Modifications récentes
Suivez les changements les plus récents du wiki sur cette page.
Légende des abréviations :
- N
- Cette modification a créé une nouvelle page (voir aussi la liste des nouvelles pages)
- m
- Cette modification est mineure.
- b
- Cette modification a été effectuée par un robot.
- (±123)
- La taille de la page a changé de ce nombre d’octets.
12 juin 2024
|
|
15:33 | Representation Fine-Tuning 3 modifications historique +602 [Patrickdrouin (3×)] | |||
|
|
15:33 (actu | diff) −36 Patrickdrouin discussion contributions | ||||
|
|
15:33 (actu | diff) +1 Patrickdrouin discussion contributions | ||||
|
|
15:32 (actu | diff) +637 Patrickdrouin discussion contributions | ||||
| 14:53 | Journal des renommages Patrickdrouin discussion contributions a déplacé la page Machine Unlearning vers Désapprentissage automatique | ||||
|
|
14:53 | Machine Unlearning 6 modifications historique +1 045 [Patrickdrouin (6×)] | |||
|
|
14:53 (actu | diff) +41 Patrickdrouin discussion contributions | ||||
|
|
14:51 (actu | diff) +119 Patrickdrouin discussion contributions | ||||
|
|
14:47 (actu | diff) −8 Patrickdrouin discussion contributions | ||||
|
|
14:45 (actu | diff) −1 Patrickdrouin discussion contributions | ||||
|
|
14:44 (actu | diff) +1 Patrickdrouin discussion contributions | ||||
|
|
14:42 (actu | diff) +893 Patrickdrouin discussion contributions | ||||
10 juin 2024
|
|
10:00 | Catégorie:Quantique 2 modifications historique +11 [Pitpitt (2×)] | |||
|
|
10:00 (actu | diff) +1 Pitpitt discussion contributions | ||||
|
|
09:25 (actu | diff) +10 Pitpitt discussion contributions | ||||
|
|
N 09:59 | Parrot 4 modifications historique +675 [Pitpitt (4×)] | |||
|
|
09:59 (actu | diff) +27 Pitpitt discussion contributions | ||||
|
|
09:28 (actu | diff) +1 Pitpitt discussion contributions | ||||
|
|
09:28 (actu | diff) 0 Pitpitt discussion contributions | ||||
| N |
|
09:28 (actu | diff) +647 Pitpitt discussion contributions (Page créée avec « == Définition == XXXXXXXXX == Français == ''' Parrot''' == Anglais == ''' Parrot''' Existing methods mainly focus on aligning vision encoders with LLMs through supervised fine-tuning (SFT) to endow LLMs with multimodal abilities, making MLLMs' inherent ability to react to multiple languages progressively deteriorate as the training process evolves. We empirically find that the imbalanced SFT datasets, primarily composed of English-centric image-text pairs... ») | |||
