Dmitry Ryumin PRO

DmitryRyumin's activity

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

upvoted a collection about 14 hours ago

NVIDIA Nemotron v3

Collection

Open, Production-ready Enterprise Models • 46 items • Updated 12 days ago • 394

liked a model about 16 hours ago

kandinskylab/Kandinsky-S2V-1.0-Pro

Image-to-Video • Updated about 7 hours ago • 2

upvoted a collection about 16 hours ago

Kandinsky S2V 1.0

Collection

9 items • Updated about 20 hours ago • 4

liked a Space about 16 hours ago

Running on Zero

Agents

3

Kandinsky S2V 1.0

🗣

3

Speech-driven avatar video from a reference frame

liked a model about 16 hours ago

kandinskylab/Kandinsky-S2V-1.0-Pro-distill-Diffusers

Image-to-Video • 21B • Updated about 7 hours ago • 15 • 9

upvoted a collection 1 day ago

jina-embeddings-v5-omni

Collection

Multimodal (text + image + video + audio) embedding models aligned with jina-embeddings-v5-text-*. Two sizes, four task variants each. • 27 items • Updated Sep 17 • 41

liked 3 models 4 days ago

nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16

Image-Text-to-Text • 124B • Updated 13 days ago • 2.71k • 61

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16

Any-to-Any • 33B • Updated Aug 24 • 116k • 444

jinaai/jina-embeddings-v5-omni-small-classification

Feature Extraction • 2B • Updated 23 days ago • 206 • 2

liked a dataset 4 days ago

ddwang2000/EchoDialogue

Preview • Updated Sep 12 • 1.22k • 6

liked a Space 6 days ago

Running

Featured

34

Nemotron Transcribe

🏃

34

NVIDIA Nemotron Transcribe Demo

liked a dataset 6 days ago

nvidia/Granary-v2

Updated 7 days ago • 5.39k • 45

upvoted a collection 6 days ago

Nemotron 3.5 Transcribe

Collection

Open-weight offline ASR model supporting 40 languages, 1-hr audio, and 64k context. Hybrid MoE (~4.3B active). Available in BF16, FP8, and NVFP4. • 7 items • Updated 5 days ago • 15

liked a model 6 days ago

nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B

Automatic Speech Recognition • 34B • Updated 5 days ago • 38.9k • • 744

upvoted an article 6 days ago

view article

Article

NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt

• 

nvidia

•

7 days ago

• 92

upvoted a collection 11 days ago

WeVisOne-VL

Collection

3 items • Updated 7 days ago • 8

upvoted a paper 11 days ago

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

Paper • 2610.31329 • Published 13 days ago • 45

liked a dataset 12 days ago

laion/emonet-face-big

Viewer • Updated Oct 20, 2025 • 262k • 350 • 11

upvoted a paper 14 days ago

MemT-1.0: Towards Memory-Native Evolution

Paper • 2610.26825 • Published 16 days ago • 175

upvoted an article 20 days ago

view article

Article

UltraBERT: One Encoder for Classification and Retrieval

• 

dmis-lab

•

21 days ago

• 66