📢We are #hiring! NingLab currently (as of May 1, 2024) has multiple openings for Ph.D. students, postdocs, and research staff. If interested, please contact Dr. Ning ([email protected]). More information is available here: https://t.co/MuhQLQloDV
#ArtificialIntelligence#AI#ML #MachineLearning #NLP #ecommerce #BigData #DeepLearning #LLMs #LLM #postdoc #phdrecruitment #AI4Science #AI4Health #GenerativeAI #GenAI #Bioinformatics
CSE Ph.D. students
NingLab is seeking 4 Ph.D. students for research on AI AI4Science and AI4health, starting as early as Summer 2024, with full Graduate Research Assistantship support available for 5 years. The students will help develop novel AI technologies for (1) omics analysis and drug repurposing for Alzheimer’s Disease (AD), (2) electronic health record analysis and mobile health for AD, (3) LLMs for Science, and (4) genAI for drug design.
Ideal candidates should be self-motivated and determined. They are expected to have a strong background in Computer Science and Engineering. Extensive programming experience and prior research experience are preferred. Knowledge and experience in Biology, Chemistry or Medicine are preferred but not required.
Postdocs
NingLab is seeking 2-3 postdocs, starting immediately until the positions are filled. The postdoc candidates are expected to have a Ph.D. degree in Computer Science or related disciplines (e.g., Electrical Engineering), are able to conduct research in AI/ML (e.g., doing research on deep learning or LLMs) and have strong communication skills and leadership. The postdoc candidates are also expected to be highly self-motivated and have a clear career goal set in mind. The postdocs will assist PI Ning on the methodology development in the current projects (e.g., drug repurposing for AD, predictive analysis for AD, genAI for drug design, LLMs for science). Compensation and benefits will be very competitive.
Research Staff
NingLab provides full-time research staff positions. Candidates should have at least an MS degree in Computer Science or related disciplines (e.g., Electrical Engineering) and research experience in AI/ML.
Ohio State's Research & Innovation Showcase is next Wednesday! Engineering Profs Emre Koksal, Shang-Tian Yang & Eduardo Reátegui are award finalists, as are PhD candidates Shashwat Agarwal & Tzu-Li Liu 👏 https://t.co/Drqk1FVrjm
A good story from my student @peng1230248 -- got two offers from @googlesearchc and @metaai due to a paper https://t.co/l0R53Sjfyw that was rejected recently by a conference.
To mark the International Day of Women and Girls in Science, this Collection from @CommsChem celebrates women in chemistry, including articles focused on promoting gender equality in STEM. #February11 https://t.co/M47Q47EtYL
Introducing e-Commerce Large Language Model eCeLLM (pronounce e-sellˈem, /ˌɪ- ˈseləm/))!
Website: https://t.co/rHvdy38aG7
Joint work of @peng1230248@xinyiling_ @RonZiruChen @ningx005 and @hhsun1 at OSU!
Large Language Models for Chemistry: Chemistry plays a crucial role in many domains like drug discovery and material science. While LLMs exhibit remarkable capabilities on various NLP tasks, existing work shows their performance on chemistry tasks is discouragingly low.
Introducing a series of strong LLMs for chemistry, LlaSMol (large language models on small molecules), which beats GPT-4 and other existing LLMs by a large margin (e.g., 94.5% EM for converting SMILES to Formula vs. GPT-4's 16.4%; 32.9% EM for Retrosynthesis vs. GPT-4's ~0%), and approaches SoTA task-specific models.
Thanks to the amazing team at OSU: @BotaoYu24@FrazierBaker@ziqiChen123@Ningx005@TheNingLab@osunlp
📌Project page: https://t.co/vdSOwPg9xW
📌Paper: https://t.co/TmUNYXQ8WK
📌Dataset:
https://t.co/t3icM3BFHA
📌Model: https://t.co/zFBqULUI7Y
A key factor that contributes to the great performance is our constructed SMolInstruct, a high-quality dataset curated for chemistry instruction tuning. It contains 14 meticulously selected tasks and over 3M carefully curated samples. Among various base models (Galactica, Llama 2, Code Llama, and Mistral) , we find that Mistral serves as the best, showing its great potential for chemistry. Results on four additional representative tasks are shown below. See paper for more detailed results!
Stay tuned for more analysis!
Start something new for 2022--enroll to become a data storytelling whiz! Priority registration deadline is 2/1 for the @OhioState Masters in Translational Data Analytics, a program with @OSUengineering and @ASCatOSU designed for mid-career professionals. https://t.co/sOO0DddVnc
Drug Repurposing #KnowledgeGraph (DRKG) includes, curates, normalizes #data#research related to #Covid-19. DGL-KE is a package for learning large-scale KG embeddings. DRKG #github repository provides examples on using DGL-KE & DRKG for drug repurposing https://t.co/IT7KKbqpvK
We published our work "A deep generative model for molecule optimization via one fragment modification" in Nature Machine Intelligence (https://t.co/SXf2eFpwDM). Preprint with supp materials is at https://t.co/5eoV7j1VDw. #DeepLearning#drugdiscovery#ArtificialIntelligence