Mentors: Armaan Alam <armanalam032001@gmail.com>, JB Poline <jean-baptiste.poline@mcgill.ca>, Suresh Krishna <suresh.krishna@mcgill.ca>
Skill level: Intermediate - Advanced
Required Skills: If working on the front-end, familiarity with front-end development with NextJs, efficient Server Side Rendering, Tanstack Query, using Radix UI/ShadCn UI, modular design patterns are preferred. If working with NLP tools, familiarity with LLMs, NLP, using open sourced models, etc; familiarity with Slurm and working with clusters preferred.
Time commitment: Full time (350 hours)
About: Over the past two GSoC cycles (GSoC 2024 Project Idea 11.1 A social-web tool to facilitate rating and commenting on research reports (350 h) - GSoC - Neurostars), we have built SciCommons (http://www.scicommons.org), a portal to facilitate peer-review, article-rating, public and private discussion, as well as filtering for the scientific literature. This portal is nearing a public release.
Aims: This year, we invite GSoC contributors with experience in front-end development and design (Django/NextJS) as well as those with experience with NLPs and fine-tuning LLMs (for filtering the scientific literature). The goal is to substantially improve as well as democratize scientific discourse, and bring scholarly review and access back into the hands of scholars.
Website: http://www.scicommons.org
Tech keywords: Science publishing, social web, science portals, Natural language processing, large language models, AI.
