2 papers
cs.LG2026
FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning
Xing Han, Shravan Chaudhari, Tanvi Ranade +2
Real-world model deployment across multiple domains requires multimodal models to operate under two complementary regimes: (1) multi-task pretraining, tasks are co-available at des…
cs.DB2024
The Design of an LLM-powered Unstructured Analytics System
Eric Anderson, Jonathan Fritz, Austin Lee +11
LLMs demonstrate an uncanny ability to process unstructured data, and as such, have the potential to go beyond search and run complex, semantic analyses at scale. We describe the d…