Beidi Chen

Beidi Chen on Hugging Face Daily Papers: 7 papers, 4 in the top 3 of their day, 396 upvotes.

1. HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading 10 upvotes, #20 of 2025-02-19
2. Nearest Neighbor Speculative Decoding for LLM Generation and Attribution 12 upvotes, #4 of 2024-05-30
3. Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding 47 upvotes, #1 of 2024-04-26
4. TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding 14 upvotes, #7 of 2024-04-19
5. Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length 52 upvotes, #2 of 2024-04-16
6. GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection 150 upvotes, #1 of 2024-03-07
7. Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time 14 upvotes, #3 of 2023-10-27

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.