Merlin

Reported on 3 benchmarks across 3 tasks · 2 papers

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Visual Question Answering (VQA)onMM-Vet
GPT-4 score· 2023-11-30
34.9
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
Merlin:Empowering Multimodal LLMs with Foresight Minds arXiv:2312.00589
Visual Question AnsweringonMM-Vet
GPT-4 score· 2023-11-30
34.9
best: 74.24 (MMCTAgent (GPT-4 + GPT-4V))
Merlin:Empowering Multimodal LLMs with Foresight Minds arXiv:2312.00589

Audio1 result

Text-To-Speech SynthesisonLJSpeech
Audio Quality MOS· uses extra data· 2019-05-22
2.4
best: 4.56 (NaturalSpeech)
FastSpeech: Fast, Robust and Controllable Text to Speech arXiv:1905.09263