Robert Csordas

robertcsordas's activity

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

authored 5 papers 8 months ago

Randomized Positional Encodings Boost Length Generalization of Transformers

Paper • 2305.16843 • Published May 26, 2023 • 2

Mindstorms in Natural Language-Based Societies of Mind

Paper • 2305.17066 • Published May 26, 2023 • 3

MoEUT: Mixture-of-Experts Universal Transformers

Paper • 2405.16039 • Published May 25, 2024 • 2

MrT5: Dynamic Token Merging for Efficient Byte-level Language Models

Paper • 2410.20771 • Published Oct 28, 2024 • 3

A Modern Self-Referential Weight Matrix That Learns to Modify Itself

Paper • 2202.05780 • Published Feb 11, 2022

authored a paper almost 2 years ago

SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention

Paper • 2312.07987 • Published Dec 13, 2023 • 41

authored a paper about 2 years ago

Approximating Two-Layer Feedforward Networks for Efficient Transformers

Paper • 2310.10837 • Published Oct 16, 2023 • 11