iiinova — where your digital self keeps evolving

Reposted by Neehar Kondapaneni

Oisin Mac Aodha @oisinmacaodha.bsky.social · 03/12/2025

Want to discover and visualise the differences between two different machine learning models? We will be presenting Neehar's work on "Representational Difference Explanations" at #NeurIPS2025 in San Diego from 4:30pm to 7:30pm PT today. Poster #1115. Full paper: arxiv.org/abs/2505.23917

0102

Reposted by Neehar Kondapaneni

brendan o’connor @brenocon.bsky.social · 18/11/2025

the way this is going the only trustworthy information will be from in-person interviews. for annotation projects i find it much easier to trust small numbers of expert or local students annotators, compared to broad-audience online recruiting

0111

Reposted by Neehar Kondapaneni

Jacquelyn Gill @jacquelyngill.bsky.social · 19/11/2025

ChatGPT’s signature writing style is everywhere now, and I hate it. It reminds me of when we tried mixing all the beverages at the soda fountain in middle school. We didn’t actually create the perfect drink, we just made a cloying monstrosity that lost everything good about its constituent parts.

672026354

Neehar Kondapaneni @therealpaneni.bsky.social · 19/11/2025

Excited to share our paper Representational Difference Explanations (RDX) was accepted to #NeurIPS2025! 🎉RDX is a new method for model diffing designed to isolate 🔍 representational differences. 1/7

184

Neehar Kondapaneni @therealpaneni.bsky.social · 08/07/2025

You’ve generated 10k concepts with your favorite XAI method -- now what? Many concepts you’ve found are fairly obvious and uninteresting. What if you could 𝑠𝑢𝑏𝑡𝑟𝑎𝑐𝑡 obvious concepts away and focus on the more complex ones? We tackle this in our latest preprint!

112

Neehar Kondapaneni @therealpaneni.bsky.social · 11/04/2025

Have you ever wondered what makes two models different? We all know the ViT-Large performs better than the Resnet-50, but what visual concepts drive this difference? Our new ICLR 2025 paper addresses this question! nkondapa.github.io/rsvc-page/

1259

Reposted by Neehar Kondapaneni

Angelina Wang @angelinawang.bsky.social · 17/02/2025

Our new piece in Nature Machine Intelligence: LLMs are replacing human participants, but can they simulate diverse respondents? Surveys use representative sampling for a reason, and our work shows how LLM training prevents accurate simulation of different human identities.

914935