Publications (50)
ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation
Reza Yousefi Maragheh, Pratheek Vadla, Priyank Gupta +7
Retrieval-Augmented Generation (RAG) has shown promise in enhancing recommendation systems by incorporating external context into large language model prompts. However, existing RA…
Seller-side Outcome Fairness in Online Marketplaces
Zikun Ye, Reza Yousefi Maragheh, Lalitesh Morishetti +5
This paper aims to investigate and achieve seller-side fairness within online marketplaces, where many sellers and their items are not sufficiently exposed to customers in an e-com…
NEAT: A Label Noise-resistant Complementary Item Recommender System with Trustworthy Evaluation
Luyi Ma, Jianpeng Xu, Jason H. D. Cho +3
The complementary item recommender system (CIRS) recommends the complementary items for a given query item. Existing CIRS models consider the item co-purchase signal as a proxy of…
Adaptive Object Detection for Indoor Navigation Assistance: A Performance Evaluation of Real-Time Algorithms
Abhinav Pratap, Sushant Kumar, Suchinton Chakravarty
This study addresses the need for accurate and efficient object detection in assistive technologies for visually impaired individuals. We evaluate four real-time object detection a…
On Variational Inference for User Modeling in Attribute-Driven Collaborative Filtering
Venugopal Mani, Ramasubramanian Balasubramanian, Sushant Kumar +2
Recommender Systems have become an integral part of online e-Commerce platforms, driving customer engagement and revenue. Most popular recommender systems attempt to learn from use…
Guidelines for releasing a variant effect predictor
Benjamin J. Livesey, Mihaly Badonyi, Mafalda Dias +15
Computational methods for assessing the likely impacts of mutations, known as variant effect predictors (VEPs), are widely used in the assessment and interpretation of human geneti…
CRAB: Codebook Rebalancing for Bias Mitigation in Generative Recommendation
Zezhong Fan, Ziheng Chen, Luyi Ma +5
Generative recommendation (GeneRec) has introduced a new paradigm that represents items as discrete semantic tokens and predicts items in a generative manner. Despite its strong pe…
Is More Context Always Better? Examining LLM Reasoning Capability for Time Interval Prediction
Yanan Cao, Farnaz Fallahi, Murali Mohana Krishna Dandu +9
Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning and prediction across different domains. Yet, their ability to infer temporal regularities from…
To See or To Read: User Behavior Reasoning in Multimodal LLMs
Tianning Dong, Luyi Ma, Varun Vasudevan +3
Multimodal Large Language Models (MLLMs) are reshaping how modern agentic systems reason over sequential user-behavior data. However, whether textual or image representations of us…
Fermi surface anisotropy in plasmonic metals increases the potential for efficient hot carrier extraction
Sushant Kumar, Christian Multunas, Ravishankar Sundararaman
Realizing the potential of plasmonic hot carrier harvesting for energy conversion and photodetection requires new materials that resolve the bottleneck of extracting carriers prior…
Robust Counterfactual Inferences using Feature Learning and their Applications
Abhimanyu Mitra, Kannan Achan, Sushant Kumar
In a wide variety of applications, including personalization, we want to measure the difference in outcome due to an intervention and thus have to deal with counterfactual inferenc…
GNN-GMVO: Graph Neural Networks for Optimizing Gross Merchandise Value in Similar Item Recommendation
Ramin Giahi, Reza Yousefi Maragheh, Nima Farrokhsiar +5
Similar item recommendation is a critical task in the e-Commerce industry, which helps customers explore similar and relevant alternatives based on their interested products. Despi…
High-Energy Microresonator Soliton Generation
Zhenhua Guo, Sushant Kumar, Xue Dong +7
Kerr resonators generate stable frequency combs in a compact platform with applications in coherent communications, sensing, quantum information processing, and astrophysics. Ultra…
Towards the D-Optimal Online Experiment Design for Recommender Selection
Da Xu, Chuanwei Ruan, Evren Korpeoglu +2
Selecting the optimal recommender via online exploration-exploitation is catching increasing attention where the traditional A/B testing can be slow and costly, and offline evaluat…
Product Knowledge Graph Embedding for E-commerce
Da Xu, Chuanwei Ruan, Evren Korpeoglu +2
In this paper, we propose a new product knowledge graph (PKG) embedding approach for learning the intrinsic product relations as product knowledge for e-commerce. We define the key…
Scalable Permutation-Aware Modeling for Temporal Set Prediction
Ashish Ranjan, Ayush Agarwal, Shalin Barot +1
Temporal set prediction involves forecasting the elements that will appear in the next set, given a sequence of prior sets, each containing a variable number of elements. Existing…
Thread Detection and Response Generation using Transformers with Prompt Optimisation
Kevin Joshua T, Arnav Agarwal, Shriya Sanjay +5
