Soham PetkarI am an ML Engineer at Sarvam AI, working on foundation models. My past research focuses on efficient pre-training and evaluation of graph-language multimodal models, alongside exploring interpretability and alignment in real-world scenarios using the linear representation hypothesis. Topics that intrigue me include mechanistic interpretability, alignment, graph-language modeling, deterministic & stochastic reasoning mechanisms, or anything that imparts tacit knowledge to models. Email / GitHub / Google Scholar / ORCID / LinkedIn / X / LessWrong |
|
|
My research focuses on foundation models, graph-language multimodal models, interpretability, and alignment.
|
|
Sarvam 30B and 105B: Open-Source Reasoning LLMs Trained from Scratch in IndiaSoham Petkar and 14 other researchers at Sarvam AI Sarvam AI, 2026 report / model (30B) / model (105B) / Sarvam 30B and 105B are Mixture-of-Experts reasoning models trained from scratch on large-scale, high-quality datasets. Both achieve state-of-the-art results on Indian language benchmarks and are competitive with frontier models on reasoning, coding, and agentic tasks. Open-sourced under Apache 2.0. |
|
A Graph Talks, But Who's Listening? Rethinking Evaluations for Graph-Language ModelsSoham Petkar*, Hari Aakash K*, Anirudh Vempati, Akshit Sinha, Ponnurangam Kumaraguru, Chirag Agarwal ACL 2026 and NeurIPS NPGML Workshop, 2025 arxiv / paper / code / We present a comprehensive rethinking of evaluation methodologies for graph-language models, proposing new benchmarks and evaluation strategies that better capture the true capabilities of these multimodal systems. |
|
AdaptAI: A Personalized Solution to Sense Your Stress, Fix Your Mess, and Boost ProductivitySoham Petkar*, Rushiraj Gadhvi*, Priyansh Desai*, Sidhharth et al. CHI LBW, 2025 arxiv / paper / AdaptAI is a multimodal AI system that enhances productivity and well-being by tailoring interventions to individual needs, integrating egocentric vision, audio, physiological signals, and LLM-driven workflows. |
|
I write about AI, interpretability, and related topics on LessWrong. Below are some of my posts. |
|
June 29, 2024
Exploring how narrow fine-tuning reshapes GPT-2's internal representations, analyzing shifts in activation and embedding spaces, and discovering that fine-tuning induces 'output squishing' that reduces diversity and potentially harms generalization.
Read on LessWrong →
|
|
Design and source code from Jon Barron's website |