User profiles for Kevin Liang

Kevin J Liang

Fundamental AI Research (FAIR) at Meta
Verified email at meta.com
Cited by 791

HMDB 4.0: the human metabolome database for 2018

…, YD Feunang, A Marcu, AC Guo, K Liang… - Nucleic acids …, 2018 - academic.oup.com
The Human Metabolome Database or HMDB ( www.hmdb.ca ) is a web-enabled metabolomic
database containing comprehensive information about human metabolites along with …

[HTML][HTML] Durum wheat genome highlights past domestication signatures and future improvement targets

…, JM Clarke, AG Sharpe, CS Koh, KYH Liang… - Nature …, 2019 - nature.com
The domestication of wild emmer wheat led to the selection of modern durum wheat, grown
mainly for pasta production. We describe the 10.45 gigabase (Gb) assembly of the genome …

Genomic atlas of the plasma metabolome prioritizes metabolites implicated in human diseases

…, G Butler-Laporte, T Nakanishi, A Cerani, KYH Liang… - Nature …, 2023 - nature.com
Metabolic processes can influence disease risk and provide therapeutic targets. By conducting
genome-wide association studies of 1,091 blood metabolites and 309 metabolite ratios, …

A multiplexed network for end-to-end, multilingual OCR

…, G Pang, R Kovvuri, M Toh, KJ Liang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Recent advances in OCR have shown that an end-to-end (E2E) training pipeline that includes
both detection and recognition leads to the best results. However, many existing methods …

Chronic nicotine administration exacerbates tau pathology in a transgenic model of Alzheimer's disease

…, A Caccamo, KN Green, K Liang… - Proceedings of the …, 2005 - National Acad Sciences
The association between nicotinic acetylcholine receptor (nAChR) dysfunction and cognitive
decline in Alzheimer's disease (AD) has been widely exploited for its therapeutic potential. …

Sylph: A hypernetwork framework for incremental few-shot object detection

L Yin, JM Perez-Rua, KJ Liang - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
We study the challenging incremental few-shot object detection (iFSD) setting. Recently,
hypernetwork-based approaches have been studied in the context of continuous and finetune-…

Towards fair federated learning with zero-shot data augmentation

…, J Lee, J Zhang, KJ Liang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Federated learning has emerged as an important distributed learning paradigm, where a
server aggregates a global model from many client-trained models, while having no access to …

Few-shot learning with noisy labels

KJ Liang, SB Rangrej, V Petrovic… - Proceedings of the …, 2022 - openaccess.thecvf.com
Few-shot learning (FSL) methods typically assume clean support sets with accurately labeled
samples when training on novel classes. This assumption can often be unrealistic: support …

[HTML][HTML] Roseobacters in a sea of poly-and paraphyly: whole genome-based taxonomy of the family Rhodobacteraceae and the proposal for the split of the “ …

KYH Liang, FD Orata, YF Boucher… - Frontiers in Microbiology, 2021 - frontiersin.org
The family Rhodobacteraceae consists of alphaproteobacteria that are metabolically,
phenotypically, and ecologically diverse. It includes the roseobacter clade, an informal designation…

MarkerDB: an online database of molecular biomarkers

DS Wishart, B Bartok, E Oler, KYH Liang… - Nucleic acids …, 2021 - academic.oup.com
MarkerDB is a freely available electronic database that attempts to consolidate information
on all known clinical and a selected set of pre-clinical molecular biomarkers into a single …