I’m a Machine Learning Engineer at Splunk, where I build the Splunk AI Assistant — turns out agents need engineers too. I graduated with a Master’s in Computer Science from Michigan State University, where my thesis focused on Compositionality in Diffusion Models under the supervision of Dr. Vishnu Boddeti. Prior to that, I earned my Bachelor’s degree from IIT, Guwahati.

Publications

1. ICLR'25

   

   CoInD: Enabling Logical Compositions in Diffusion Models

   Sachit Gaudi, Gautam Sreekumar, Vishnu Boddeti

   ICLR, 2025

   ABS PAPER CODE SLIDES POSTER BIB

   How can we learn generative models to sample data with arbitrary logical compositions of statistically independent attributes? The prevailing solution is to sample from distributions expressed as a composition of attributes' conditional marginal distributions under the assumption that they are statistically independent. This paper shows that standard conditional diffusion models violate this assumption, even when all attribute compositions are observed during training. And, this violation is significantly more severe when only a subset of the compositions is observed. We propose CoInD to address this problem. It explicitly enforces statistical independence between the conditional marginal distributions by minimizing Fisher’s divergence between the joint and marginal distributions. The theoretical advantages of CoInD are reflected in both qualitative and quantitative experiments, demonstrating a significantly more faithful and controlled generation of samples for arbitrary logical compositions of attributes. The benefit is more pronounced for scenarios that current solutions relying on the assumption of conditionally independent marginals struggle with, namely, logical compositions involving the NOT operation and when only a subset of compositions are observed during training.

   @inproceedings{gaudi2025coind,
     title={CoInD: Enabling Logical Compositions in Diffusion Models},
     author={Sachit Gaudi and Gautam Sreekumar and Vishnu Boddeti},
     booktitle={The Thirteenth International Conference on Learning Representations},
     year={2025},
     url={https://openreview.net/forum?id=cCRlEvjrx4}
   }

2. ICLRW'25

   

   Compositional World Knowledge leads to High Utility Synthetic data

   Sachit Gaudi, Gautam Sreekumar, Vishnu Boddeti

   SynthData, ICLRW, 2025

   ABS PAPER CODE BIB

   Machine learning systems struggle with robustness, under subpopulation shifts. This problem becomes especially pronounced in scenarios where only a subset of attribute combinations is observed during training—a severe form of subpopulation shift, referred as compositional shift. To address this problem, we ask the following question: Can we improve the robustness by training on synthetic data, spanning all possible attribute combinations? We first show that training of conditional diffusion models on limited data lead to incorrect underlying distribution. Therefore, synthetic data sampled from such models will result in unfaithful samples and does not lead to improve performance of downstream machine learning systems. To address this problem, we propose COIND to reflect the compositional nature of the world by enforcing conditional independence through minimizing Fisher’s divergence between joint and marginal distributions. We demonstrate that synthetic data generated by COIND is faithful and this translates to state-of-the-art worst-group accuracy on compositional shift tasks on CelebA.

   @inproceedings{ gaudi2025compositional, title={Compositional World Knowledge leads to High Utility Synthetic data}, author={Sachit Gaudi and Gautam Sreekumar and Vishnu Boddeti}, booktitle={Will Synthetic Data Finally Solve the Data Access Problem?}, year={2025}, url={https://openreview.net/forum?id=e9i1Frx5Kc} }

☕ Apart from Research

🧑‍🏫 I love teaching. At Michigan State University, I taught CSE 232 from Aug 2023 to May 2025 and CSE 480 from May 2023 to Aug 2023.

⛳ I enjoy running on rare sunny days on the East Coast. When the weather turns gloomy, I settle in with a cup of coffee ☕, pick up a book, work through math problems, and occasionally revisit LeetCode.

New Posts

Solving an Adversarial Optimization Problem The Hitchhiker’s Guide to a Master’s Program