Conversational systems are crucial for human-computer interaction, managing complex dialogues by identifying threads and prioritising responses. This is especially vital in multi-p…
Topological Metal MoP Nanowire for Interconnect
Hyeuk Jin Han, Sushant Kumar, Xiaoyang Ji +9
The increasing resistance of Cu interconnects for decreasing dimensions is a major challenge in continued downscaling of integrated circuits beyond the 7-nm technology node as it l…
Triple Modality Fusion: Aligning Visual, Textual, and Graph Data with Large Language Models for Multi-Behavior Recommendations
Luyi Ma, Xiaohan Li, Zezhong Fan +7
Integrating diverse data modalities is crucial for enhancing the performance of personalized recommendation systems. Traditional models, which often rely on singular data sources,…
LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks
Luyi Ma, Wanjia Sherry Zhang, Zezhong Fan +10
On online advertising platforms, newly introduced promotional ads face the cold-start problem, as they lack sufficient user feedback for model training. In this work, we propose LL…
Surface-dominated conductance scaling in Weyl semimetal NbAs
Sushant Kumar, Yi-Hsin Tu, Luo Sheng +6
Protected surface states arising from non-trivial bandstructure topology in semimetals can potentially enable new device functionalities in compute, memory, interconnect, sensing,…
Chaining text-to-image and large language model: A novel approach for generating personalized e-commerce banners
Shanu Vashishtha, Abhinav Prakash, Lalitesh Morishetti +4
Text-to-image models such as stable diffusion have opened a plethora of opportunities for generating art. Recent literature has surveyed the use of text-to-image models for enhanci…
Inductive Representation Learning on Temporal Graphs
Da Xu, Chuanwei Ruan, Evren Korpeoglu +2
Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic gr…
Variational Inference for Category Recommendation in E-Commerce platforms
Ramasubramanian Balasubramanian, Venugopal Mani, Abhinav Mathur +2
Category recommendation for users on an e-Commerce platform is an important task as it dictates the flow of traffic through the website. It is therefore important to surface precis…
Ultralow Electron-Surface Scattering in Nanoscale Metals Leveraging Fermi Surface Anisotropy
Sushant Kumar, Christian Multunas, Benjamin Defay +2
Increasing resistivity of metal wires with reducing nanoscale dimensions is a major performance bottleneck of semiconductor computing technologies. We show that metals with suitabl…
Rethinking Neural vs. Matrix-Factorization Collaborative Filtering: the Theoretical Perspectives
Da Xu, Chuanwei Ruan, Evren Korpeoglu +2
The recent work by Rendle et al. (2020), based on empirical observations, argues that matrix-factorization collaborative filtering (MCF) compares favorably to neural collaborative…
On Detecting Data Pollution Attacks On Recommender Systems Using Sequential GANs
Behzad Shahrasbi, Venugopal Mani, Apoorv Reddy Arrabothu +3
Recommender systems are an essential part of any e-commerce platform. Recommendations are typically generated by aggregating large amounts of user data. A malicious actor may be mo…
Generative Graph Convolutional Network for Growing Graphs
Da Xu, Chuanwei Ruan, Kamiya Motwani +3
Modeling generative process of growing graphs has wide applications in social networks and recommendation systems, where cold start problem leads to new nodes isolated from existin…
Campaign-2-PT-RAG: LLM-Guided Semantic Product Type Attribution for Scalable Campaign Ranking
Yiming Che, Mansi Ranjit Mane, Keerthi Gopalakrishnan +8
E-commerce campaign ranking models require large-scale training labels indicating which users purchased due to campaign influence. However, generating these labels is challenging b…
GRACE: Generative Recommendation via Journey-Aware Sparse Attention on Chain-of-Thought Tokenization
Luyi Ma, Wanjia Zhang, Kai Zhao +15
Generative models have recently demonstrated strong potential in multi-behavior recommendation systems, leveraging the expressive power of transformers and tokenization to generate…
LLM-driven Constrained Copy Generation through Iterative Refinement
Varun Vasudevan, Faezeh Akhavizadegan, Abhinav Prakash +5
Crafting a marketing message (copy), or copywriting is a challenging generation task, as the copy must adhere to various constraints. Copy creation is inherently iterative for huma…
Improving Sequential Recommender Systems with Online and In-store User Behavior
Luyi Ma, Aashika Padmanabhan, Anjana Ganesh +9
Online e-commerce platforms have been extending in-store shopping, which allows users to keep the canonical online browsing and checkout experience while exploring in-store shoppin…
Latent Customer Segmentation and Value-Based Recommendation Leveraging a Two-Stage Model with Missing Labels
Keerthi Gopalakrishnan, Tianning Dong, Chia-Yen Ho +5
The success of businesses depends on their ability to convert consumers into loyal customers. A customer's value proposition is a primary determinant in this process, requiring a b…
