Papers by Kaizhi Zheng

1 papers
R2H: Building Multimodal Navigation Helpers that Respond to Help Requests (2023.emnlp-main)

Copied to clipboard

Challenge: Existing dialog-based embodied datasets are not sufficient to develop intelligent navigation-helper agents capable of navigating users in unfamiliar areas.
Approach: They introduce a novel benchmark, Respond to Help Requests, to promote the development of multi-modal navigation helpers capable of responding to requests for help . they also propose two approaches to construct the navigation-helper agent, including fine-tuning a task-oriented multi-mod response generation model that can see and respond, named SeeRee, and employing . a multi-module large language model in a zero-shot manner.
Outcome: The proposed model outperforms the baseline model and the proposed model on two tasks based on human evaluations and automatic benchmarking.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations