5 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…
Deep Contrastive Unlearning for Language Models
Estrid He, Tabinda Sarwar, Ibrahim Khalil +2
The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like language…
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…