Yaroslav Aksenov

Yaroslav Aksenov on Hugging Face Daily Papers: 5 papers, 3 in the top 3 of their day, 292 upvotes.

1. Train Sparse Autoencoders Efficiently by Utilizing Features Correlation 21 upvotes, #16 of 2025-05-30
2. You Do Not Fully Utilize Transformer's Representation Capacity 33 upvotes, #8 of 2025-02-19
3. Analyze Feature Flow to Enhance Interpretation and Steering in Language Models 53 upvotes, #1 of 2025-02-07
4. Learn Your Reference Model for Real Good Alignment 75 upvotes, #1 of 2024-04-16
5. Linear Transformers with Learnable Kernel Functions are Better In-Context Models 81 upvotes, #1 of 2024-02-19

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.