Anton Razzhigaev

Anton Razzhigaev on Hugging Face Daily Papers: 10 papers, 7 in the top 3 of their day, 1,120 upvotes.

1. Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs 100 upvotes, #2 of 2026-09-25
2. Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution 86 upvotes, #6 of 2026-08-11
3. SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens 45 upvotes, #5 of 2025-08-12
4. Through the Looking Glass: Common Sense Consistency Evaluation of Weird Images 29 upvotes, #9 of 2025-05-20
5. I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders 110 upvotes, #1 of 2025-03-25
6. Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders 212 upvotes, #1 of 2025-03-11
7. LLM-Microscope: Uncovering the Hidden Role of Punctuation in Context Memory of Transformers 155 upvotes, #1 of 2025-02-24
8. Your Transformer is Secretly Linear 120 upvotes, #1 of 2024-05-22
9. OmniFusion Technical Report 71 upvotes, #1 of 2024-04-10
10. Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion 79 upvotes, #1 of 2023-10-06

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.