Search Results for author: Hanxu Hu

Found 6 papers, 3 papers with code

Fine-tuning Large Language Models with Sequential Instructions

no code implementations12 Mar 2024 Hanxu Hu, Simon Yu, Pinzhen Chen, Edoardo M. Ponti

Despite the success of existing instruction-tuned models, we find that they usually struggle to respond to queries with multiple instructions.

Question Answering Visual Question Answering

Meta-learning For Vision-and-language Cross-lingual Transfer

no code implementations24 May 2023 Hanxu Hu, Frank Keller

Current pre-trained vison-language models (PVLMs) achieve excellent performance on a range of multi-modal datasets.

Cross-Lingual Transfer Meta-Learning

Chain-of-Symbol Prompting Elicits Planning in Large Langauge Models

1 code implementation17 May 2023 Hanxu Hu, Hongyuan Lu, Huajian Zhang, Yun-Ze Song, Wai Lam, Yue Zhang

To this end, we propose a novel method called CoS (Chain-of-Symbol Prompting) that represents the complex environments with condensed symbolic spatial representations during the chained intermediate thinking steps.

Improving User Controlled Table-To-Text Generation Robustness

1 code implementation20 Feb 2023 Hanxu Hu, Yunqing Liu, Zhongyi Yu, Laura Perez-Beltrachini

In this work we study user controlled table-to-text generation where users explore the content in a table by selecting cells and reading a natural language description thereof automatically produce by a natural language generator.

Table-to-Text Generation

A Channel Mix Method for Fine-Grained Cross-Modal Retrieval

3 code implementations IEEE International Conference on Multimedia and Expo (ICME) 2022 Yang shen, Xuhao Sun, Xiu-Shen Wei, Hanxu Hu, Zhipeng Chen

In this paper, we propose a simple but effective method for dealing with the challenging fine-grained cross-modal retrieval task where it aims to enable flexible retrieval among subor-dinate categories across different modalities.

Cross-Modal Retrieval Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.