Ruomeng Ding
YOU?
Author Swipe
View article: Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs Open
Reward models trained on human preference data have been proven to effectively align Large Language Models (LLMs) with human intent within the framework of reinforcement learning from human feedback (RLHF). However, current reward models h…
View article: Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation
Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation Open
Recent advancements in Large Language Models (LLMs) have revolutionized decision-making by breaking down complex problems into more manageable language sequences referred to as "thoughts". An effective thought design should consider three …
View article: TraceDiag: Adaptive, Interpretable, and Efficient Root Cause Analysis on Large-Scale Microservice Systems
TraceDiag: Adaptive, Interpretable, and Efficient Root Cause Analysis on Large-Scale Microservice Systems Open
Root Cause Analysis (RCA) is becoming increasingly crucial for ensuring the reliability of microservice systems. However, performing RCA on modern microservice systems can be challenging due to their large scale, as they usually comprise h…
View article: ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detection
ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detection Open
Anomaly detection in multivariate time series data is of paramount importance for ensuring the efficient operation of large-scale systems across diverse domains. However, accurately detecting anomalies in such data poses significant challe…
View article: Action Unit Detection with Joint Adaptive Attention and Graph Relation
Action Unit Detection with Joint Adaptive Attention and Graph Relation Open
This paper describes an approach to the facial action unit (AU) detection. In this work, we present our submission to the Field Affective Behavior Analysis (ABAW) 2021 competition. The proposed method uses the pre-trained JAA model as the …