35 citations · 75 across the 12 of their papers we have counts for
12 papers
The Prompt is Mightier than the Example
Shengzhe Xu, Nikhil Muralidhar, Naren Ramakrishnan
Numerous recent prompt optimization approaches like chain-of-thought, have been demonstrated to significantly improve the quality of content generated by large language models (LLM…
Information Guided Regularization for Fine-tuning Language Models
Mandar Sharma, Nikhil Muralidhar, Shengzhe Xu +2
The pretraining-fine-tuning paradigm has been the de facto strategy for transfer learning in modern language modeling. With the understanding that task adaptation in LMs is often a…
Why LLMs Are Bad at Synthetic Table Generation (and what to do about it)
Shengzhe Xu, Cho-Ting Lee, Mandar Sharma +3
Synthetic data generation is integral to ML pipelines, e.g., to augment training data, replace sensitive information, and even to power advanced platforms like DeepSeek. While LLMs…
Laying Anchors: Semantically Priming Numerals in Language Modeling
Mandar Sharma, Rutuja Murlidhar Taware, Pravesh Koirala +2
Off-the-shelf pre-trained language models have become the de facto standard in NLP pipelines for a multitude of downstream tasks. However, the inability of these models to properly…
Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems
Shengzhe Xu, Christo Kurisummoottil Thomas, Omar Hashash +3
Large language models (LLMs) and foundation models have been recently touted as a game-changer for 6G systems. However, recent efforts on LLMs for wireless networks are limited to…
Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency
Mandar Sharma, Nikhil Muralidhar, Naren Ramakrishnan
The field of Math-NLP has witnessed significant growth in recent years, motivated by the desire to expand LLM performance to the learning of non-linguistic notions (numerals, and s…
Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic
Mandar Sharma, Nikhil Muralidhar, Naren Ramakrishnan
Through their transfer learning abilities, highly-parameterized large pre-trained language models have dominated the NLP landscape for a multitude of downstream language tasks. Tho…
Detecting Irregular Network Activity with Adversarial Learning and Expert Feedback
Gopikrishna Rathinavel, Nikhil Muralidhar, Timothy O'Shea +1
Anomaly detection is a ubiquitous and challenging task relevant across many disciplines. With the vital role communication networks play in our daily lives, the security of these n…
Contrastive Graph Convolutional Networks for Hardware Trojan Detection in Third Party IP Cores
Nikhil Muralidhar, Abdullah Zubair, Nathanael Weidler +2
The availability of wide-ranging third-party intellectual property (3PIP) cores enables integrated circuit (IC) designers to focus on designing high-level features in ASICs/SoCs. T…
Using AntiPatterns to avoid MLOps Mistakes
Nikhil Muralidhar, Sathappah Muthiah, Patrick Butler +8
We describe lessons learned from developing and deploying machine learning models at scale across the enterprise in a range of financial analytics applications. These lessons are p…
Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19
Alexander Rodríguez, Nikhil Muralidhar, Bijaya Adhikari +3
Forecasting influenza in a timely manner aids health organizations and policymakers in adequate preparation and decision making. However, effective influenza forecasting still rema…
Physics-guided Design and Learning of Neural Networks for Predicting Drag Force on Particle Suspensions in Moving Fluids
Nikhil Muralidhar, Jie Bu, Ze Cao +4
Physics-based simulations are often used to model and understand complex physical systems and processes in domains like fluid dynamics. Such simulations, although used frequently,…