Shiv

shiv2050

AI & ML interests

ARTIFICIAL INTELLIGENCE,MACHINE LEARNING ,DEEP LEARNING,NATURAL LANGUAGE PROCESSING,,GENAI,LLM,MLOPS,MULTIAGENT

Recent Activity

upvoted an article 16 days ago

Open-R1: a fully open reproduction of DeepSeek-R1

upvoted a paper about 1 month ago

Search-o1: Agentic Search-Enhanced Large Reasoning Models

reacted to aaditya's post with 👍 2 months ago

Last Week in Medical AI: Top Research Papers/Models 🔥 🏅 (December 2 – December 7, 2024) Medical LLM & Models - Block MedCare: Blockchain AI & IoT - LLMs4Life: Biomedical Ontology Learning - LLaMA II for Multimodal Diagnosis - Compact LLM for EHR Privacy Frameworks & Methods - RARE: Retrieval-Augmented Reasoning - STORM: Strategies for Rare Events - TransFair: Fair Disease Classification - PePR: Performance Per Resource - Medical LLM Best Practices LLM Applications - Medchain: LLMs in Clinical Practice - Query Nursing Note Summarization - CLINICSUM: Patient Conversation Summaries - Text Embeddings for Classifiers LLM Benchmarks - Polish Medical Exams Transfer - Single-Cell Omics Annotation - LLMs in Precision Medicine - Low-Resource Healthcare Challenges Other Models - LLM Chatbot Hallucinations - Multi-stage Chest X-ray Diagnosis - EchoONE: Echocardiography AI - Radiology Report Grounding Ethics & Fairness - Privacy in Medical Imaging - Demographic Fairness in AI Datasets - LLM Scientific Knowledge Extraction - Biomedical Knowledge Review Now you can watch and listen to the latest Medical AI papers daily on our YouTube and Spotify channels as well! - Full thread in detail: https://x.com/OpenlifesciAI/status/1865584829057929303 - Youtube Link: https://youtu.be/SwawtIFy-BI - Spotify: https://open.spotify.com/episode/17Cxk0NLfKhiRWPoykzjem

View all activity

Organizations

shiv2050's activity

upvoted an article 16 days ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

17 days ago

• 734

upvoted a paper about 1 month ago

Search-o1: Agentic Search-Enhanced Large Reasoning Models

Paper • 2501.05366 • Published Jan 9 • 93

reacted to aaditya's post with 👍 2 months ago

Post

2056

Last Week in Medical AI: Top Research Papers/Models 🔥
🏅 (December 2 – December 7, 2024)

Medical LLM & Models
- Block MedCare: Blockchain AI & IoT
- LLMs4Life: Biomedical Ontology Learning
- LLaMA II for Multimodal Diagnosis
- Compact LLM for EHR Privacy

Frameworks & Methods
- RARE: Retrieval-Augmented Reasoning
- STORM: Strategies for Rare Events
- TransFair: Fair Disease Classification
- PePR: Performance Per Resource
- Medical LLM Best Practices

LLM Applications
- Medchain: LLMs in Clinical Practice
- Query Nursing Note Summarization
- CLINICSUM: Patient Conversation Summaries
- Text Embeddings for Classifiers

LLM Benchmarks
- Polish Medical Exams Transfer
- Single-Cell Omics Annotation
- LLMs in Precision Medicine
- Low-Resource Healthcare Challenges

Other Models
- LLM Chatbot Hallucinations
- Multi-stage Chest X-ray Diagnosis
- EchoONE: Echocardiography AI
- Radiology Report Grounding

Ethics & Fairness
- Privacy in Medical Imaging
- Demographic Fairness in AI

Datasets
- LLM Scientific Knowledge Extraction
- Biomedical Knowledge Review

Now you can watch and listen to the latest Medical AI papers daily on our YouTube and Spotify channels as well!

- Full thread in detail: https://x.com/OpenlifesciAI/status/1865584829057929303
- Youtube Link: https://youtu.be/SwawtIFy-BI
- Spotify: https://open.spotify.com/episode/17Cxk0NLfKhiRWPoykzjem

upvoted a paper 10 months ago

FlowMind: Automatic Workflow Generation with LLMs

Paper • 2404.13050 • Published Mar 17, 2024 • 34

liked a model 10 months ago

microsoft/Phi-3-mini-128k-instruct

Text Generation • Updated Aug 20, 2024 • 211k • • 1.63k

upvoted an article 10 months ago

Article

Fine-tune Llama 3 with ORPO

•

Apr 22, 2024

• 233

upvoted a collection 10 months ago

Papers to read

Collection

106 items • Updated 3 days ago • 7

liked a Space 10 months ago

12.5k

Open LLM Leaderboard

🏆

Track, rank and evaluate open LLMs and chatbots

reacted to clem's post with 👍 10 months ago

Post

2914

Already almost 1,000 llama3 model variations have been shared publicly on HF (many more in private use at companies): https://huggingface.co/models?p=5&sort=trending&search=llama3.

Everyone should fine-tune their own models for their use-cases, languages, industry, infra constraints,...

10,000 llama3 variants by the end of next week?