Zobrazeno 1 - 10
of 2 263
pro vyhledávání: '"Arabzadeh, A."'
Text-to-Image (TTI) systems often support people during ideation, the early stages of a creative process when exposure to a broad set of relevant images can help explore the design space. Since ideation is an important subclass of TTI tasks, understa
Externí odkaz:
http://arxiv.org/abs/2410.17331
Publikováno v:
2024. International Workshop on Recommender Systems for Sustainability and Social Good (RecSoGood) at the 18th ACM Conference on Recommender Systems (ACM RecSys)
As recommender systems become increasingly prevalent, the environmental impact and energy efficiency of training large-scale models have come under scrutiny. This paper investigates the potential for energy-efficient algorithm performance by optimizi
Externí odkaz:
http://arxiv.org/abs/2410.09359
This paper introduces a novel approach to personalised federated learning within the $\mathcal{X}$-armed bandit framework, addressing the challenge of optimising both local and global objectives in a highly heterogeneous environment. Our method emplo
Externí odkaz:
http://arxiv.org/abs/2409.07251
Autor:
Mohanty, Shrestha, Arabzadeh, Negar, Tupini, Andrea, Sun, Yuxuan, Skrynnik, Alexey, Zholus, Artem, Côté, Marc-Alexandre, Kiseleva, Julia
Seamless interaction between AI agents and humans using natural language remains a key goal in AI research. This paper addresses the challenges of developing interactive agents capable of understanding and executing grounded natural language instruct
Externí odkaz:
http://arxiv.org/abs/2407.08898
Autor:
Arabzadeh, Negar, Huo, Siqing, Mehta, Nikhil, Wu, Qinqyun, Wang, Chi, Awadallah, Ahmed, Clarke, Charles L. A., Kiseleva, Julia
The rapid development of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents, assisting humans in their daily tasks. However, a significant gap remains in assessing to what extent LLM-po
Externí odkaz:
http://arxiv.org/abs/2405.02178
We study ranked list truncation (RLT) from a novel "retrieve-then-re-rank" perspective, where we optimize re-ranking by truncating the retrieved list (i.e., trim re-ranking candidates). RLT is crucial for re-ranking as it can improve re-ranking effic
Externí odkaz:
http://arxiv.org/abs/2404.18185
This paper is a draft of a chapter intended to appear in a forthcoming book on generative information retrieval, co-edited by Chirag Shah and Ryen White. In this chapter, we consider generative information retrieval evaluation from two distinct but i
Externí odkaz:
http://arxiv.org/abs/2404.08137
Information retrieval systems increasingly incorporate generative components. For example, in a retrieval augmented generation (RAG) system, a retrieval component might provide a source of ground truth, while a generative component summarizes and aug
Externí odkaz:
http://arxiv.org/abs/2404.04044
Query performance prediction (QPP) aims to estimate the retrieval quality of a search system for a query without human relevance judgments. Previous QPP methods typically return a single scalar value and do not require the predicted values to approxi
Externí odkaz:
http://arxiv.org/abs/2404.01012
Autor:
Arabzadeh, Negar, Kiseleva, Julia, Wu, Qingyun, Wang, Chi, Awadallah, Ahmed, Dibia, Victor, Fourney, Adam, Clarke, Charles
The rapid development in the field of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents to assist humans in their daily tasks. However, a significant gap remains in assessing whether L
Externí odkaz:
http://arxiv.org/abs/2402.09015