Phillip Rust

@rust_phillip

Research Scientist @AIatMeta (FAIR) • PhD @coastalcph

Paris, France

phillip.rs

Replies Reposts Media

Pinned
Phillip Rust
@rust_phillip
Jan 24, 2023
Happy to share our paper on language modelling with pixels has been accepted to ICLR‘23 (notable-top-5% / oral) 🎉. Big thanks and congrats to Team-PIXEL @jonasflotz @ebugliarello @esalesk @mdlhx @delliott and looking forward to presenting in Kigali! 🌍 #ICLR2023
Emanuele Bugliarello
@ebugliarello
Jul 15, 2022
Tired of tokenizers/subwords? Check out PIXEL, a new language model that processes written text as images📸 “Language Modelling with Pixels” 📄 arxiv.org/abs/2207.06991 🧑‍💻github.com/xplip/pixel 🤖huggingface.co/Team-PIXEL/pix… by @rust_phillip @jonasflotz me @esalesk @mdlhx @delliott
Phillip Rust
@rust_phillip
Aug 12, 2024
I will be presenting this work in-person at ACL🇹🇭 this week. Drop by if you'd like to chat! Oral: Today (Monday) 16:30 Poster: Tuesday (Tomorrow) 10:30 - 12:00
Phillip Rust
@rust_phillip
Feb 23, 2024
Introducing “Towards Privacy-Aware Sign Language Translation at Scale” We leverage self-supervised pretraining on anonymized videos, achieving SOTA ASL-to-English translation performance while mitigating risks arising from biometric data. 📄: arxiv.org/abs/2402.09611 🧵(1/9)
Phillip Rust
@rust_phillip
Feb 23, 2024
Introducing “Towards Privacy-Aware Sign Language Translation at Scale” We leverage self-supervised pretraining on anonymized videos, achieving SOTA ASL-to-English translation performance while mitigating risks arising from biometric data. 📄: arxiv.org/abs/2402.09611 🧵(1/9)
Phillip Rust
@rust_phillip
Aug 2, 2022
We have now released the rendered English Wikipedia and BookCorpus datasets used to train our PIXEL model under huggingface.co/Team-PIXEL and they can be loaded via the datasets library. Thanks to @huggingface for hosting our >100GB of image data completely for free!
Team-PIXEL (Team-PIXEL)
From huggingface.co
Phillip Rust
@rust_phillip
Jul 15, 2022
thanks @_akhaliq for sharing our work!! :)
AK
@_akhaliq
Jul 15, 2022
Language Modelling with Pixels abs: arxiv.org/abs/2207.06991 introduced PIXEL, a pretrained language model that renders text as images, which allows it to represent any written language that can be typeset using its text renderer