in graph learning community due to its power of alleviating the lack of labels problem in many real-world…
Frustratingly Easy Transferability Estimation
Long-Kai Huang, Ying Wei, Yu Rong +2
Transferability estimation has been an essential tool in selecting a pre-trained model and the layers in it for transfer learning, to transfer, so as to maximize the performance on…
Improving Generalization in Meta-learning via Task Augmentation
Huaxiu Yao, Longkai Huang, Linjun Zhang +5
Meta-learning has proven to be a powerful paradigm for transferring the knowledge from previous tasks to facilitate the learning of a novel task. Current dominant algorithms train…
Online Hashing
Long-Kai Huang, Qiang Yang, Wei-Shi Zheng
Although hash function learning algorithms have achieved great success in recent years, most existing hash models are off-line, which are not suitable for processing sequential or…