107 citations · 254 across the 13 of their papers we have counts for
14 papers
OpenThoughts: Data Recipes for Reasoning Models
Etash Guha, Ryan Marten, Sedrick Keh +47
Reasoning models have made rapid progress on many benchmarks involving math, code, and science. Yet, there are still many open questions about the best training recipes for reasoni…
Toward Holistic Evaluation of Recommender Systems Powered by Generative Models
Yashar Deldjoo, Nikhil Mehta, Maheswaran Sathiamoorthy +3
Recommender systems powered by generative models (Gen-RecSys) extend beyond classical item ranking by producing open-ended content, which simultaneously unlocks richer user experie…
Recommendation with Generative Models
Yashar Deldjoo, Zhankui He, Julian McAuley +8
Generative models are a class of AI models capable of creating new instances of data by learning and sampling from their statistical distributions. In recent years, these models ha…
A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)
Yashar Deldjoo, Zhankui He, Julian McAuley +7
Traditional recommender systems (RS) typically use user-item rating histories as their main data source. However, deep generative models now have the capability to model and sample…
Aligning Large Language Models with Recommendation Knowledge
Yuwei Cao, Nikhil Mehta, Xinyang Yi +5
Large language models (LLMs) have recently been used as backbones for recommender systems. However, their performance often lags behind conventional methods in standard tasks like…
Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations
Anima Singh, Trung Vu, Nikhil Mehta +9
Randomly-hashed item ids are used ubiquitously in recommendation models. However, the learned representations from random hashing prevents generalization across similar items, caus…
Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction
Wang-Cheng Kang, Jianmo Ni, Nikhil Mehta +4
Large Language Models (LLMs) have demonstrated exceptional capabilities in generalizing to new tasks in a zero-shot or few-shot manner. However, the extent to which LLMs can compre…
Recommender Systems with Generative Retrieval
Shashank Rajput, Nikhil Mehta, Anima Singh +10
Modern recommender systems perform large-scale retrieval by first embedding queries and item candidates in the same unified space, followed by approximate nearest neighbor search t…
Improving Training Stability for Multitask Ranking Models in Recommender Systems
Jiaxi Tang, Yoel Drori, Daryl Chang +6
Recommender systems play an important role in many content platforms. While most recommendation research is dedicated to designing better models to improve user experience, we foun…
Nonlinear Initialization Methods for Low-Rank Neural Networks
Kiran Vodrahalli, Rakesh Shivanna, Maheswaran Sathiamoorthy +2
We propose a novel low-rank initialization framework for training low-rank deep neural networks -- networks where the weight parameters are re-parameterized by products of two low-…
DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning
Hussein Hazimeh, Zhe Zhao, Aakanksha Chowdhery +5
The Mixture-of-Experts (MoE) architecture is showing promising results in improving parameter sharing in multi-task learning (MTL) and in scaling high-capacity neural networks. Sta…
XORing Elephants: Novel Erasure Codes for Big Data
Maheswaran Sathiamoorthy, Megasthenis Asteris, Dimitris Papailiopoulos +4
Distributed storage systems for large clusters typically use replication to provide reliability. Recently, erasure codes have been used to reduce the large storage overhead of thre…
Analysis of Twitter Traffic based on Renewal Densities
Javier Esteban, Antonio Ortega, Sean McPherson +1
In this paper we propose a novel approach for Twitter traffic analysis based on renewal theory. Even though twitter datasets are of increasing interest to researchers, extracting i…
Backpressure with Adaptive Redundancy (BWAR)
Majed Alresaini, Maheswaran Sathiamoorthy, Bhaskar Krishnamachari +1
Backpressure scheduling and routing, in which packets are preferentially transmitted over links with high queue differentials, offers the promise of throughput-optimal operation fo…