Mostafa Elhoushi
Mostafa Elhoushi on Hugging Face Daily Papers: 7 papers, 3 in the top 3 of their day, 270 upvotes.
- Unlocking Lossless Speedups in LLMs via Discrete Diffusion 150 upvotes, #1 of 2026-09-08
- Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference 23 upvotes, #8 of 2026-09-07
- Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation in Transformers 10 upvotes, #21 of 2026-08-27
- any4: Learned 4-bit Numeric Representation for LLMs 6 upvotes, #22 of 2025-07-09
- Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding 47 upvotes, #1 of 2024-04-26
- AST-T5: Structure-Aware Pretraining for Code Generation and Understanding 14 upvotes, #7 of 2024-01-09
- Large Language Models for Compiler Optimization 25 upvotes, #2 of 2023-09-14
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.