RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
Paper
•
2312.00849
•
Published
•
11
Kaiyuan Chen
Lucky2022
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 18 hours ago
RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from
Fine-grained Correctional Human Feedback
upvoted
a
paper
about 18 hours ago
MiniCPM-V: A GPT-4V Level MLLM on Your Phone
upvoted
a
paper
about 22 hours ago
Unveiling Downstream Performance Scaling of LLMs: A Clustering-Based
Perspective
Organizations
