Valley2: Exploring Multimodal Models with Scalable Vision-Language Design
This work addresses the need for more effective multimodal models in practical applications like e-commerce and short videos, representing an incremental advancement.
The authors tackled the problem of improving vision-language model performance across domains, particularly in e-commerce and short video scenarios, achieving state-of-the-art results with Valley2, which scored 79.66 on e-commerce benchmarks and 67.4 on the OpenCompass leaderboard.
Recently, vision-language models have made remarkable progress, demonstrating outstanding capabilities in various tasks such as image captioning and video understanding. We introduce Valley2, a novel multimodal large language model designed to enhance performance across all domains and extend the boundaries of practical applications in e-commerce and short video scenarios. Notably, Valley2 achieves state-of-the-art (SOTA) performance on e-commerce benchmarks, surpassing open-source models of similar size by a large margin (79.66 vs. 72.76). Additionally, Valley2 ranks second on the OpenCompass leaderboard among models with fewer than 10B parameters, with an impressive average score of 67.4. The code and model weights are open-sourced at https://github.com/bytedance/Valley.