Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models Paper • 2405.20541 • Published May 30, 2024 • 22
Pipelined Backpropagation at Scale: Training Large Models without Batches Paper • 2003.11666 • Published Mar 25, 2020
Memory Efficient 3D U-Net with Reversible Mobile Inverted Bottlenecks for Brain Tumor Segmentation Paper • 2104.09648 • Published Apr 19, 2021
RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid Network Paper • 2206.14098 • Published Jun 28, 2022
Improving Language Models with Advantage-based Offline Policy Gradients Paper • 2305.14718 • Published May 24, 2023 • 2
Towards Characterizing Domain Counterfactuals For Invertible Latent Causal Models Paper • 2306.11281 • Published Jun 20, 2023
StarCraftImage: A Dataset For Prototyping Spatial Reasoning Methods For Multi-Agent Environments Paper • 2401.04290 • Published Jan 9, 2024 • 3
CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images Paper • 2310.16825 • Published Oct 25, 2023 • 33
Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests Paper • 2107.06929 • Published Jul 14, 2021