240 citations · 445 across the 20 of their papers we have counts for
20 papers
Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models
Sheng Shen, Le Hou, Yanqi Zhou +17
Sparse Mixture-of-Experts (MoE) is a neural architecture design that can be utilized to add learnable parameters to Large Language Models (LLMs) without increasing inference cost.…
Token Imbalance Adaptation for Radiology Report Generation
Yuexin Wu, I-Chan Huang, Xiaolei Huang
Imbalanced token distributions naturally exist in text documents, leading neural language models to overfit on frequent tokens. The token imbalance may dampen the robustness of rad…
Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference
Tao Lei, Junwen Bai, Siddhartha Brahma +9
We propose Conditional Adapter (CoDA), a parameter-efficient transfer learning method that also improves inference efficiency. CoDA generalizes beyond standard adapter approaches t…
Large Language Models Can Self-Improve
Jiaxin Huang, Shixiang Shane Gu, Le Hou +4
Large Language Models (LLMs) have achieved excellent performances in various tasks. However, fine-tuning an LLM requires extensive supervision. Human, on the other hand, may improv…
Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation
Ziqi Wang, Yuexin Wu, Frederick Liu +5
Knowledge distillation is one of the primary methods of transferring knowledge from large to small models. However, it requires massive task-specific data, which may not be plausib…
Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classification
Yuexin Wu, Xiaolei Huang
Class imbalance naturally exists when train and test models in different domains. Unsupervised domain adaptation (UDA) augments model performance with only accessible annotations f…
Token Dropping for Efficient BERT Pretraining
Le Hou, Richard Yuanzhe Pang, Tianyi Zhou +4
Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelera…
Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance
Zhuoning Yuan, Yuexin Wu, Zi-Hao Qiu +4
In this paper, we study contrastive learning from an optimization perspective, aiming to analyze and address a fundamental issue of existing contrastive learning methods that eithe…
TADO: Time-varying Attention with Dual-Optimizer Model
Yuexin Wu, Tianyu Gao, Sihao Wang +1
The review-based recommender systems are commonly utilized to measure users preferences towards different items. In this paper, we focus on addressing three main problems existing…
A Gumbel-based Rating Prediction Framework for Imbalanced Recommendation
Yuexin Wu, Xiaolei Huang
Rating prediction is a core problem in recommender systems to quantify user's preferences towards items, however, rating imbalance naturally roots in real-world user ratings that c…
Knowledge Embedding Based Graph Convolutional Network
Donghan Yu, Yiming Yang, Ruohong Zhang +1
Recently, a considerable literature has grown up around the theme of Graph Convolutional Network (GCN). How to effectively leverage the rich structural information in complex graph…
Graph-Revised Convolutional Network
Donghan Yu, Ruohong Zhang, Zhengbao Jiang +2
Graph Convolutional Networks (GCNs) have received increasing attention in the machine learning community for effectively leveraging both the content features of nodes and the linka…
Active Learning for Graph Neural Networks via Node Feature Propagation
Yuexin Wu, Yichong Xu, Aarti Singh +2
Graph Neural Networks (GNNs) for prediction tasks like node classification or edge prediction have received increasing attention in recent machine learning from graphically structu…
StoryGAN: A Sequential Conditional GAN for Story Visualization
Yitong Li, Zhe Gan, Yelong Shen +6
We propose a new task, called Story Visualization. Given a multi-sentence paragraph, the story is visualized by generating a sequence of images, one for each sentence. In contrast…
Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning
Yuexin Wu, Xiujun Li, Jingjing Liu +2
Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm extends Q-learning by integratin…
Unsupervised Cross-lingual Transfer of Word Embedding Spaces
Ruochen Xu, Yiming Yang, Naoki Otani +1
Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding…
Contextual Encoding for Translation Quality Estimation
Junjie Hu, Wei-Cheng Chang, Yuexin Wu +1
The task of word-level quality estimation (QE) consists of taking a source sentence and machine-generated translation, and predicting which words in the output are correct and whic…
Analogical Inference for Multi-Relational Embeddings
Hanxiao Liu, Yuexin Wu, Yiming Yang
Large-scale multi-relational embedding refers to the task of learning the latent representations for entities and relations in large knowledge graphs. An effective and scalable sol…
Review Networks for Caption Generation
Zhilin Yang, Ye Yuan, Yuexin Wu +2
We propose a novel extension of the encoder-decoder framework, called a review network. The review network is generic and can enhance any existing encoder- decoder model: in this p…
Computational Protein Design Using AND/OR Branch-and-Bound Search
Yichao Zhou, Yuexin Wu, Jianyang Zeng
The computation of the global minimum energy conformation (GMEC) is an important and challenging topic in structure-based computational protein design. In this paper, we propose a…