Summary of Correlated Proxies: a New Definition and Improved Mitigation For Reward Hacking, by Cassidy Laidlaw et al.
Correlated Proxies: A New Definition and Improved Mitigation for Reward Hackingby Cassidy Laidlaw, Shivam Singhal,…
Correlated Proxies: A New Definition and Improved Mitigation for Reward Hackingby Cassidy Laidlaw, Shivam Singhal,…
How Well Can Transformers Emulate In-context Newton’s Method?by Angeliki Giannou, Liu Yang, Tianhao Wang, Dimitris…
Reliable, Adaptable, and Attributable Language Models with Retrievalby Akari Asai, Zexuan Zhong, Danqi Chen, Pang…
G4-Attention: Deep Learning Model with Attention for predicting DNA G-Quadruplexesby Shrimon Mukherjee, Pulakesh Pramanik, Partha…
Rehabilitation Exercise Quality Assessment through Supervised Contrastive Learning with Hard and Soft Negativesby Mark Karlov,…
A Zero-Shot Reinforcement Learning Strategy for Autonomous Guidewire Navigationby Valentina Scarponi, Michel Duprez, Florent Nageotte,…
EasyQuant: An Efficient Data-free Quantization Algorithm for LLMsby Hanlin Tang, Yifu Sun, Decheng Wu, Kai…
Data Collaboration Analysis with Orthonormal Basis Selection and Alignmentby Keiyu Nosaka, Yuichi Takano, Akiko YoshiseFirst…
Semi-Supervised Graph Representation Learning with Human-centric Explanation for Predicting Fatty Liver Diseaseby So Yeon Kim,…
Dynamic Gaussian Graph Operator: Learning parametric partial differential equations in arbitrary discrete mechanics problemsby Chu…