🔄 In a Training Loop

Dmitry Ryumin PRO

DmitryRyumin

53 137 229

https://dmitryryumin.github.io

DmitryRyumin

AI & ML interests

Machine Learning and Applications, Multi-Modal Understanding

Recent Activity

upvoted a collection about 18 hours ago

WeVisOne-VL

upvoted a paper about 18 hours ago

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

liked a dataset 2 days ago

laion/emonet-face-big

View all activity

Organizations

upvoted a collection about 18 hours ago

WeVisOne-VL

Collection

3 items • Updated 1 day ago • 7

upvoted a paper about 18 hours ago

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

Paper • 2610.31329 • Published 3 days ago • 233

liked a dataset 2 days ago

laion/emonet-face-big

Viewer • Updated Oct 20, 2025 • 262k • 367 • 11

upvoted a paper 4 days ago

MemT-1.0: Towards Memory-Native Evolution

Paper • 2610.26825 • Published 6 days ago • 177

upvoted an article 10 days ago

Article

UltraBERT: One Encoder for Classification and Retrieval

dmis-lab

•

11 days ago

• 64

upvoted a collection 10 days ago

UltraBERT

Collection

UltraBERT: Beyond the Limit of BERT Pre-Training. Pre-trained 150M/380M encoders and a text embedding model, English, 32K context. • 4 items • Updated 11 days ago • 30

upvoted a paper 14 days ago

Recurrent Looped Transformer

Paper • 2610.07591 • Published 19 days ago • 36

liked 2 datasets 18 days ago

Abhijeet8901/XPlainVerse

Preview • Updated Aug 8 • 22 • 14

inesc-id/multimodal_care

Viewer • Updated Jul 29 • 4.28k • 137 • 4

upvoted 2 papers 19 days ago

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

Paper • 2610.05608 • Published 21 days ago • 176

RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

Paper • 2610.01780 • Published 24 days ago • 289

liked a dataset 24 days ago

zaqxsw0526/MMDF

Viewer • Updated Sep 4 • 33.7k • 1.39k • 5

liked a model 28 days ago

espnet/meld_esp2_cls_wavlm_base_plus

Updated Sep 21 • 20 • 1

liked a dataset 28 days ago

espnet/yodas3

Viewer • Updated 17 days ago • 4.08M • 420k • 253

liked a dataset 29 days ago

HuggingFaceM4/something_something_v2

Updated Oct 20, 2022 • 455 • 27

liked a model about 1 month ago

nvidia/Nemotron-3-Diarization

Voice Activity Detection • 99.2M • Updated about 1 month ago • 118k • 805

upvoted an article about 1 month ago

Article

Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization

nvidia

•

Sep 23

• 71

liked 3 models about 1 month ago