No-Human in the Loop: Agentic Evaluation at Scale for Recommendation
Tao Zhang, Kehui Yao, Luyi Ma +7
Evaluating large language models (LLMs) as judges is increasingly critical for building scalable and trustworthy evaluation pipelines. We present ScalingEval, a large-scale benchma…
CARTS: Collaborative Agents for Recommendation Textual Summarization
Jiao Chen, Kehui Yao, Reza Yousefi Maragheh +6
Current recommendation systems often require some form of textual data summarization, such as generating concise and coherent titles for product carousels or other grouped item dis…
Knowledge-aware Complementary Product Representation Learning
Da Xu, Chuanwei Ruan, Jason Cho +3
Learning product representations that reflect complementary relationship plays a central role in e-commerce recommender system. In the absence of the product relationships graph, w…
GridVQA-X: A Framework for Evaluating Multimodal Explainability Methods
Sujay Belsare, Sudarshan Nikhil, Sushant Kumar +2
With the increasing development of Vision-Language Models, it becomes imperative that their predictions are readily explainable to relevant stakeholders. However, the field of expl…
Surface-dominant transport in Weyl semimetal NbAs nanowires for next-generation interconnects
Yeryun Cheon, Mehrdad T. Kiani, Yi-Hsin Tu +20
Ongoing demands for smaller and more energy efficient electronic devices necessitate alternative interconnect materials with lower electrical resistivity at reduced dimensions. Des…
Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs
Jiao Chen, Luyi Ma, Xiaohan Li +7
Knowledge Graphs (KGs) play a crucial role in enhancing e-commerce system performance by providing structured information about entities and their relationships, such as complement…
LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction
Chenhao Fang, Xiaohan Li, Zezhong Fan +5
Product attribute value extraction is a pivotal component in Natural Language Processing (NLP) and the contemporary e-commerce industry. The provision of precise product attribute…
MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems
Shreeranjani Srirangamsridharan, Ali Abavisani, Reza Yousefi Maragheh +4
Meta titles and descriptions strongly shape engagement in search and recommendation platforms, yet optimizing them remains challenging. Search engine ranking models are black box e…
LLM-TAKE: Theme Aware Keyword Extraction Using Large Language Models
Reza Yousefi Maragheh, Chenhao Fang, Charan Chand Irugu +8
Keyword extraction is one of the core tasks in natural language processing. Classic extraction models are notorious for having a short attention span which make it hard for them to…
Adversarial Counterfactual Learning and Evaluation for Recommender System
Da Xu, Chuanwei Ruan, Evren Korpeoglu +2
The feedback data of recommender systems are often subject to what was exposed to the users; however, most learning and evaluation methods do not account for the underlying exposur…
LLMs with User-defined Prompts as Generic Data Operators for Reliable Data Processing
Luyi Ma, Nikhil Thakurdesai, Jiao Chen +4
Data processing is one of the fundamental steps in machine learning pipelines to ensure data quality. Majority of the applications consider the user-defined function (UDF) design p…
Causal Structure Learning with Recommendation System
Shuyuan Xu, Da Xu, Evren Korpeoglu +4
A fundamental challenge of recommendation systems (RS) is understanding the causal dynamics underlying users' decision making. Most existing literature addresses this problem by us…
Theoretical Understandings of Product Embedding for E-commerce Machine Learning
Da Xu, Chuanwei Ruan, Evren Korpeoglu +2
Product embeddings have been heavily investigated in the past few years, serving as the cornerstone for a broad range of machine learning applications in e-commerce. Despite the em…
A Temporal Kernel Approach for Deep Learning with Continuous-time Information
Da Xu, Chuanwei Ruan, Evren Korpeoglu +2
Sequential deep learning models such as RNN, causal CNN and attention mechanism do not readily consume continuous-time information. Discretizing the temporal data, as we show, caus…
Spin-phonon relaxation from a universal \emph{ab initio} density-matrix approach
Junqing Xu, Adela Habib, Sushant Kumar +3
Designing new quantum materials with long-lived electron spin states urgently requires a general theoretical formalism and computational technique to reliably predict intrinsic spi…
Event-based Product Carousel Recommendation with Query-Click Graph
Luyi Ma, Nimesh Sinha, Parth Vajge +3
Many current recommender systems mainly focus on the product-to-product recommendations and user-to-product recommendations even during the time of events rather than modeling the…
Self-attention with Functional Time Representation Learning
Da Xu, Chuanwei Ruan, Sushant Kumar +2
Sequential modelling with self-attention has achieved cutting edge performances in natural language processing. With advantages in model flexibility, computation complexity and int…