Sashank Pisupati

spisupat

reflectionai

·

https://spisupat.github.io/

AI & ML interests

Alignment & safety, failure modes of intelligence, RL

Recent Activity

upvoted an article 8 days ago

Featuring Every Eval Ever Results on Hugging Face Model Pages

authored a paper 15 days ago

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

upvoted a paper 15 days ago

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

View all activity

Organizations

upvoted an article 8 days ago

Article

Featuring Every Eval Ever Results on Hugging Face Model Pages

+5

deepmage121, evijit, SaylorTwift, janbatzner, borgr, irenesolaiman, julien-c

•

8 days ago

• 42

upvoted a paper 15 days ago

Counsel: A Meta-Evaluation Dataset for Agentic Tasks

Paper • 2606.21627 • Published 19 days ago • 6

upvoted a paper 8 months ago

Language Models are Injective and Hence Invertible

Paper • 2510.15511 • Published Oct 17, 2025 • 70

upvoted a collection over 1 year ago

Selene-1-Mini

13 items • Updated Mar 2 • 9

upvoted a paper over 1 year ago

Atla Selene Mini: A General Purpose Evaluation Model

Paper • 2501.17195 • Published Jan 27, 2025 • 35

upvoted an article over 1 year ago

Article

Selene 1 Mini: the best small language model-as-a-judge

AtlaAI

•

Jan 29, 2025

• 13