·
AI & ML interests
NLP, Privacy, multi-modal DL
Recent Activity
Organizations
-
-
-
-
-
-
-
-
-
-
-
view article ModernVBERT: Towards Smaller Visual Document Retrievers
view article Introducing ColQwen-Omni: Retrieve in every modality
view article Should We Still Pretrain Encoders with Masked Language Modeling?
view article *Context Is Gold to Find the Gold Passage*: Evaluating and Training Contextual Document Embeddings
view article DeepSearch Using Visual RAG in Agentic Frameworks 🔎
view article ViDoRe Benchmark V2: Raising the Bar for Visual Retrieval
view article Introducing EuroBERT: A High-Performance Multilingual Encoder Model
published an
article over 1 year ago view article ColPali: Efficient Document Retrieval with Vision Language Models 👀
published an
article about 2 years ago view article 🥐CroissantLLM: A Truly Bilingual French-English Language Model