psp_dada

Hello, that's a great work! May I ask if you can open-source the HACL trained LLaVA 1.5 model mentioned in your paper? It would be very helpful for my research.

Online Evaluator is Significantly Slower Than Before

1

Currently, during regular times when there are only a few people in the queue, the online evaluator (https://huggingface.co/spaces/whyu/MM-Vet_Evaluator) may take several hours to start processing an evaluation. This is excessively...

Hello! I have some questions about the optimizer used in your training. The paper mentions, "We use an Adam optimizer [47] for all the experiments." However, I noticed that the...

Thank you for such excellent work — it greatly contributes to the advancement of multimodal hallucination research! Our work, Mitigating Object Hallucinations via Sentence-Level Early Intervention, has been accepted to...

**Describe the bug** A clear and concise description of what the bug is. I'm in Windows and use Clash to proxy my connection to a server using SSH, When I...