-
Should We Still Pretrain Encoders with Masked Language Modeling?
Paper • 2507.00994 • Published • 74 -
MLMvsCLM/610m-mlm40-42k-10000
Feature Extraction • Updated • 12 -
MLMvsCLM/610m-clm-40k-mlm20-42k
Feature Extraction • Updated • 12 -
MLMvsCLM/1b-mlm40-42k
Feature Extraction • Updated • 11
Hippolyte Gisserot-Boukhlef
hgissbkh
AI & ML interests
NLP, Information Retrieval, Uncertainty Estimation
Recent Activity
commented on
a paper
8 days ago
Should We Still Pretrain Encoders with Masked Language Modeling?
updated
a Space
18 days ago
MLMvsCLM/README
upvoted
a
paper
21 days ago
Should We Still Pretrain Encoders with Masked Language Modeling?
Organizations
-
EuroBERT: Scaling Multilingual Encoders for European Languages
Paper • 2503.05500 • Published • 81 -
EuroBERT/EuroBERT-210m
Fill-Mask • 0.3B • Updated • 18.2k • 73 -
EuroBERT/EuroBERT-610m
Fill-Mask • 0.8B • Updated • 5.15k • 30 -
EuroBERT/EuroBERT-2.1B
Fill-Mask • 2B • Updated • 1.24k • 58
-
Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis
Paper • 2409.20059 • Published • 17 -
hgissbkh/ALMA-13B-LoRA
Text Generation • 13B • Updated • 7 -
hgissbkh/ALMA-13B-LoRA-SFT-xCOMET-QE-Multi
Text Generation • 13B • Updated • 10 -
hgissbkh/ALMA-13B-LoRA-CPO-xCOMET-QE-Multi
Text Generation • 13B • Updated • 9
-
Should We Still Pretrain Encoders with Masked Language Modeling?
Paper • 2507.00994 • Published • 74 -
MLMvsCLM/610m-mlm40-42k-10000
Feature Extraction • Updated • 12 -
MLMvsCLM/610m-clm-40k-mlm20-42k
Feature Extraction • Updated • 12 -
MLMvsCLM/1b-mlm40-42k
Feature Extraction • Updated • 11
-
EuroBERT: Scaling Multilingual Encoders for European Languages
Paper • 2503.05500 • Published • 81 -
EuroBERT/EuroBERT-210m
Fill-Mask • 0.3B • Updated • 18.2k • 73 -
EuroBERT/EuroBERT-610m
Fill-Mask • 0.8B • Updated • 5.15k • 30 -
EuroBERT/EuroBERT-2.1B
Fill-Mask • 2B • Updated • 1.24k • 58
-
Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis
Paper • 2409.20059 • Published • 17 -
hgissbkh/ALMA-13B-LoRA
Text Generation • 13B • Updated • 7 -
hgissbkh/ALMA-13B-LoRA-SFT-xCOMET-QE-Multi
Text Generation • 13B • Updated • 10 -
hgissbkh/ALMA-13B-LoRA-CPO-xCOMET-QE-Multi
Text Generation • 13B • Updated • 9