Igor Shatalin's picture

Igor Shatalin

blanchefort

·

https://skl.vc/

AI & ML interests

None yet

Recent Activity

upvoted a collection 25 minutes ago

updated a collection 14 days ago

updated a collection 19 days ago

View all activity

Organizations

upvoted a collection 25 minutes ago

talkie-13b

talkie-1930-13b is a vintage language model trained on pre-1931 English-language text. See https://github.com/talkie-lm/talkie to run talkie. • 3 items • Updated 17 days ago • 47

upvoted a collection 28 days ago

Gemma 4

12 items • Updated 3 days ago • 765

upvoted a collection about 2 months ago

GreenVLA

8 items • Updated Mar 5 • 8

upvoted 2 collections 2 months ago

Tiny Aya

Bridging Scale and Multilingual Depth • 10 items • Updated Feb 17 • 69

GigaChat3

6 items • Updated Dec 5, 2025 • 18

upvoted a collection 3 months ago

Xiaomi-Robotics-0

6 items • Updated Mar 5 • 12

upvoted 2 papers 3 months ago

Green-VLA: Staged Vision-Language-Action Model for Generalist Robots

Paper • 2602.00919 • Published Jan 31 • 324

Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective

Paper • 2506.17930 • Published Jun 22, 2025 • 19

upvoted 2 collections 3 months ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 15 items • Updated Mar 10 • 626

Qwen3-TTS

7 items • Updated Jan 22 • 357

upvoted 4 collections 4 months ago

KVAE 1.0

KVAE 1.0 tokenizers are for images (KVAE-2D-1.0) and video (KVAE-3D-1.0) are distributed under MIT license (commercial use is possible). • 2 items • Updated Dec 14, 2025 • 7

MedGemma Release

Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 9 items • Updated Mar 12 • 487

TranslateGemma

3 items • Updated Mar 12 • 237

VideoPrism

VideoPrism is a foundational video encoder that enables state-of-the-art performance on a large variety of video understanding tasks. • 5 items • Updated Mar 12 • 19

upvoted a paper 4 months ago

Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models

Paper • 2512.00590 • Published Nov 29, 2025 • 52

upvoted 2 collections 6 months ago

Qwen3-VL

37 items • Updated Dec 31, 2025 • 713

Saiga GGUF

Russian fine-tunes of different base LLMs in the GGUF format compatible with llama.cpp • 8 items • Updated Apr 27, 2025 • 39

upvoted 3 papers 8 months ago

DTrOCR: Decoder-only Transformer for Optical Character Recognition

Paper • 2308.15996 • Published Aug 30, 2023 • 4

Transformer-Based Approach for Joint Handwriting and Named Entity Recognition in Historical documents

Paper • 2112.04189 • Published Dec 8, 2021 • 3

General Detection-based Text Line Recognition

Paper • 2409.17095 • Published Sep 25, 2024 • 1