output
20072025
most citedHeterogeneous Multi-task Learning with Expert Diversity

29 citations

7 papers

cs.LG2025★ 23 cited

Humanity's Last Exam

Long Phan, Alice Gatti, Ziwen Han +1144

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…

cs.CL2024★ 20 cited

Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study

Imed Keraghel, Stanislas Morbieu, Mohamed Nadif

Named Entity Recognition seeks to extract substrings within a text that name real-world objects and to determine their type (for example, whether they refer to persons or organizat…

cs.LG2021★ 29 cited

Heterogeneous Multi-task Learning with Expert Diversity

Raquel Aoki, Frederick Tung, Gabriel L. Oliveira

Predicting multiple heterogeneous biological and medical targets is a challenge for traditional deep learning models. In contrast to single-task learning, in which a separate model…

cs.CV2021

Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation

Mengyao Zhai, Lei Chen, Jiawei He +3

Humans accumulate knowledge in a lifelong fashion. Modern deep neural networks, on the other hand, are susceptible to catastrophic forgetting: when adapted to perform new tasks, th…

math.DG2008

Differentiable Categories, gerbes and G-structures

Tsemo Aristide

The theories of strings and -branes have motivated the development of non Abelian cohomology techniques in differential geometry, on the purpose to find a geometric interpretati…

math.CO2008

A homotopical algebra of graphs related to zeta series

Terrence Bisson, Aristide Tsemo

The purpose of this paper is to develop a homotopical algebra for graphs, relevant to zeta series and spectra of finite graphs. More precisely, we define a Quillen model structure…