Stella Biderman

Stella Biderman on Hugging Face Daily Papers: 13 papers, 2 in the top 3 of their day, 316 upvotes.

1. The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text 36 upvotes, #7 of 2025-06-06
2. When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research 9 upvotes, #23 of 2025-05-20
3. Open Problems in Mechanistic Interpretability 16 upvotes, #5 of 2025-01-29
4. Towards Best Practices for Open Datasets for LLM Training 47 upvotes, #1 of 2025-01-16
5. Bridging the Data Provenance Gap Across Text, Speech and Video 6 upvotes, #10 of 2024-12-25
6. Consent in Crisis: The Rapid Decline of the AI Data Commons 9 upvotes, #11 of 2024-07-23
7. LLM Circuit Analyses Are Consistent Across Training and Scale 4 upvotes, #12 of 2024-07-16
8. Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive? 5 upvotes, #8 of 2024-06-10
9. Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence 23 upvotes, #4 of 2024-04-10
10. On the Societal Impact of Open Foundation Models 13 upvotes, #6 of 2024-03-14
11. Suppressing Pink Elephants with Direct Principle Feedback 10 upvotes, #13 of 2024-02-13
12. Llemma: An Open Language Model For Mathematics 56 upvotes, #1 of 2023-10-17
13. LEACE: Perfect linear concept erasure in closed form 2 upvotes, #7 of 2023-06-07

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.