4 papers
Negative Entity Suppression for Zero-Shot Captioning with Synthetic Images
Zimao Lu, Hui Xu, Bing Liu +1
Text-only training provides an attractive approach to address data scarcity challenges in zero-shot image captioning (ZIC), avoiding the expense of collecting paired image-text ann…
Fine-Tuning Large Multimodal Models for Automatic Pronunciation Assessment
Ke Wang, Wenning Wei, Yan Deng +2
Automatic Pronunciation Assessment (APA) is critical for Computer-Assisted Language Learning (CALL), requiring evaluation across multiple granularities and aspects. Large Multimoda…
Exploring the Potential of Large Multimodal Models as Effective Alternatives for Pronunciation Assessment
Ke Wang, Lei He, Kun Liu +3
Large Multimodal Models (LMMs) have demonstrated exceptional performance across a wide range of domains. This paper explores their potential in pronunciation assessment tasks, with…
LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Information
Ke Wang, Hong Xuan
Multi-modal large language models (MLLMs) utilizing instruction-following data, such as LLaVA, have achieved great progress in the industry. A major limitation in these models is t…