Trustworthy Generation
Data is key to technological innovations. We develop theoretical and algorithmic frameworks for generative AI to synthesize realistic, diverse, and targeted data. Our methods facilitate data augmentation for trustworthy machine learning and accelerate novel designs for drug and material discovery, and beyond.
Our work
Teaching AI models to improve themselves
ResearchPeter HessWhat is retrieval-augmented generation?
ExplainerKim MartineauAccelerating molecular optimization with AI
Deep DivePayel Das, Samuel Hoffman, Vijil Chenthamarakshan, Kahini Wadhawan, and Pin-Yu Chen11 minute readAI boosts the discovery of metamaterials vital for next-gen gadgets
ResearchYoussef Mroueh, Karthikeyan Shanmugam, and Payel Das10 minute readIBM AI finds new peptides – paving the way to better drug design
ResearchAleksandra Mojsilovic and Payel Das4 minute readDualTKB: A Dual Learning Bridge between Text and Knowledge Base
ResearchPierre Dognin6 minute readImage captioning as an assistive technology
NewsYoussef Mroueh5 minute read
Publications
Interpolating Item and User Fairness in Multi-Sided Recommendations
- Qinyi Chen
- Jason Cheuk Nam Liang
- et al.
- 2024
- NeurIPS 2024
Enhancing Reasoning to Adapt Large Language Models for Domain-Specific Applications
- Bo Wen
- Xin Zhang
- 2024
- NeurIPS 2024
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
- Megh Thakkar
- Yash More
- et al.
- 2024
- NeurIPS 2024
Value Alignment from Unstructured Text
- 2024
- NeurIPS 2024
Distributional Preference Alignment of LLMs via Optimal Transport
- Igor Melnyk
- Youssef Mroueh
- et al.
- 2024
- NeurIPS 2024
Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
- Gabriel Rioux
- Apoorva Nitsure
- et al.
- 2024
- NeurIPS 2024