FiMMIA: scaling semantic perturbation-based membership inference across modalities.
ai-forever PRO
ai-forever
AI & ML interests
NLP, CV, multimodal, python3, pytorch, machine learning, deep learning
Recent Activity
published
a Space 8 days ago
ai-forever/sage updated
a dataset about 1 month ago
ai-forever/POLLUX-instructions updated
a dataset about 1 month ago
ai-forever/hist-rag-bench-public-questions Organizations
LLM-as-a-judge
-
ai-forever/pollux-judge-7b
Text Generation • 8B • Updated • 466 • 2 -
ai-forever/pollux-judge-7b-r
Text Generation • 8B • Updated • 3 • 4 -
ai-forever/pollux-judge-32b
Text Generation • 33B • Updated • 321 • 5 -
ai-forever/pollux-judge-32b-r
Text Generation • 33B • Updated • 4
-
ai-forever/georeview-classification
Updated • 33 -
ai-forever/headline-classification
Viewer • Updated • 60k • 718 • 1 -
ai-forever/inappropriateness-classification
Viewer • Updated • 54k • 637 • 1 -
ai-forever/kinopoisk-sentiment-classification
Viewer • Updated • 13.5k • 830 • 6
Collection with our sentence embedding models, like sbert, e5 etc.
-
ai-forever/sbert_large_mt_nlu_ru
Feature Extraction • 0.4B • Updated • 1.07k • • 26 -
ai-forever/sbert_large_nlu_ru
Feature Extraction • 0.4B • Updated • 51.1k • • 100 -
ai-forever/ru-en-RoSBERTa
Feature Extraction • 0.4B • Updated • 115k • • 77 -
ai-forever/FRIDA
Feature Extraction • 0.8B • Updated • 286k • • 132
-
kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers
Updated • 470 • 4 -
kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers
Updated • 233 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers
Updated • 101 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-5s-Diffusers
Updated • 1
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 • 268 • 5 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.5-STA-11-5-5
Text-to-Video • Updated • 116 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.6-STA-11-3-3
Text-to-Video • Updated • 120 • 1 -
nablaNABLA: Neighborhood Adaptive Block-Level Attention
Paper • 2507.13546 • Published • 125
FiMMIA: scaling semantic perturbation-based membership inference across modalities.
-
kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers
Updated • 470 • 4 -
kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers
Updated • 233 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers
Updated • 101 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-5s-Diffusers
Updated • 1
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 • 268 • 5 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.5-STA-11-5-5
Text-to-Video • Updated • 116 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.6-STA-11-3-3
Text-to-Video • Updated • 120 • 1 -
nablaNABLA: Neighborhood Adaptive Block-Level Attention
Paper • 2507.13546 • Published • 125
LLM-as-a-judge
-
ai-forever/pollux-judge-7b
Text Generation • 8B • Updated • 466 • 2 -
ai-forever/pollux-judge-7b-r
Text Generation • 8B • Updated • 3 • 4 -
ai-forever/pollux-judge-32b
Text Generation • 33B • Updated • 321 • 5 -
ai-forever/pollux-judge-32b-r
Text Generation • 33B • Updated • 4
-
ai-forever/georeview-classification
Updated • 33 -
ai-forever/headline-classification
Viewer • Updated • 60k • 718 • 1 -
ai-forever/inappropriateness-classification
Viewer • Updated • 54k • 637 • 1 -
ai-forever/kinopoisk-sentiment-classification
Viewer • Updated • 13.5k • 830 • 6
Collection with our sentence embedding models, like sbert, e5 etc.
-
ai-forever/sbert_large_mt_nlu_ru
Feature Extraction • 0.4B • Updated • 1.07k • • 26 -
ai-forever/sbert_large_nlu_ru
Feature Extraction • 0.4B • Updated • 51.1k • • 100 -
ai-forever/ru-en-RoSBERTa
Feature Extraction • 0.4B • Updated • 115k • • 77 -
ai-forever/FRIDA
Feature Extraction • 0.8B • Updated • 286k • • 132