Sangmin Bae

Sangmin Bae on Hugging Face Daily Papers: 4 papers, 2 in the top 3 of their day, 162 upvotes.

1. Hybrid Architectures for Language Models: Systematic Analysis and Design Insights 31 upvotes, #7 of 2025-10-07
2. Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation 57 upvotes, #2 of 2025-07-15
3. Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA 5 upvotes, #16 of 2024-10-29
4. Block Transformer: Global-to-Local Language Modeling for Fast Inference 30 upvotes, #1 of 2024-06-06

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.