#Lvlm
Showing 8 of 8 repositories tagged #lvlm, ranked by stars
Eagle: Frontier Vision-Language Models with Data-Centric Strategies
🔥🔥🔥 A curated list of papers on LLMs-based multimodal generation (image, video, 3D and audio).
[Fully open] [Encoder-free MLLM] Vision as LoRA
Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal LLMs
[ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"
📜 Paper list on decoding methods for LLMs and LVLMs
The official repository of "SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber World".
LEMMA: An effective and explainable way to detect multimodal misinformation with LVLM and external knowledge augmentation, incorporating the intuition and reasoning capbility inside LVLM.