T. Xu
YOU?
Author Swipe
View article: Improving Recommendation Fairness via Graph Structure and Representation Augmentation
Improving Recommendation Fairness via Graph Structure and Representation Augmentation Open
Graph Convolutional Networks (GCNs) have become increasingly popular in recommendation systems. However, recent studies have shown that GCN-based models will cause sensitive information to disseminate widely in the graph structure, amplify…
View article: Reinforcement Learning from User Feedback
Reinforcement Learning from User Feedback Open
As large language models (LLMs) are increasingly deployed in diverse user facing applications, aligning them with real user preferences becomes essential. Existing methods like Reinforcement Learning from Human Feedback (RLHF) rely on expe…
View article: MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems Open
The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently, but it depends on heterogeneous compute and memory resources. These factors jointly affect system Cost, Accuracy…
View article: Improved corrosion inhibition effect of a green three-component compound to Q235 steel in acidic solution
Improved corrosion inhibition effect of a green three-component compound to Q235 steel in acidic solution Open
Chitosan (Chi), curcumin (Cur) and geraniol (Ger) are natural compounds, which can potentially serve as green corrosion inhibitors. Herein, the corrosion inhibition efficiency (IE) of them was compared. The corrosion rate of 1.5 mM Chi on …
View article: Effects of Lactiplantibacillus plantarum on Metabolites and Flavors in Synthetic Microbiota During Baijiu Fermentation
Effects of Lactiplantibacillus plantarum on Metabolites and Flavors in Synthetic Microbiota During Baijiu Fermentation Open
The distinctive flavor and aroma of Chinese baijiu are closely linked to the microorganisms involved in the fermentation process. Lactiplantibacillus plantarum, a dominant species in the fermentation of Chinese baijiu, has become a promine…
View article: Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following
Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following Open
Large Language Models (LLMs) have demonstrated impressive capabilities in various tasks, including instruction following, which is crucial for aligning model outputs with user expectations. However, evaluating LLMs' ability to follow instr…
View article: The Perfect Blend: Redefining RLHF with Mixture of Judges
The Perfect Blend: Redefining RLHF with Mixture of Judges Open
Reinforcement learning from human feedback (RLHF) has become the leading approach for fine-tuning large language models (LLM). However, RLHF has limitations in multi-task learning (MTL) due to challenges of reward hacking and extreme multi…