Selective Publications

(* equal contribution)

AMR-Evol: Adaptive Modular Response Evolution Elicits Better Knowledge Distillation for Large Language Models in Code Generation
EMNLP 2024: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.
Ziyang Luo, Xin Li, Hongzhan Lin, Jing Ma, and Lidong Bing.

Towards Low-Resource Harmful Meme Detection with LMM Agents
EMNLP 2024: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.
Jianzhao Huang, Hongzhan Lin, Ziyan Liu, Ziyang Luo, Guang Chen, and Jing Ma.

MMCode: Evaluating Multi-Modal Code Large Language Models with Visually Rich Programming Problems
EMNLP 2024: Findings of the 2024 Conference on Empirical Methods in Natural Language Processing, (Data).
Kaixin Li, Yuchen Tian, Qisheng Hu, Ziyang Luo, and Jing Ma.

CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models
ACL 2024: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, (Code).
Zixin Chen, