Europe
Doubly Mild Generalization for Offline Reinforcement Learning Yixiu Mao 1, Qi Wang 1, Y un Qu
Offline Reinforcement Learning (RL) suffers from the extrapolation error and value overestimation. From a generalization perspective, this issue can be attributed to the over-generalization of value functions or policies towards out-of-distribution (OOD) actions.
FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
Yixiao Ge, Zhuowan Li, Haiyu Zhao, Guojun Yin, Shuai Yi, Xiaogang Wang, hongsheng Li
Neural Information Processing Systems http://nips.cc/
Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics
Niru Maheswaranathan, Alex Williams, Matthew Golub, Surya Ganguli, David Sussillo
Neural Information Processing Systems http://nips.cc/
Emergent Communication in Interactive Sketch Question Answering
Ironically, previous works neglect multi-round interaction, which is indispensable in human communication.
Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
Bruno Korbar, Du Tran, Lorenzo Torresani
Toeasethelearning, wedemonstrate thatitisbeneficial toadoptacurriculum learning strategy [23], where harder negatives are introduced after an initial stage of learning on easiernegatives.
Sublinear Time Low-Rank Approximation of Distance Matrices
In an attempt to reduce their description size, we study low rank approximation of such matrices.
WenMind: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Classical Literature and Language Arts Supplementary Material
For details on M1-M5, please refer to Appendix B.3.
Identifying Causal Effects via Context-specific Independence Relations
Santtu Tikka, Antti Hyttinen, Juha Karvanen
Causal effect identification considers whether an interventional probability distribution can be uniquely determined from a passively observed distribution in a given causal structure.