Théo Deschamps-Berger

TheoDB

·

https://scholar.google.com/citations?user=c1qB3dcAAAAJ&hl=en

AI & ML interests

Multimodal - Speech - NLP

Recent Activity

liked a model 9 days ago

XiaomiMiMo/MiMo-V2.6-Flash-RL

liked a dataset 11 days ago

secemp9/arxiv-complete

liked a dataset about 1 month ago

datapointai/text-to-speech-human-preferences-315k

View all activity

Organizations

upvoted a collection 4 months ago

BidirLM - Embedding

1 item • Updated Aug 27 • 1

upvoted an article 6 months ago

Article

BidirLM: Turning Generative LLMs into the Best Open-Source Omnimodal Encoders

Nicolas-BZRD

•

Apr 7

• 28

upvoted a paper 6 months ago

BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs

Paper • 2604.02045 • Published Apr 2 • 36

upvoted 2 articles about 1 year ago

Article

Design choices for Vision Language Models in 2024

gigant

•

Apr 16, 2024

• 35

Article

Introducing EuroBERT: A High-Performance Multilingual Encoder Model

EuroBERT

•

Mar 10, 2025

• 150

upvoted a paper about 1 year ago

Should We Still Pretrain Encoders with Masked Language Modeling?

Paper • 2507.00994 • Published Jul 1, 2025 • 81

upvoted a paper over 1 year ago

EuroBERT: Scaling Multilingual Encoders for European Languages

Paper • 2503.05500 • Published Mar 7, 2025 • 81