Aaditya Ura (@aadityaura) 's Twitter Profile
Aaditya Ura

@aadityaura

ML Researcher | Focus on Representation Learning on Graphs and Manifolds | NLP | Generative Modeling | Healthcare

ID: 1466097836433592328

linkhttp://aadityaura.github.io calendar_today01-12-2021 17:32:36

452 Tweet

1,1K Followers

947 Following

Chaojun Xiao (@xcjthu1) 's Twitter Profile Photo

1/5 πŸš€ Excited to share our latest paper on Configurable Foundation Models! 🧠 Inspired by the human brain's functional specialization, we propose a concept: Configurable Foundation Model, a modular approach to LLMs.

1/5 πŸš€ Excited to share our latest paper on Configurable Foundation Models! 🧠

Inspired by the human brain's functional specialization, we propose a concept: Configurable Foundation Model, a modular approach to LLMs.
Open Life Science AI (@openlifesciai) 's Twitter Profile Photo

Last Week in Medical AI: Top Research Papers/Models πŸ…(September 7 - September 14, 2024) πŸ… Medical AI Paper of the week Chai-1 Foundation model molecular structure prediction from Chai Discovery , Joshua Meier, @_JackDent Medical LLMs & Benchmarks - BrainWave: A Brain Signal

Last Week in Medical AI: Top Research Papers/Models
πŸ…(September 7  - September 14, 2024)

πŸ… Medical AI Paper of the week
Chai-1 Foundation model molecular structure prediction from <a href="/chaidiscovery/">Chai Discovery</a> , <a href="/joshim5/">Joshua Meier</a>, @_JackDent

Medical LLMs &amp; Benchmarks

- BrainWave: A Brain Signal
Aaditya Ura (@aadityaura) 's Twitter Profile Photo

Inspired by Andrej Karpathy 's NotebookLM project, I gave the codebase of Llama-3 Architecture to NLM and used Rag to find the perfect images to sync with the generated audio. The result exceeded my expectations. Google's NotebookLM is truly amazing :) Here is a youtube link as

Aaditya Ura (@aadityaura) 's Twitter Profile Photo

Old vs. New Claude 3.5: A Quick Review of Speed and Output Quality Was using the older Claude 3.5 model for data generation but recently switched to the newer version of Claude 3.5. TL;DR: - Old 3.5 = slower but more detailed. - New 3.5 = faster but more like summaries.