Mariusz Kurman's picture

Mariusz Kurman PRO

mkurman

AI & ML interests

AI Tech Lead | MD

Recent Activity

reacted to openfree's post with πŸ”₯ about 12 hours ago
# 🧬 Protein Genesis AI: Design Proteins with Just a Prompt ## πŸ€” Current Challenges in Protein Design Traditional protein design faces critical barriers: - πŸ’° High costs ($1M - $10M+) & long development cycles (2-3 years) - πŸ”¬ Complex equipment and expert knowledge required - πŸ“‰ Low success rates (<10%) - ⏰ Time-consuming experimental validation ## ✨ Our Solution: Protein Genesis AI Transform protein design through simple natural language input: ``` "Design a protein that targets cancer cells" "Create an enzyme that breaks down plastic" ``` ### Key Features - πŸ€– AI-powered automated design - πŸ“Š Real-time analysis & optimization - πŸ”¬ Instant 3D visualization - πŸ’Ύ Immediate PDB file generation ## 🎯 Applications ### Medical & Industrial - πŸ₯ Drug development - πŸ’‰ Antibody design - 🏭 Industrial enzymes - ♻️ Environmental solutions ### Research & Education - πŸ”¬ Basic research - πŸ“š Educational tools - 🧫 Experimental design - πŸ“ˆ Data analysis ## πŸ’« Key Advantages - πŸ‘¨β€πŸ’» No coding or technical expertise needed - ⚑ Results in minutes (vs. years) - πŸ’° 90% cost reduction - 🌐 Accessible anywhere ## πŸŽ“ Who Needs This? - 🏒 Biotech companies - πŸ₯ Pharmaceutical research - πŸŽ“ Academic institutions - πŸ§ͺ Research laboratories ## 🌟 Why It Matters Protein Genesis AI democratizes protein design by transforming complex processes into simple text prompts. This breakthrough accelerates scientific discovery, potentially leading to faster drug development and innovative biotechnology solutions. The future of protein design starts with a simple prompt! πŸš€ https://huggingface.co/spaces/openfree/ProteinGenesis
reacted to singhsidhukuldeep's post with πŸ‘€ about 12 hours ago
Exciting breakthrough in e-commerce recommendation systems! Walmart Global Tech researchers have developed a novel Triple Modality Fusion (TMF) framework that revolutionizes how we make product recommendations. >> Key Innovation The framework ingeniously combines three distinct data types: - Visual data to capture product aesthetics and context - Textual information for detailed product features - Graph data to understand complex user-item relationships >> Technical Architecture The system leverages a Large Language Model (Llama2-7B) as its backbone and introduces several sophisticated components: Modality Fusion Module - All-Modality Self-Attention (AMSA) for unified representation - Cross-Modality Attention (CMA) mechanism for deep feature integration - Custom FFN adapters to align different modality embeddings Advanced Training Strategy - Curriculum learning approach with three complexity levels - Parameter-Efficient Fine-Tuning using LoRA - Special token system for behavior and item representation >> Real-World Impact The results are remarkable: - 38.25% improvement in Electronics recommendations - 43.09% boost in Sports category accuracy - Significantly higher human evaluation scores compared to traditional methods Currently deployed in Walmart's production environment, this research demonstrates how combining multiple data modalities with advanced LLM architectures can dramatically improve recommendation accuracy and user satisfaction.
new activity about 22 hours ago
mkurman/llama-3.2-MEDIT-3B-o1:space
View all activity

Organizations

MedIT Solutions's profile picture BigScience Biomedical Datasets's profile picture SOWA Project's profile picture

mkurman's activity

reacted to openfree's post with πŸ”₯ about 12 hours ago
view post
Post
2038
# 🧬 Protein Genesis AI: Design Proteins with Just a Prompt

## πŸ€” Current Challenges in Protein Design

Traditional protein design faces critical barriers:
- πŸ’° High costs ($1M - $10M+) & long development cycles (2-3 years)
- πŸ”¬ Complex equipment and expert knowledge required
- πŸ“‰ Low success rates (<10%)
- ⏰ Time-consuming experimental validation

## ✨ Our Solution: Protein Genesis AI

Transform protein design through simple natural language input:
"Design a protein that targets cancer cells"
"Create an enzyme that breaks down plastic"


