Russian User Memory Benchmark: Evaluating long-context memory
ai-forever PRO
ai-forever
AI & ML interests
NLP, CV, multimodal, python3, pytorch, machine learning, deep learning
Recent Activity
new activity 3 days ago
ai-forever/FRIDA:add MTEB and rusBEIR results updated a model 3 days ago
ai-forever/FRIDA upvoted an article 20 days ago
Security incident disclosure — July 2026Organizations
-
kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers
2B • Updated • 171 • 4 -
kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers
2B • Updated • 17 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers
2B • Updated • 292 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-5s-Diffusers
2B • Updated • 12 • 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 • 14B • Updated • 269 • 6 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.5-STA-11-5-5
Text-to-Video • 14B • Updated • 175 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.6-STA-11-3-3
Text-to-Video • 14B • Updated • 120 • 1 -
nablaNABLA: Neighborhood Adaptive Block-Level Attention
Paper • 2507.13546 • Published • 126
FiMMIA: scaling semantic perturbation-based membership inference across modalities.
LLM-as-a-judge
Collection with our sentence embedding models, like sbert, e5 etc.
-
ai-forever/sbert_large_mt_nlu_ru
Feature Extraction • 0.4B • Updated • 583 • • 26 -
ai-forever/sbert_large_nlu_ru
Feature Extraction • 0.4B • Updated • 30.4k • • 104 -
ai-forever/ru-en-RoSBERTa
Feature Extraction • 0.4B • Updated • 133k • • 86 -
ai-forever/FRIDA
Feature Extraction • 0.8B • Updated • 127k • • 147
Russian User Memory Benchmark: Evaluating long-context memory
FiMMIA: scaling semantic perturbation-based membership inference across modalities.
-
kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers
2B • Updated • 171 • 4 -
kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers
2B • Updated • 17 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers
2B • Updated • 292 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-5s-Diffusers
2B • Updated • 12 • 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 • 14B • Updated • 269 • 6 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.5-STA-11-5-5
Text-to-Video • 14B • Updated • 175 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.6-STA-11-3-3
Text-to-Video • 14B • Updated • 120 • 1 -
nablaNABLA: Neighborhood Adaptive Block-Level Attention
Paper • 2507.13546 • Published • 126
LLM-as-a-judge
Collection with our sentence embedding models, like sbert, e5 etc.
-
ai-forever/sbert_large_mt_nlu_ru
Feature Extraction • 0.4B • Updated • 583 • • 26 -
ai-forever/sbert_large_nlu_ru
Feature Extraction • 0.4B • Updated • 30.4k • • 104 -
ai-forever/ru-en-RoSBERTa
Feature Extraction • 0.4B • Updated • 133k • • 86 -
ai-forever/FRIDA
Feature Extraction • 0.8B • Updated • 127k • • 147