In this work, we present InfiMM, an advanced Multimodal Large Language Model that adapts to intricate vision-language tasks. InfiMM, inspired by the Flamingo architecture, distinguishes itself through the utilization of large-scale training data, comprehensive training strategies, and diverse large language models. This approach ensures the preservation of Flamingo’s foundational strengths while simultaneously introducing augmented capabilities. Empirical evaluations across a variety of benchmarks underscore InfiMM’s remarkable capability in multimodal understanding. The code can be found at: https://anonymous.4open.science/r/infimm-zephyr-F60C/.

This paper presents the submission from Global Tone Communication Co., Ltd. and Dalian University of Technology for the WMT24 shared general Machine Translation (MT) task at the Conference on Empirical Methods in Natural Language Processing (EMNLP). Our participation encompasses two language pairs: English to Japanese and Japanese to Chinese. The systems are developed without particular constraints or requirements, facilitating extensive research in machine translation. We emphasize back-translation, utilize multilingual translation models, and apply fine-tuning strategies to improve performance. Additionally, we integrate both human-generated and machine-generated data to fine-tune our models, leading to enhanced translation accuracy. The automatic evaluation results indicate that our system ranks first in terms of BLEU score for the Japanese to Chinese translation.