Picture for Pierre Colombo

Pierre Colombo

EuroBERT: Scaling Multilingual Encoders for European Languages

Add code
Mar 07, 2025
Viaarxiv icon

Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis

Add code
Sep 30, 2024
Viaarxiv icon

EuroLLM: Multilingual Language Models for Europe

Add code
Sep 24, 2024
Viaarxiv icon

SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain

Add code
Jul 28, 2024
Viaarxiv icon

ColPali: Efficient Document Retrieval with Vision Language Models

Add code
Jul 02, 2024
Viaarxiv icon

SaulLM-7B: A pioneering Large Language Model for Law

Add code
Mar 07, 2024
Viaarxiv icon

Tower: An Open Multilingual Large Language Model for Translation-Related Tasks

Add code
Feb 27, 2024
Figure 1 for Tower: An Open Multilingual Large Language Model for Translation-Related Tasks
Figure 2 for Tower: An Open Multilingual Large Language Model for Translation-Related Tasks
Figure 3 for Tower: An Open Multilingual Large Language Model for Translation-Related Tasks
Figure 4 for Tower: An Open Multilingual Large Language Model for Translation-Related Tasks
Viaarxiv icon

Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism

Add code
Feb 22, 2024
Viaarxiv icon

Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation

Add code
Feb 20, 2024
Viaarxiv icon

Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs

Add code
Feb 20, 2024
Figure 1 for Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Figure 2 for Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Figure 3 for Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Figure 4 for Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
Viaarxiv icon