16 citations · 45 across the 10 of their papers we have counts for
13 papers
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Juzheng Zhang, Disha Makhija, Manoj Ghuhan Arivazhagan +2
Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies loss only to agent-authored action tokens, using environment o…
Probing the Prompt KV Cache: Where It Becomes Dispensable
Vinayshekhar Bannihatti Kumar, Manoj Ghuhan Arivazhagan, Disha Makhija +1
Prior KV cache compression schemes empirically demonstrate that the prompt cache is partially redundant during decoding, dropping or summarising entries with little accuracy loss.…
Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language
Vinayshekhar Bannihatti Kumar, Disha Makhija, Manoj Ghuhan Arivazhagan +1
Large language models (LLMs) achieve high pass rates on code generation benchmarks, yet whether they can transfer this ability to languages absent from pretraining remains poorly u…
Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis
Disha Makhija, Manoj Ghuhan Arivazhagan, Vinayshekhar Bannihatti Kumar +1
Membership inference attacks (MIAs) reveal whether specific data was used to train machine learning models, serving as important tools for privacy auditing and compliance assessmen…
Achieving Fairness Across Local and Global Models in Federated Learning
Disha Makhija, Xing Han, Joydeep Ghosh +1
Achieving fairness across diverse clients in Federated Learning (FL) remains a significant challenge due to the heterogeneity of the data and the inaccessibility of sensitive attri…
Federated Learning for Estimating Heterogeneous Treatment Effects
Disha Makhija, Joydeep Ghosh, Yejin Kim
Machine learning methods for estimating heterogeneous treatment effects (HTE) facilitate large-scale personalized decision-making across various domains such as healthcare, policy…
Privacy Preserving Bayesian Federated Learning in Heterogeneous Settings
Disha Makhija, Joydeep Ghosh, Nhat Ho
In several practical applications of federated learning (FL), the clients are highly heterogeneous in terms of both their data and compute resources, and therefore enforcing the sa…
Federated Self-supervised Learning for Heterogeneous Clients
Disha Makhija, Nhat Ho, Joydeep Ghosh
Federated Learning has become an important learning paradigm due to its privacy and computational benefits. As the field advances, two key challenges that still remain to be addres…
Architecture Agnostic Federated Learning for Neural Networks
Disha Makhija, Xing Han, Nhat Ho +1
With growing concerns regarding data privacy and rapid increase in data volume, Federated Learning(FL) has become an important learning paradigm. However, jointly learning a deep n…
Audience Creation for Consumables -- Simple and Scalable Precision Merchandising for a Growing Marketplace
Shreyas S, Harsh Maheshwari, Avijit Saha +6
Consumable categories, such as grocery and fast-moving consumer goods, are quintessential to the growth of e-commerce marketplaces in developing countries. In this work, we present…
FairJudge: Trustworthy User Prediction in Rating Platforms
Srijan Kumar, Bryan Hooi, Disha Makhija +3
Rating platforms enable large-scale collection of user opinion about items (products, other users, etc.). However, many untrustworthy users give fraudulent ratings for excessive mo…
EdgeCentric: Anomaly Detection in Edge-Attributed Networks
Neil Shah, Alex Beutel, Bryan Hooi +5
Given a network with attributed edges, how can we identify anomalous behavior? Networks with edge attributes are commonplace in the real world. For example, edges in e-commerce net…
BIRDNEST: Bayesian Inference for Ratings-Fraud Detection
Bryan Hooi, Neil Shah, Alex Beutel +5
Review fraud is a pervasive problem in online commerce, in which fraudulent sellers write or purchase fake reviews to manipulate perception of their products and services. Fake rev…