wubanggu's picture

1 4

wubanggu

banggu

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation

upvoted a paper 3 months ago

Virtual Width Networks

upvoted a paper 5 months ago

UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning

View all activity

Organizations

None yet

authored a paper 11 months ago

Frac-Connections: Fractional Extension of Hyper-Connections

Paper • 2503.14125 • Published Mar 18, 2025 • 22

authored a paper about 1 year ago

Over-Tokenized Transformer: Vocabulary is Generally Worth Scaling

Paper • 2501.16975 • Published Jan 28, 2025 • 31

authored a paper over 1 year ago

Hyper-Connections

Paper • 2409.19606 • Published Sep 29, 2024 • 26