Showing 1–10 of 10 results
/ Date/ Name
Jul 10, 2024Uncovering Layer-Dependent Activation Sparsity Patterns in ReLU TransformersApr 13, 2018A Deep Learning Approach to Fast, Format-Agnostic Detection of Malicious Web ContentMay 16, 2022An Empirical Investigation of Representation Learning for ImitationMar 13, 2019ALOHA: Auxiliary Loss Optimization for Hypothesis AugmentationApr 14, 2022Retrospective on the 2021 BASALT Competition on Learning from Human FeedbackMay 1, 2025On the generalization of language models from in-context learning and finetuning: a controlled studyMay 25, 2019Adversarial Policies: Attacking Deep Reinforcement LearningMar 4, 2021Clusterability in Neural NetworksMar 10, 2020Pruned Neural Networks are Surprisingly ModularJul 5, 2021The MineRL BASALT Competition on Learning from Human Feedback