22 citations · 23 across the 11 of their papers we have counts for
7 papers · 1 filter
Elite-Weighted Supervised Fine-tuning for Goal-Directed Molecular Optimization
Shiyun Wa, Yifei Wang, Anna G. Green +2
Goal-directed optimization is essential for steering molecular generators to propose candidates with desired properties. However, it is often implemented with policy-gradient reinf…
On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy
Jingyi Cui, Qi Zhang, Yifei Wang +1
Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the features learned by large language models (LLMs). By reconstructing features with sparsely…
Can In-context Learning Really Generalize to Out-of-distribution Tasks?
Qixun Wang, Yifei Wang, Yisen Wang +1
In this work, we explore the mechanism of in-context learning (ICL) on out-of-distribution (OOD) tasks that were not encountered during training. To achieve this, we conduct synthe…
How to Craft Backdoors with Unlabeled Data Alone?
Yifei Wang, Wenhan Ma, Stefanie Jegelka +1
Relying only on unlabeled data, Self-supervised learning (SSL) can learn rich features in an economical and scalable way. As the drive-horse for building foundation models, SSL has…
Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning
Xiaojun Guo, Yifei Wang, Zeming Wei +1
With the prosperity of contrastive learning for visual representation learning (VCL), it is also adapted to the graph domain and yields promising performance. However, through a sy…
Towards Control-Centric Representations in Reinforcement Learning from Images
Chen Liu, Hongyu Zang, Xin Li +5
Image-based Reinforcement Learning is a practical yet challenging task. A major hurdle lies in extracting control-centric representations while disregarding irrelevant information.…
Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
Zeming Wei, Yifei Wang, Ang Li +2
Large Language Models (LLMs) have shown remarkable success in various tasks, yet their safety and the risk of generating harmful content remain pressing concerns. In this paper, we…