FuxiaoLiu / LRV-Instruction

[ICLR'24] Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

https://fuxiaoliu.github.io/LRV/

FuxiaoLiu/LRV-Instruction Issues

Failed Loading for mPLUG-Owl finetuned model
Closed 5 months ago1
About results of POPE of MiniGPT-4 after LRV Instruction
Closed 5 months ago
How many GPUs were used during fine-tuning?
Closed 5 months ago1
About instruction data
Closed 7 months ago2
Cannot reproduce MME results on mPLUG-OWL version
Closed 7 months ago
Cannot reproduce the result on MME leaderboard
Closed 9 months ago2
Chart images
Closed 9 months ago5
Question about the coordinate in the instruction
Closed 9 months ago2
Quality control
Closed 10 months ago1
bounding box
Closed 10 months ago
why code not corresponds to paper
Closed 10 months ago1
How to run validation during training?
Closed 10 months ago1
About filter_cap.json file
Closed 10 months ago1
how to inference model parallelly?
Closed 10 months ago2
Evaluation set
Closed a year ago2
Could you please share the code using GPT4 and prompt to generate visual instructions ?
Closed a year ago1
Good checkpoint.pth ?
Closed a year ago1
Environment Set up Issue
Closed a year ago