← Search

Sumeet Agarwal

4 accepted papers

2025

MOGIC: Metadata-infused Oracle Guidance for Improved Extreme Classification

ICML 2025poster

Retrieval-augmented classification and generation models benefit from *early-stage fusion* of high-quality text-based metadata, often called memory, but face high latency and noise sensitivity. In extreme classification (XC), where low latency is crucial, existing methods use *late-stage fusion* for…

2022

Discourse Context Predictability Effects in Hindi Word Order

EMNLP 2022main

We test the hypothesis that discourse predictability influences Hindi syntactic choice. While prior work has shown that a number of factors (e.g., information status, dependency length, and syntactic surprisal) influence Hindi word order preferences, the role of discourse predictability is underexpl…

2022

Multi-Modal Extreme Classification

CVPR 2022poster

This paper develops the MUFIN technique for extreme classification (XC) tasks with millions of labels where datapoints and labels are endowed with visual and textual descriptors. Applications of MUFIN to product-to-product recommendation and bid query prediction over several millions of products are…

Cited by 16PDFcodeScholar
2021

SiameseXML: Siamese Networks meet Extreme Classifiers with 100M Labels

ICML 2021spotlight

Deep extreme multi-label learning (XML) requires training deep architectures that can tag a data point with its most relevant subset of labels from an extremely large label set. XML applications such as ad and product recommendation involve labels rarely seen during training but which nevertheless h…