Georgy Makarov

makarov-gv's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection about 6 hours ago

Kandinsky 6.0 Diffusers

Collection

6 items • Updated 1 day ago • 16

authored a paper about 11 hours ago

Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

Paper • 2610.05608 • Published 3 days ago • 113

upvoted a paper about 14 hours ago

KVAE: Family of Tokenizers for Multimodal Generative Models

Paper • 2608.05798 • Published Aug 6 • 31

upvoted a paper about 16 hours ago

Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

Paper • 2610.05608 • Published 3 days ago • 113

upvoted a paper 11 days ago

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

Paper • 2609.29845 • Published 13 days ago • 104

liked 3 models 3 months ago

ai-sage/GigaChat3-10B-A1.8B-base

Text Generation • 11B • Updated Nov 22, 2025 • 258 • 15

ai-sage/GFusion-10B-A1.8B-base

Text Generation • 11B • Updated Jul 21 • 223 • 17

ai-sage/GFusion-10B-A1.8B

Text Generation • 11B • Updated Jul 5 • 207 • 20

upvoted a collection 3 months ago

KVAE-Audio

Collection

KVAE-Audio is a continuous full-band audio waveform autoencoder • 2 items • Updated 1 day ago • 7

liked a model 3 months ago

kandinskylab/KVAE-Audio

Audio-to-Audio • 0.2B • Updated Aug 10 • 171 • 60

liked a Space 4 months ago

Runtime error

Agents

4

MASAI

😀

4

Intelligent system for Multimodal Affective States Analysis

upvoted a collection 4 months ago

Kandinsky 5.0 Video Pro Diffusers

Collection

Kandinsky 5.0 Video Pro is a 19B model that generates high-quality HD videos from English and Russian prompts with controllable camera motion. • 4 items • Updated 1 day ago • 15

liked 2 models 6 months ago

kandinskylab/Kandinsky-5.0-I2V-Pro-sft-5s-Diffusers

19B • Updated Jun 27 • 60 • 33

kandinskylab/KVAE-3D-2.0-t4s16

2B • Updated Aug 11 • 21.5k • 13

liked a model 7 months ago

kandinskylab/Kandinsky-5.0-I2V-Lite-5s

Image-to-Video • Updated Nov 20, 2025 • 34 • 17

upvoted a paper 8 months ago

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders

Paper • 2602.05027 • Published Feb 4 • 63

upvoted 2 papers 10 months ago

T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground

Paper • 2512.10430 • Published Dec 11, 2025 • 121

Multimodal Evaluation of Russian-language Architectures

Paper • 2511.15552 • Published Nov 19, 2025 • 79

upvoted 2 papers 11 months ago

Unveiling Intrinsic Dimension of Texts: from Academic Abstract to Creative Story

Paper • 2511.15210 • Published Nov 19, 2025 • 91

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Paper • 2511.14993 • Published Nov 19, 2025 • 236