Sort by
Refine Your Search
-
structured problem-solving Investigating advanced strategies for model adaptation, including in-domain pre-training, domain adapters, task-specific instruction tuning, and retrieval-augmented generation (RAG
-
reality can be restored and sustained in the face of increasingly polarized information environments and the widespread dissemination of misinformation. The project addresses two main research questions
-
genomics, virtual cell models Graph-based neural networks, optimal transport Biomedical imaging, deep learning, virtual reality, AI-driven image analysis Agentic systems, large language models Generative AI
-
objects (e.g., fabrics) Bimanual coordination and manipulation planning Vision- and tactile-based perception and state estimation of deformable objects Simulation and reality gap bridging for deformable
-
adaptation, including in-domain pre-training, domain adapters, task-specific instruction tuning, and retrieval-augmented generation (RAG) Collaboration with interdisciplinary teams to enhance model performance