AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User MemoryMar 2024·Jitesh Jain,Shubham Maheshwari,Ning Yu,Wen-Mei Hwu,Humphrey Shi· 0 min readGo to Project Site Preprint PDF CiteAbstractTBDTypeWorkshop PaperPublicationLAW 2025 WorkshopLast updated on Mar 2024LAW Workshop @NeurIPS 2025 AuthorsJitesh JainPh.D. Student ← Elevating Perception in Multimodal LLMs with Visual Embedding Distillation Dec 2024VCoder: Versatile Vision Encoders for Multimodal Large Language Models Dec 2023 →