Simeon Emanuilov PRO

s-emanuilov

AI & ML interests

Software Engineer & Ph.D. candidate | Specializing in ML/DL system development & applying AI to solve real-world business problems.

Recent Activity

posted an update 7 days ago

Converted PaddleOCR models to ONNX for easier deployment and faster inference. These have been working well in production at Monkt.com, so figured I'd share them with the community. Just straight conversions of the original models—might save you some time if you're building OCR pipelines. https://huggingface.co/monkt/paddleocr-onnx

commented on a paper 7 days ago

Stemming Hallucination in Language Models Using a Licensing Oracle

authored a paper 8 days ago

How Large Language Models are Designed to Hallucinate

View all activity

Organizations

upvoted an article about 1 month ago

Article

SOTA OCR with Core ML and dots.ocr

Oct 2

•

upvoted a collection about 1 month ago

PP-OCRv5

Collection

PP-OCRv5 is the latest text recognition solution, supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese • 13 items • Updated Sep 15 • 49

upvoted an article 2 months ago

Article

mmBERT: ModernBERT goes Multilingual

Sep 9

•

125

upvoted a paper 2 months ago

Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth

Paper • 2509.03867 • Published Sep 4 • 209

upvoted a paper 3 months ago

MMTEB: Massive Multilingual Text Embedding Benchmark

Paper • 2502.13595 • Published Feb 19 • 41

upvoted a collection 3 months ago

EmbeddingGemma

Collection

3 items • Updated Sep 11 • 98

upvoted an article 3 months ago

Article

Welcome EmbeddingGemma, Google's new efficient embedding model

Sep 4

•

256

upvoted a collection 4 months ago

Health AI Developer Foundations (HAI-DEF)

Collection

Groups models released for use in health AI by Google. Read more about HAI-DEF at https://developers.google.com/health-ai-developer-foundations • 15 items • Updated Jul 10 • 110

upvoted a collection 5 months ago

Tucan

Collection

A series of open-source Bulgarian language models fine-tuned for function calling and tool use. 2.6B, 9B, and 27B parameter variants. • 12 items • Updated Jul 1 • 1

upvoted an article 6 months ago

Article

Train 400x faster Static Embedding Models with Sentence Transformers

Jan 15

•

218

upvoted a paper 7 months ago

CoLLM: A Large Language Model for Composed Image Retrieval

Paper • 2503.19910 • Published Mar 25 • 15

upvoted 2 articles 8 months ago

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

May 28, 2024

•

259

Article

Training and Finetuning Reranker Models with Sentence Transformers v4

Mar 26

•

175

upvoted a paper 8 months ago

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

Paper • 2503.11576 • Published Mar 14 • 117

upvoted 3 articles 9 months ago

Article

PaliGemma 2 Mix - New Instruction Vision Language Models by Google

Feb 19

•

Article

SigLIP 2: A better multilingual vision language encoder

Feb 21

•

192

Article

Merge Large Language Models with mergekit

Jan 9, 2024

•

145

upvoted 2 papers 9 months ago

Fast Video Generation with Sliding Tile Attention

Paper • 2502.04507 • Published Feb 6 • 51

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Paper • 2402.03300 • Published Feb 5, 2024 • 131

upvoted a paper 10 months ago

Executable Code Actions Elicit Better LLM Agents

Paper • 2402.01030 • Published Feb 1, 2024 • 181

Simeon Emanuilov PRO

AI & ML interests

Recent Activity

Organizations

s-emanuilov's activity

SOTA OCR with Core ML and dots.ocr

mmBERT: ModernBERT goes Multilingual

Welcome EmbeddingGemma, Google's new efficient embedding model

Train 400x faster Static Embedding Models with Sentence Transformers

Training and Finetuning Embedding Models with Sentence Transformers v3

Training and Finetuning Reranker Models with Sentence Transformers v4

PaliGemma 2 Mix - New Instruction Vision Language Models by Google

SigLIP 2: A better multilingual vision language encoder

Merge Large Language Models with mergekit