Respository for ACL 2024 paper "Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI feedback"
SNUMPR
SNUMPR
AI & ML interests
CV, Multimodal
Organizations
None yet
spaces
1
models
11
SNUMPR/vlm_policy_init_7b_lora
Updated
SNUMPR/vlm_rm_13b_lora
Updated
SNUMPR/hlsm_alfred
Updated
SNUMPR/vlm_sft_video_llava_13b
Updated
•
644
SNUMPR/vlm_sft_video_llava_7b
Updated
•
8
SNUMPR/realfred_film_BERT_pretrained
Updated
SNUMPR/realfred_film_bert
Updated
SNUMPR/realfred_film_BERT_data
Updated
SNUMPR/hlsm_realfred_models
Updated
SNUMPR/isrt_video_llava_7b_9th
Text Generation
•
Updated
•
5