Yanzhe Zhang

张彦哲 (Yanzhe Zhang)

I am a second-year computer science Ph.D. student at Georgia Tech, working with Diyi Yang. Before coming to Georgia Tech, I received my bachelor's degree from Zhejiang University in 2021.

I work as a research intern at Adobe Research (Summer 2022, Summer 2023) with Ruiyi Zhang.

I am visiting Stanford NLP now.

Email / Google Scholar / Github

Research

I am interested in natural language processing and artificial intelligence, especially in the following directions:

(1) To make NLP models capable of continually learning multiple tasks and transferring knowledge.

(2) To make NLP models more robust, interpretable and efficient.

(3) To enable NLP models to benefit from and for other modalities and humans.

Publications

(* refers to equal contribution)

	Design2Code: How Far Are We From Automating Front-End Engineering? Chenglei Si, Yanzhe Zhang , Zhengyuan Yang, Ruibo Liu, Diyi Yang Preprint, 2024 website / code / data / bibtex A benchmark for screenshot-to-html/css transformation.
	TRINS: Towards Multimodal Language Models That Can Read Ruiyi Zhang, Yanzhe Zhang , Jian Chen, Yufan Zhou, Jiuxiang Gu, Changyou Chen, Tong Sun CVPR, 2024 Coming Soon! A Text-Rich image INStruction dataset.
	Dynamic LLM-Agent Network: An LLM-agent Collaboration Framework with Agent Evaluation Zijun Liu, Yanzhe Zhang , Peng Li, Yang Liu, Diyi Yang Preprint, 2023 code / bibtex A dynamic framework for multi-LLM-agent collaboration with auto agent evaluation.
	Enhanced Visual Instruction Tuning for Text-rich Image Understanding Yanzhe Zhang , Ruiyi Zhang, Jiuxiang Gu, Yufan Zhou, Nedim Lipka, Diyi Yang, Tong Sun NeurIPS Workshop on Instruction Tuning and Instruction Following, 2023 website / code / data / bibtex A multimodal (vision-language, to be honest) large language model that can read text.
	Auditing Gender Presentation Differences in Text-to-Image Models Yanzhe Zhang , Lu Jiang, Greg Turk, Diyi Yang Preprint, 2023 website / code / data / bibtex A metric to evaluate attribute-wise differences between genders in text-to-image models.
	Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints Albert Lu* Hongxin Zhang, Yanzhe Zhang, Xuezhi Wang, Diyi Yang EACL (Findings)*, 2023 code / bibtex A study on the limitation of LLM on structural and stylistic constraints.
	Robustness of Demonstration-based Learning Under Limited Data Scenario Hongxin Zhang, Yanzhe Zhang , Ruiyi Zhang, Diyi Yang EMNLP, 2022 (Oral Presentation) code / bibtex Astonishingly find that random tokens strings work well as demonstrations.
	Continual Sequence Generation with Adaptive Compositional Modules Yanzhe Zhang , Xuezhi Wang, Diyi Yang ACL, 2022 (Oral Presentation) code / bibtex Add and reuse adapters strategically in continual sequence generation.
	Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition Aaron Reich, Jiaao Chen, Aastha Agrawal, Yanzhe Zhang , Diyi Yang ACL (Findings), 2022 code / data / bibtex Alter entity type by predefined change on tokens and contexts to attack NER models.
	Continual Learning for Text Classification with Information Disentanglement Based Regularization Yufan Huang, Yanzhe Zhang , Jiaao Chen, Xuezhi Wang, Diyi Yang NAACL, 2021 code / bibtex Augment regularization in continual text classification with two simple auxiliary tasks.

Service

Volunteer: NAACL 2021.

Reviewer: EMNLP 2022, ICLR 2023, EACL 2023, ACL 2023, EMNLP 2023. ARR (Oct 2023, Dec 2023).

Website's code is from Jon Barron.