Summary of Learning Metrics That Maximise Power For Accelerated A/b-tests, by Olivier Jeunen and Aleksei Ustimenko
Learning Metrics that Maximise Power for Accelerated A/B-Testsby Olivier Jeunen, Aleksei UstimenkoFirst submitted to arxiv…
Summary of Return-aligned Decision Transformer, by Tsunehiko Tanaka et al.
Return-Aligned Decision Transformerby Tsunehiko Tanaka, Kenshi Abe, Kaito Ariu, Tetsuro Morimura, Edgar Simo-SerraFirst submitted to…
Summary of Elastic Feature Consolidation For Cold Start Exemplar-free Incremental Learning, by Simone Magistri et al.
Elastic Feature Consolidation for Cold Start Exemplar-Free Incremental Learningby Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais,…
Summary of Discovery Of the Hidden World with Large Language Models, by Chenxi Liu et al.
Discovery of the Hidden World with Large Language Modelsby Chenxi Liu, Yongqiang Chen, Tongliang Liu,…
Summary of In-context Learning Agents Are Asymmetric Belief Updaters, by Johannes A. Schubert et al.
In-context learning agents are asymmetric belief updatersby Johannes A. Schubert, Akshay K. Jagadish, Marcel Binz,…
Summary of A Comparison Between Humans and Ai at Recognizing Objects in Unusual Poses, by Netta Ollikka et al.
A comparison between humans and AI at recognizing objects in unusual posesby Netta Ollikka, Amro…
Summary of Space Group Constrained Crystal Generation, by Rui Jiao et al.
Space Group Constrained Crystal Generationby Rui Jiao, Wenbing Huang, Yu Liu, Deli Zhao, Yang LiuFirst…
Summary of Cross Entropy Versus Label Smoothing: a Neural Collapse Perspective, by Li Guo et al.
Cross Entropy versus Label Smoothing: A Neural Collapse Perspectiveby Li Guo, Keith Ross, Zifan Zhao,…
Summary of Neural Rank Collapse: Weight Decay and Small Within-class Variability Yield Low-rank Bias, by Emanuele Zangrando et al.
Neural Rank Collapse: Weight Decay and Small Within-Class Variability Yield Low-Rank Biasby Emanuele Zangrando, Piero…
Summary of Efficient Sketches For Training Data Attribution and Studying the Loss Landscape, by Andrea Schioppa
Efficient Sketches for Training Data Attribution and Studying the Loss Landscapeby Andrea SchioppaFirst submitted to…