Deep Learning
Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models
Modularity is a critical design principle for both software systems and artificial intelligence (AI).
Provably Bounding Neural Network Preimages
However, many use cases of neural network verification require solving the inverse problem, or over-approximating the set of inputs that lead to certain outputs.
Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation Adam Fisch, Joshua Maynez, R. Alex Hofer Bhuwan Dhingra Amir Globerson William W. Cohen
Evaluating machine learning models requires evaluation data.
On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences Anonymous Author(s) Affiliation Address email
Recurrent Neural Networks (RNNs) are effective tools for processing sequential data.
GO4Align: Group Optimization for Multi-Task Alignment
Multi-task learning is a promising paradigm for handling several tasks simultaneously using a unified architecture.