147 citations · 528 across the 21 of their papers we have counts for
21 papers
Aligners: Decoupling LLMs and Alignment
Lilian Ngweta, Mayank Agarwal, Subha Maity +3
Large Language Models (LLMs) need to be aligned with human expectations to ensure their safety and utility in most applications. Alignment is challenging, costly, and needs to be r…
An Investigation of Representation and Allocation Harms in Contrastive Learning
Subha Maity, Mayank Agarwal, Mikhail Yurochkin +1
The effect of underrepresentation on the performance of minority groups is known to be a serious problem in supervised learning settings; however, it has been underexplored so far…
Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness
Zahra Ashktorab, Benjamin Hoover, Mayank Agarwal +4
Mitigating algorithmic bias is a critical task in the development and deployment of machine learning models. While several toolkits exist to aid machine learning practitioners in a…
Geometry-biased Transformers for Novel View Synthesis
Naveen Venkat, Mayank Agarwal, Maneesh Singh +1
We tackle the task of synthesizing novel views of an object given a few input images and associated camera viewpoints. Our work is inspired by recent 'geometry-free' approaches whe…
Better Together? An Evaluation of AI-Supported Code Translation
Justin D. Weisz, Michael Muller, Steven I. Ross +5
Generative machine learning models have recently been applied to source code, for use cases including translating code between programming languages, creating documentation from co…
Investigating Explainability of Generative AI for Code through Scenario-based Design
Jiao Sun, Q. Vera Liao, Michael Muller +4
What does it mean for a generative AI model to be explainable? The emergent discipline of explainable AI (XAI) has made great strides in helping people understand discriminative mo…
On sensitivity of meta-learning to support data
Mayank Agarwal, Mikhail Yurochkin, Yuekai Sun
Meta-learning algorithms are widely used for few-shot learning. For example, image recognition systems that readily adapt to unseen classes after seeing only a few labeled examples…
Using Document Similarity Methods to create Parallel Datasets for Code Translation
Mayank Agarwal, Kartik Talamadupula, Fernando Martinez +5
Translating source code from one programming language to another is a critical, time-consuming task in modernizing legacy applications and codebases. Recent work in this space has…
COVID-19 India Dataset: Parsing COVID-19 Data in Daily Health Bulletins from States in India
Mayank Agarwal, Tathagata Chakraborti, Sachin Grover +1
While India has been one of the hotspots of COVID-19, data about the pandemic from the country has proved to be largely inaccessible at scale. Much of the data exists in unstructur…
Perfection Not Required? Human-AI Partnerships in Code Translation
Justin D. Weisz, Michael Muller, Stephanie Houde +5
Generative models have become adept at producing artifacts such as images, videos, and prose at human-like levels of proficiency. New generative techniques, such as unsupervised ne…
NeurIPS 2020 NLC2CMD Competition: Translating Natural Language to Bash Commands
Mayank Agarwal, Tathagata Chakraborti, Quchen Fu +6
The NLC2CMD Competition hosted at NeurIPS 2020 aimed to bring the power of natural language processing to the command line. Participants were tasked with building models that can t…
Quality Estimation & Interpretability for Code Translation
Mayank Agarwal, Kartik Talamadupula, Stephanie Houde +5
Recently, the automated translation of source code from one programming language to another by using automatic approaches inspired by Neural Machine Translation (NMT) methods for n…
Online Semi-Supervised Learning with Bandit Feedback
Sohini Upadhyay, Mikhail Yurochkin, Mayank Agarwal +2
We formulate a new problem at the intersectionof semi-supervised learning and contextual bandits,motivated by several applications including clini-cal trials and ad recommendations…
IBM Federated Learning: an Enterprise Framework White Paper V0.1
Heiko Ludwig, Nathalie Baracaldo, Gegi Thomas +21
Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume. How…
Project CLAI: Instrumenting the Command Line as a New Environment for AI Agents
Mayank Agarwal, Jorge J. Barroso, Tathagata Chakraborti +5
This whitepaper reports on Project CLAI (Command Line AI), which aims to bring the power of AI to the command line interface (CLI). The CLAI platform sets up the CLI as a new envir…
Statistical Model Aggregation via Parameter Matching
Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh +2
We consider the problem of aggregating models learned from sequestered, possibly heterogeneous datasets. Exploiting tools from Bayesian nonparametrics, we develop a general meta-mo…
A Bandit Approach to Posterior Dialog Orchestration Under a Budget
Sohini Upadhyay, Mayank Agarwal, Djallel Bounneffouf +1
Building multi-domain AI agents is a challenging task and an open problem in the area of AI. Within the domain of dialog, the ability to orchestrate multiple independently trained…
Bayesian Nonparametric Federated Learning of Neural Networks
Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh +3
In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric fram…
Machine Translation: A Literature Review
Ankush Garg, Mayank Agarwal
Machine translation (MT) plays an important role in benefiting linguists, sociologists, computer scientists, etc. by processing natural language to translate it into some other nat…
CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision
Navaneet K L, Priyanka Mandikal, Mayank Agarwal +1
Knowledge of 3D properties of objects is a necessity in order to build effective computer vision systems. However, lack of large scale 3D datasets can be a major constraint for dat…
3D-LMNet: Latent Embedding Matching for Accurate and Diverse 3D Point Cloud Reconstruction from a Single Image
Priyanka Mandikal, K L Navaneet, Mayank Agarwal +1
3D reconstruction from single view images is an ill-posed problem. Inferring the hidden regions from self-occluded images is both challenging and ambiguous. We propose a two-pronge…