Stas Bekman

3 papers · 2021–2023 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad ❓ The Questioner

Venues

EMNLP (2) NeurIPS (1)

Top co-authors

Victor Sanh (3) Alexander Rush (2) Thomas Wang (2) Teven Le Scao (2) Siddharth Karamcheti (1) Patrick von Platen (1) Joe Davison (1) Philipp Schmid (1) Sheng Shen (1) Colin Raffel (1)

Research topics

Machine Learning (2) Natural Language Processing (2) Resources & Methods (2) Computer Science (1) Deep Learning (1) Application Areas (1) Generation (1) Learning Types (1) Models (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1) Systems (1)

Keywords

large language model (2) multimodal learning (1) model training (1) vision-language model (1) zero-shot generalization (1) model scaling (1) pretraining corpus (1) multilingual model (1) data filtering (1) scaling behavior (1) multilingual language model (1) ablation study (1) corpus curation (1) nlp dataset (1) interleaved image-text (1) web-scale dataset (1) community contribution (1) corpus management (1) dataset library (1) transformer architecture (1)

Papers

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents NeurIPS 2023 What Language Model to Train if You Have One Million GPU Hours? EMNLP 2022 Datasets: A Community Library for Natural Language Processing EMNLP 2021