Showing 1–20 of 32 results
/ Date/ Name
Dec 11, 2025TPV: Parameter Perturbations Through the Lens of Test Prediction VarianceJan 19, 2024Causal Layering via Conditional EntropyJan 15, 2024Editing Arbitrary Propositions in LLMs without Subject LabelsAug 11, 2023BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous AgentsAug 4, 2023Retroformer: Retrospective Large Language Agents with Policy Gradient OptimizationJul 18, 2023REX: Rapid Exploration and eXploitation for AI AgentsMar 10, 2023On the Unlikelihood of D-SeparationJan 25, 2023Salesforce CausalAI Library: A Fast and Scalable Framework for Causal Analysis of Time Series and Tabular DataOct 21, 2021Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain GeneralizationOct 19, 2021Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAEOct 19, 2021Learning Rich Nearest Neighbor Representations from Self-supervised EnsemblesSep 20, 2021Merlion: A Machine Learning Library for Time SeriesDec 28, 2020Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts GeneralizationFeb 21, 2020The Break-Even Point on Optimization Trajectories of Deep Neural NetworksFeb 20, 2020Neural Bayes: A Generic Parameterization Method for Unsupervised Representation LearningOct 1, 2019Predicting with High Correlation FeaturesJun 5, 2019How to Initialize your Network? Robust Initialization for WeightNorm & ResNetsJan 11, 2019The Benefits of Over-parameterization at Initialization in Deep ReLU NetworksOct 6, 2018h-detach: Modifying the LSTM Gradient Towards Better OptimizationJun 22, 2018On the Spectral Bias of Neural Networks