### Key Features
- πŸ€– AI-powered automated design
- πŸ“Š Real-time analysis & optimization
- πŸ”¬ Instant 3D visualization
- πŸ’Ύ Immediate PDB file generation

## 🎯 Applications

### Medical & Industrial
- πŸ₯ Drug development
- πŸ’‰ Antibody design
- 🏭 Industrial enzymes
- ♻️ Environmental solutions

### Research & Education
- πŸ”¬ Basic research
- πŸ“š Educational tools
- 🧫 Experimental design
- πŸ“ˆ Data analysis

## πŸ’« Key Advantages

- πŸ‘¨β€πŸ’» No coding or technical expertise needed
- ⚑ Results in minutes (vs. years)
- πŸ’° 90% cost reduction
- 🌐 Accessible anywhere

## πŸŽ“ Who Needs This?
- 🏒 Biotech companies
- πŸ₯ Pharmaceutical research
- πŸŽ“ Academic institutions
- πŸ§ͺ Research laboratories

## 🌟 Why It Matters
Protein Genesis AI democratizes protein design by transforming complex processes into simple text prompts. This breakthrough accelerates scientific discovery, potentially leading to faster drug development and innovative biotechnology solutions. The future of protein design starts with a simple prompt! πŸš€

openfree/ProteinGenesis
Β·
reacted to singhsidhukuldeep's post with πŸ‘€ about 12 hours ago
view post
Post
851
Exciting breakthrough in e-commerce recommendation systems!
Walmart Global Tech researchers have developed a novel Triple Modality Fusion (TMF) framework that revolutionizes how we make product recommendations.

>> Key Innovation
The framework ingeniously combines three distinct data types:
- Visual data to capture product aesthetics and context
- Textual information for detailed product features
- Graph data to understand complex user-item relationships

>> Technical Architecture
The system leverages a Large Language Model (Llama2-7B) as its backbone and introduces several sophisticated components:

Modality Fusion Module
- All-Modality Self-Attention (AMSA) for unified representation
- Cross-Modality Attention (CMA) mechanism for deep feature integration
- Custom FFN adapters to align different modality embeddings

Advanced Training Strategy
- Curriculum learning approach with three complexity levels
- Parameter-Efficient Fine-Tuning using LoRA
- Special token system for behavior and item representation

>> Real-World Impact
The results are remarkable:
- 38.25% improvement in Electronics recommendations
- 43.09% boost in Sports category accuracy
- Significantly higher human evaluation scores compared to traditional methods

Currently deployed in Walmart's production environment, this research demonstrates how combining multiple data modalities with advanced LLM architectures can dramatically improve recommendation accuracy and user satisfaction.
New activity in mkurman/llama-3.2-MEDIT-3B-o1 about 22 hours ago

space

1
#1 opened 1 day ago by
reonyy
reacted to Sri-Vigneshwar-DJ's post with πŸ”₯ 1 day ago
view post
Post
1311
Combining smolagents with Anthropic’s best practices simplifies building powerful AI agents:

1. Code-Based Agents: Write actions as Python code, reducing steps by 30%.
2. Prompt Chaining: Break tasks into sequential subtasks with validation gates.
3. Routing: Classify inputs and direct them to specialized handlers.
4. Fallback: Handle tasks even if classification fails.

https://huggingface.co/blog/Sri-Vigneshwar-DJ/building-effective-agents-with-anthropics-best-pra
reacted to ezgikorkmaz's post with πŸ”₯ 1 day ago
posted an update 1 day ago
view post
Post
1049
I kindly invite you to try my experimental Llama 3.2 3B with o1-like thinking.

It utilizes Thoughts when needed, so don't be surprised when it's not. It also has a minor bug that requires further fine-tuning (sometimes it starts with the <|python_tag|> instead of <Thought>).

Enjoy!

