Aditya K Surikuchi
@akskuchi.bsky.social
PhD Candidate @University of Amsterdam. Working on understanding language generation from visual events—particularly from a "creative" POV!
🔗 akskuchi.github.io
🔗 akskuchi.github.io
Reposted by Aditya K Surikuchi
What makes an image memorable? And can we predict image memorability using pretrained vision encoders? We explored activations, attention distributions, image patch uniformity and sparse autoencoder losses using image representations across the layers of CLIP, DINOv2 and SigLIP2.
October 15, 2025 at 9:10 AM
What makes an image memorable? And can we predict image memorability using pretrained vision encoders? We explored activations, attention distributions, image patch uniformity and sparse autoencoder losses using image representations across the layers of CLIP, DINOv2 and SigLIP2.
Reposted by Aditya K Surikuchi
🌍Introducing BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data!
LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data
We extend this effort to 45 new languages!
LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data
We extend this effort to 45 new languages!
October 15, 2025 at 10:53 AM
🌍Introducing BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data!
LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data
We extend this effort to 45 new languages!
LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data
We extend this effort to 45 new languages!
Reposted by Aditya K Surikuchi
Delighted to share that our paper "Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization" (joint work with @arianna-bis.bsky.social and Raquel Fernández) got accepted to the main conference of #EMNLP
Can't wait to discuss our work at #EMNLP2025 in Suzhou this November!
Can't wait to discuss our work at #EMNLP2025 in Suzhou this November!
Do LLMs assume demographic information based on stereotypes?
We (@arianna-bis.bsky.social, Raquel Fernández and I) answered this question in our new paper: "Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization".
🧵
arxiv.org/abs/2505.16467
We (@arianna-bis.bsky.social, Raquel Fernández and I) answered this question in our new paper: "Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization".
🧵
arxiv.org/abs/2505.16467
August 21, 2025 at 8:59 AM
Delighted to share that our paper "Reading Between the Prompts: How Stereotypes Shape LLM's Implicit Personalization" (joint work with @arianna-bis.bsky.social and Raquel Fernández) got accepted to the main conference of #EMNLP
Can't wait to discuss our work at #EMNLP2025 in Suzhou this November!
Can't wait to discuss our work at #EMNLP2025 in Suzhou this November!
Reposted by Aditya K Surikuchi
Our paper on multilingual reasoning is accepted to Findings of #EMNLP2025! 🎉 (OA: 3/3/3.5/4)
We show SOTA LMs struggle with reasoning in non-English languages; prompt-hack & post-training improve alignment but trade off accuracy.
📄 arxiv.org/abs/2505.22888
See you in Suzhou! #EMNLP
We show SOTA LMs struggle with reasoning in non-English languages; prompt-hack & post-training improve alignment but trade off accuracy.
📄 arxiv.org/abs/2505.22888
See you in Suzhou! #EMNLP
August 20, 2025 at 8:02 PM
Our paper on multilingual reasoning is accepted to Findings of #EMNLP2025! 🎉 (OA: 3/3/3.5/4)
We show SOTA LMs struggle with reasoning in non-English languages; prompt-hack & post-training improve alignment but trade off accuracy.
📄 arxiv.org/abs/2505.22888
See you in Suzhou! #EMNLP
We show SOTA LMs struggle with reasoning in non-English languages; prompt-hack & post-training improve alignment but trade off accuracy.
📄 arxiv.org/abs/2505.22888
See you in Suzhou! #EMNLP
Reposted by Aditya K Surikuchi
What a privilege to have #CCN2025 in (an exceptionally warm and sunny) Amsterdam this year!
It was my first time attending the conference, and being surrounded by so many talented researchers whose interests are similar to mine has been a deeply enriching experience ✨
It was my first time attending the conference, and being surrounded by so many talented researchers whose interests are similar to mine has been a deeply enriching experience ✨
August 17, 2025 at 1:46 PM
What a privilege to have #CCN2025 in (an exceptionally warm and sunny) Amsterdam this year!
It was my first time attending the conference, and being surrounded by so many talented researchers whose interests are similar to mine has been a deeply enriching experience ✨
It was my first time attending the conference, and being surrounded by so many talented researchers whose interests are similar to mine has been a deeply enriching experience ✨