Inference Throughput Comparison of LLaVA and Multimodal Models in Zero-Shot Cross-Lingual Evaluation

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuning again on the target task---often improves model performance substantially on language understanding tasks in monolingual English settings. We investigate whether English intermediate-task training is still helpful on non-English target tasks. Using nine intermediate language-understanding tasks, we evaluate intermediate-task transfer in a zero-shot cross-lingual setting on the XTREME benchmark. We see large improvements from intermediate training on the BUCC and Tatoeba sentence retrieval tas

Research goal: How does the inference throughput of LLaVA compare to other multimodal models (e.g., BLIP-2, MiniGPT-4) when applying English intermediate-task training for zero-shot cross-lingual evaluation on XTREME-R benchmarks, measured in tokens/second?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.