Swaroop Ramaswamy
7 papers · 2020–2026 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(14)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Machine Learning
(6)
Artificial Intelligence
(5)
Application Areas
(5)
Learning Paradigms · Artificial Intelligence
(3)
Deep Learning
(2)
Core AI
(2)
Optimization & Theory
(2)
Natural Language Processing
(1)
Speech & Audio
(1)
Core Methods
(1)
Generation
(1)
Learning Paradigms · Machine Learning
(1)
Learning Types
(1)
Models
(1)
Recognition
(1)
Keywords
differential privacy
(4)
federated learning
(4)
language model
(2)
privacy-preserving learning
(1)
gradient descent
(1)
linear regression
(1)
distributed training
(1)
mirror descent
(1)
generative model
(1)
recurrent neural network
(1)
public data
(1)
generative adversarial network
(1)
gradient attack
(1)
long context
(1)
model update
(1)
gradient quantization
(1)
on-device learning
(1)
label leakage
(1)
next-word prediction
(1)
word error rate
(1)
Papers
We Are What We Repeatedly Do: Improving Long Context Instruction Following
EACL 2026
Public Data-Assisted Mirror Descent for Private Model Training
ICML 2022
UserLibri: A Dataset for ASR Personalization Using Only Text
Interspeech 2022
Differentially Private Learning with Adaptive Clipping
NeurIPS 2021
Revealing and Protecting Labels in Distributed Training
NeurIPS 2021
Understanding Unintended Memorization in Language Models Under Federated Learning
NAACL 2021
Generative Models for Effective ML on Private, Decentralized Datasets
ICLR 2020