FiMMIA: scaling semantic perturbation-based membership inference across modalities.
ai-forever
ai-forever
AI & ML interests
NLP, CV, multimodal, python3, pytorch, machine learning, deep learning
Recent Activity
updated
a collection
8 days ago
FiMMIA
updated
a collection
8 days ago
FiMMIA
updated
a collection
8 days ago
FiMMIA
Organizations
Kandinsky 5.0
POLLUX
LLM-as-a-judge
RU-MTEB
SentenceEmbedders
Collection with our sentence embedding models, like sbert, e5 etc.
-
ai-forever/sbert_large_mt_nlu_ru
Feature Extraction • 0.4B • Updated • 3.68k • • 26 -
ai-forever/sbert_large_nlu_ru
Feature Extraction • 0.4B • Updated • 84.3k • • 97 -
ai-forever/ru-en-RoSBERTa
Feature Extraction • 0.4B • Updated • 269k • • 62 -
ai-forever/FRIDA
Feature Extraction • 0.8B • Updated • 185k • • 124
Kandinsky 5.0 T2V Lite Diffusers
Wan-NABLA
Collection of finetuned models for NABLA: Neighborhood Adaptive Block-Level Attention
https://arxiv.org/abs/2507.13546
-
ai-forever/Wan2.1-T2V-14B-NABLA-0.7
Text-to-Video • Updated • 174 • 5 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.5-STA-11-5-5
Text-to-Video • Updated • 129 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.6-STA-11-3-3
Text-to-Video • Updated • 84 • 1 -
nablaNABLA: Neighborhood Adaptive Block-Level Attention
Paper • 2507.13546 • Published • 124
SAGE v1.1.0 release
ruELECTRA-family
SAGE v1.0.0 release
FiMMIA
FiMMIA: scaling semantic perturbation-based membership inference across modalities.
Kandinsky 5.0 T2V Lite Diffusers
Kandinsky 5.0
Wan-NABLA
Collection of finetuned models for NABLA: Neighborhood Adaptive Block-Level Attention
https://arxiv.org/abs/2507.13546
-
ai-forever/Wan2.1-T2V-14B-NABLA-0.7
Text-to-Video • Updated • 174 • 5 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.5-STA-11-5-5
Text-to-Video • Updated • 129 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.6-STA-11-3-3
Text-to-Video • Updated • 84 • 1 -
nablaNABLA: Neighborhood Adaptive Block-Level Attention
Paper • 2507.13546 • Published • 124
POLLUX
LLM-as-a-judge
SAGE v1.1.0 release
RU-MTEB
ruELECTRA-family
SentenceEmbedders
Collection with our sentence embedding models, like sbert, e5 etc.
-
ai-forever/sbert_large_mt_nlu_ru
Feature Extraction • 0.4B • Updated • 3.68k • • 26 -
ai-forever/sbert_large_nlu_ru
Feature Extraction • 0.4B • Updated • 84.3k • • 97 -
ai-forever/ru-en-RoSBERTa
Feature Extraction • 0.4B • Updated • 269k • • 62 -
ai-forever/FRIDA
Feature Extraction • 0.8B • Updated • 185k • • 124
SAGE v1.0.0 release