Chandramouli Shama Sastry — accepted AI-conference papers

2025

Accelerating neural network training: An analysis of the AlgoPerf competition

Priya Kasimbeg, Frank Schneider, Runa Eschenhagen, Juhan Bae, Chandramouli Shama Sastry, Mark Saroufim +8

ICLR 2025poster

The goal of the AlgoPerf: Training Algorithms competition is to evaluate practical speed-ups in neural network training achieved solely by improving the underlying training algorithms. In the external tuning ruleset, submissions must provide workload-agnostic hyperparameter search spaces, while in t…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers

Chandramouli Shama Sastry, Sri Harsha Dumpala, Sageev Oore

NeurIPS 2024poster

We introduce DiffAug, a simple and efficient diffusion-based augmentation technique to train image classifiers for the crucial yet challenging goal of improved classifier robustness. Applying DiffAug to a given example consists of one forward-diffusion step followed by one reverse-diffusion step. Us…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations

Sri Harsha Dumpala, Aman Jaiswal, Chandramouli Shama Sastry, Evangelos Milios, Sageev Oore, Hassan Sajjad

NeurIPS 2024poster

Despite their remarkable successes, state-of-the-art large language models (LLMs), including vision-and-language models (VLMs) and unimodal language models (ULMs), fail to understand precise semantics. For example, semantically equivalent sentences expressed using different lexical compositions elic…

Cited by 11 Source ↗PDF ↗code ↗Scholar ↗

2024

Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion

Yujia Huang, Adishree Ghatare, Yuanzhe Liu, Ziniu Hu, Qinsheng Zhang, Chandramouli Shama Sastry +3

ICML 2024oral

We study the problem of symbolic music generation (e.g., generating piano rolls), with a technical focus on non-differentiable rule guidance. Musical rules are often expressed in symbolic form on note characteristics, such as note density or chord progression, many of which are non-differentiable wh…

Cited by 14 Source ↗PDF ↗code ↗Scholar ↗

2020

Detecting Out-of-Distribution Examples with Gram Matrices

Chandramouli Shama Sastry, Sageev Oore

ICML 2020poster

When presented with Out-of-Distribution (OOD) examples, deep neural networks yield confident, incorrect predictions; detecting OOD examples is challenging, and the potential risks are high. In this paper, we propose to detect OOD examples by identifying inconsistencies between activity patterns and…

Cited by 291 Source ↗PDF ↗Scholar ↗