Sarah Pratt

5 papers · 2020–2024 · 3 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 · Legion ❓ The Questioner

Venues

NeurIPS (3) ECCV (1) ICCV (1)

Top co-authors

Ali Farhadi (4) Gabriel Ilharco (2) Thao Nguyen (2) Giannis Daras (2) Sham Kakade (2) Yair Carmon (2) Vaishaal Shankar (2) Dhruba Ghosh (2) Jenia Jitsev (2) Georgios Smyrnis (2)

Research topics

Machine Learning (3) Natural Language Processing (3) Application Areas (2) Generation (2) Learning Types · Machine Learning (2) Artificial Intelligence (1) Deep Learning (1) Core AI (1) Learning Types · Deep Learning (1) Resources & Methods (1)

Keywords

language model (2) data filtering (2) multimodal dataset (1) zero-shot image classification (1) image-text pair (1) prompt generation (1) clip model (1) data curation (1) decoding algorithm (1) zero-shot accuracy (1) dataset filtering (1) autoregressive inference (1) large language model (1) open-vocabulary model (1) superposed decoding (1) zero-shot learning (1) multiple generation (1) text generation (1)

Papers

DataComp-LM: In search of the next generation of training sets for language models NeurIPS 2024 Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass NeurIPS 2024 DataComp: In search of the next generation of multimodal datasets NeurIPS 2023 What Does a Platypus Look Like? Generating Customized Prompts for Zero-Shot Image Classification ICCV 2023 Grounded Situation Recognition ECCV 2020