Give some likes and whatever to make me feel better and motivated to keep going πŸ˜‚

mkurman/llama-3.2-MEDIT-3B-o1
New activity in Datou1111/shou_xin 24 days ago

Add generated example

1
#3 opened 24 days ago by
mkurman
reacted to reddgr's post with πŸ‘€ about 1 month ago
view post
Post
1822
Thought it would only make sense to share this here. Lately, one of my favorite activities has been annotating prompts and putting them into datasets ( reddgr/tl-test-learn-prompts reddgr/rq-request-question-prompts reddgr/nli-chatbot-prompt-categorization), which I then use to classify and select chatbot conversations for my website. It's quite fun to use this widget on the lmsys/lmsys-chat-1m, but I also use it on my 2 years of talking to chatbots (soon to be dataset, but still a lot of web scraping and ETL work left)... This one in the picture was probably one of the first prompts I wrote to an LLM:
posted an update about 1 month ago
view post
Post
317
How Do I Contribute (HDIC)

Exciting times to come? We are working on a layer self-esteem technique to score their contribution to the final prediction. For now, it unlocks a lot of knowledge already stored in weights we couldn't force the model to extract by further fine-tuning!
reacted to AdinaY's post with πŸ”₯ about 1 month ago
view post
Post
1342
HunyuanVideo πŸ“Ή The new open video generation model by Tencent!
πŸ‘‰ tencent/HunyuanVideo
zh-ai-community/video-models-666afd86cfa4e4dd1473b64c
✨ 13B parameters: Probably the largest open video model to date
✨ Unified architecture for image & video generation
✨ Powered by advanced features: MLLM Text Encoder, 3D VAE, and Prompt Rewrite
✨ Delivers stunning visuals, diverse motion, and unparalleled stability
πŸ”“ Fully open with code & weights
reacted to singhsidhukuldeep's post with πŸ€— about 1 month ago
view post
Post
1308
Exciting breakthrough in Document AI! Researchers from UNC Chapel Hill and Bloomberg have developed M3DocRAG, a revolutionary framework for multi-modal document understanding.

The innovation lies in its ability to handle complex document scenarios that traditional systems struggle with:
- Process 40,000+ pages across 3,000+ documents
- Answer questions requiring information from multiple pages
- Understand visual elements like charts, tables, and figures
- Support both closed-domain (single document) and open-domain (multiple documents) queries

Under the hood, M3DocRAG operates through three sophisticated stages:

>> Document Embedding:
- Converts PDF pages to RGB images
- Uses ColPali to project both text queries and page images into a shared embedding space
- Creates dense visual embeddings for each page while maintaining visual information integrity

>> Page Retrieval:
- Employs MaxSim scoring to compute relevance between queries and pages
- Implements inverted file indexing (IVFFlat) for efficient search
- Reduces retrieval latency from 20s to under 2s when searching 40K+ pages
- Supports approximate nearest neighbor search via Faiss

>> Question Answering:
- Leverages Qwen2-VL 7B as the multi-modal language model
- Processes retrieved pages through a visual encoder
- Generates answers considering both textual and visual context

The results are impressive:
- State-of-the-art performance on MP-DocVQA benchmark
- Superior handling of non-text evidence compared to text-only systems
- Significantly better performance on multi-hop reasoning tasks

This is a game-changer for industries dealing with large document volumesβ€”finance, healthcare, and legal sectors can now process documents more efficiently while preserving crucial visual context.
Β·
reacted to cfahlgren1's post with πŸ”₯ about 1 month ago
view post
Post
1930
You can just ask things πŸ—£οΈ

"show me messages in the coding category that are in the top 10% of reward model scores"

Download really high quality instructions from the Llama3.1 405B synthetic dataset πŸ”₯

argilla/magpie-ultra-v1.0

replied to their post about 1 month ago
view reply

That is an excellent question. I was just googling and searching in Arxiv. Now, I try Elicit, β€œtalk” with papers and listen to β€œpodcasts” on NotebookLM.

replied to their post about 1 month ago
reacted to AdinaY's post with ❀️ about 1 month ago
view post
Post
1481
2023 & 2024 Top Downloaded (all time) Open Models on the hub are both from the Chinese community πŸ‘€

2023 πŸ‘‰ Bge base by BAAI
BAAI/bge-base-en-v1.5
2024 πŸ‘‰ Qwen 2.5 by Alibaba Qwen
Qwen/Qwen2.5-1.5B-Instruct

Can’t wait to see what incredible models the Chinese community will bring in 2025πŸš€

✨ Follow https://huggingface.co/zh-ai-community to get the latest updates from the Chinese community
✨ Explore the 2024 Year in Review huggingface/open-source-ai-year-in-review-2024