523 citations · 584 across the 20 of their papers we have counts for
21 papers
Mosaic: Runtime-Efficient Multi-Agent Embodied Planning
Kunjal Panchal, Saayan Mitra, Sunav Choudhary +3
LLM-based multi-agent embodied planning remains impractical due to prohibitively high execution latency. We identify failed actions as the dominant bottleneck, stemming from two co…
TACO: Task-Aware Column Description Generation Using LLMs
Ting Cai, Rakesh R. Menon, Yiru Chen +8
Generating accurate and informative column descriptions (e.g. "membership status of customers" for the column name "cust_mem") is essential for a wide range of downstream NLP tasks…
Improving Selective Classification with Pairwise Queries for Binary Classification
Harsh Vardhan, Sunav Choudhary, Natwar Modani +1
In selective classification, a model predicts the labels of data samples where it is confident, and abstains from predicting labels for samples on which it is not confident. The re…
TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems
Jiale Liu, Victor S. Bursztyn, Lin Ai +4
In open-ended domains, teams must reconcile diverse viewpoints to produce strong deliverables. Answer aggregation approaches commonly used in closed domains are ill-suited to this…
Learning to Reason in LLMs by Expectation Maximization
Junghyun Lee, Branislav Kveton, Anup Rao +4
Large language models (LLMs) solve reasoning problems by first generating a rationale and then answering. We formalize reasoning as a latent variable model and derive a reward-base…
PRISM: Learning Design Knowledge from Data for Stylistic Design Improvement
Huaxiaoyue Wang, Sunav Choudhary, Franck Dernoncourt +2
Graphic design often involves exploring different stylistic directions, which can be time-consuming for non-experts. We address this problem of stylistically improving designs base…
Charts Are Not Images: On the Challenges of Scientific Chart Editing
Shawn Li, Ryan Rossi, Sungchul Kim +5
Generative models, such as diffusion and autoregressive approaches, have demonstrated impressive capabilities in editing natural images. However, applying these tools to scientific…
Memory Savings at What Cost? A Study of Alternatives to Backpropagation
Kunjal Panchal, Sunav Choudhary, Yuriy Brun +1
Forward-mode automatic differentiation (FmAD) and zero-order (ZO) optimization are increasingly proposed as memory-efficient, backpropagation-free alternatives for large language m…
Sequential Causal Discovery with Noisy Language Model Priors
Prakhar Verma, David Arbour, Sunav Choudhary +3
Causal discovery from observational data typically assumes access to complete data and availability of perfect domain experts. In practice, data often arrive in batches, are subjec…
Sparse Linear Bandits with Blocking Constraints
Adit Jain, Soumyabrata Pal, Sunav Choudhary +3
We investigate the high-dimensional sparse linear bandits problem in a data-poor regime where the time horizon is much smaller than the ambient dimension and number of arms. We stu…
Thinking Forward: Memory-Efficient Federated Finetuning of Language Models
Kunjal Panchal, Nisarg Parikh, Sunav Choudhary +3
Finetuning large language models (LLMs) in federated learning (FL) settings has become increasingly important as it allows resource-constrained devices to finetune a model using pr…
Delivery Optimized Discovery in Behavioral User Segmentation under Budget Constraint
Harshita Chopra, Atanu R. Sinha, Sunav Choudhary +5
Users' behavioral footprints online enable firms to discover behavior-based user segments (or, segments) and deliver segment specific messages to users. Following the discovery of…
Fake or Compromised? Making Sense of Malicious Clients in Federated Learning
Hamid Mozaffari, Sunav Choudhary, Amir Houmansadr
Federated learning (FL) is a distributed machine learning paradigm that enables training models on decentralized data. The field of FL security against poisoning attacks is plagued…
Flow: Per-Instance Personalized Federated Learning Through Dynamic Routing
Kunjal Panchal, Sunav Choudhary, Nisarg Parikh +2
Personalization in Federated Learning (FL) aims to modify a collaboratively trained global model according to each client. Current approaches to personalization in FL are at a coar…
Correlated Stochastic Knapsack with a Submodular Objective
Sheng Yang, Samir Khuller, Sunav Choudhary +2
We study the correlated stochastic knapsack problem of a submodular target function, with optional additional constraints. We utilize the multilinear extension of submodular functi…
Federated Learning with Personalization Layers
Manoj Ghuhan Arivazhagan, Vinay Aggarwal, Aaditya Kumar Singh +1
The emerging paradigm of federated learning strives to enable collaborative training of machine learning models on the network edge without centrally aggregating raw data and hence…
Data-Driven Compression of Convolutional Neural Networks
Ramit Pahwa, Manoj Ghuhan Arivazhagan, Ankur Garg +3
Deploying trained convolutional neural networks (CNNs) to mobile devices is a challenging task because of the simultaneous requirements of the deployed model to be fast, lightweigh…
Active Target Localization using Low-Rank Matrix Completion and Unimodal Regression
Sunav Choudhary, Naveen Kumar, Srikanth Narayanan +1
The detection and localization of a target from samples of its generated field is a problem of interest in a broad range of applications. Often, the target field admits structural…
Fundamental Limits of Blind Deconvolution Part II: Sparsity-Ambiguity Trade-offs
Sunav Choudhary, Urbashi Mitra
Blind deconvolution is an ubiquitous non-linear inverse problem in applications like wireless communications and image processing. This problem is generally ill-posed since signal…
Fundamental Limits of Blind Deconvolution Part I: Ambiguity Kernel
Sunav Choudhary, Urbashi Mitra
Blind deconvolution is an ubiquitous non-linear inverse problem in applications like wireless communications and image processing. This problem is generally ill-posed, and there ha…
Identifiability Scaling Laws in Bilinear Inverse Problems
Sunav Choudhary, Urbashi Mitra
A number of ill-posed inverse problems in signal processing, like blind deconvolution, matrix factorization, dictionary learning and blind source separation share the common charac…