61 citations
- Arizona State UniversityUS7 papers
- University of MichiganUS4 papers
- California Institute of TechnologyUS3 papers
- University of ArizonaUS3 papers
- University of Illinois Urbana-ChampaignUS3 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- IBM Research - HaifaIL2 papers
- Institut de Recherche en Informatique et Systèmes AléatoiresFR2 papers
- Jet Propulsion LaboratoryUS2 papers
- OpticaUS2 papers
- Rutgers, The State University of New JerseyUS2 papers
- Université de RennesFR2 papers
21 papers
COMBOOD: A Semiparametric Approach for Detecting Out-of-distribution Data for Image Classification
Magesh Rajasekaran, Md Saiful Islam Sajol, Frej Berglind +2
Identifying out-of-distribution (OOD) data at inference time is crucial for many machine learning applications, especially for automation. We present a novel unsupervised semi-para…
Conditional PED-ANOVA: Hyperparameter Importance in Hierarchical & Dynamic Search Spaces
Kaito Baba, Yoshihiko Ozaki, Shuhei Watanabe
We propose conditional PED-ANOVA (condPED-ANOVA), a principled framework for estimating hyperparameter importance (HPI) in conditional search spaces, where the presence or domain o…
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…
LLM+Reasoning+Planning for Supporting Incomplete User Queries in Presence of APIs
Sudhir Agarwal, Anu Sreepathy, David H. Alonso +1
Recent availability of Large Language Models (LLMs) has led to the development of numerous LLM-based approaches aimed at providing natural language interfaces for various end-user…
RecUP-FL: Reconciling Utility and Privacy in Federated Learning via User-configurable Privacy Defense
Yue Cui, Syed Irfan Ali Meerza, Zhuohang Li +3
Federated learning (FL) provides a variety of privacy advantages by allowing clients to collaboratively train a model without sharing their private data. However, recent studies ha…
Unsupervised Improvement of Factual Knowledge in Language Models
Nafis Sadeq, Byungkyu Kang, Prarit Lamba +1
Masked language modeling (MLM) plays a key role in pretraining large language models. But the MLM objective is often dominated by high-frequency words that are sub-optimal for lear…