揭秘千卡 GPU 集群如何高效训练多模态大模型：vivo AI 团队实战经验分享｜AICon
"LLaVA" 相关文章
统一SAM2和LLaVA！字节豆包提出Dense Video多模态大模型Sa2VA
Sa2VA: A Unified AI Framework for Dense Grounded Video and Image Understanding through SAM-2 and LLaVA Integration
Are SAE features from the Base Model still meaningful to LLaVA?
Are SAE features from the Base Model still meaningful to LLaVA?
12%计算量就能媲美原模型，Adobe、罗切斯特大学等提出YOPO剪枝技术
UGround: A Universal GUI Visual Grounding Model Developed with Large-Scale Web-based Synthetic Data
LLaVaOLMoBitnet1B: The First Ternary Multimodal LLM Capable of Accepting Image(s) and Text Inputs to Produce Coherent Textual Response
SF-LLaVA: A Training-Free Video LLM that is Built Upon LLaVA-NeXT and Requires No Additional Fine-Tuning to Work Effectively for Various Video Tasks
Math-LLaVA: A LLaVA-1.5-based AI Model Fine-Tuned with MathV360K Dataset
LLaVA-NeXT: Advancements in Multimodal Understanding and Video Comprehension
