Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D Gaussianby Amirhosein Chahe, Lifeng ZhouFirst submitted…
Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injectionby Subaru Kimura,…
Is Child-Directed Speech Effective Training Data for Language Models?by Steven Y. Feng, Noah D. Goodman,…
Recording First-person Experiences to Build a New Type of Foundation Modelby Dionis Barcari, David Gamez,…
MedSyn: LLM-based Synthetic Medical Text Generation Frameworkby Gleb Kumichev, Pavel Blinov, Yulia Kuzkina, Vasily Goncharov,…
Evaluating the Performance of Large Language Models for SDG Mapping (Technical Report)by Hui Yin, Amir…
Efficient Solutions For An Intriguing Failure of LLMs: Long Context Window Does Not Mean LLMs…
MALADE: Orchestration of LLM-powered Agents with Retrieval Augmented Generation for Pharmacovigilanceby Jihye Choi, Nils Palumbo,…