Soham De

sohamde's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 7 papers 3 months ago

Resurrecting Recurrent Neural Networks for Long Sequences

Paper • 2303.06349 • Published Mar 11, 2023 • 1

ConvNets Match Vision Transformers at Scale

Paper • 2310.16764 • Published Oct 25, 2023 • 21

Characterizing signal propagation to close the performance gap in unnormalized ResNets

Paper • 2101.08692 • Published Jan 21, 2021 • 2

High-Performance Large-Scale Image Recognition Without Normalization

Paper • 2102.06171 • Published Feb 11, 2021

On the Universality of Linear Recurrences Followed by Nonlinear Projections

Paper • 2307.11888 • Published Jul 21, 2023 • 1

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models

Paper • 2402.19427 • Published Feb 29, 2024 • 57

Gemma: Open Models Based on Gemini Research and Technology

Paper • 2403.08295 • Published Mar 13, 2024 • 50

authored a paper over 1 year ago

RecurrentGemma: Moving Past Transformers for Efficient Open Language Models

Paper • 2404.07839 • Published Apr 11, 2024 • 48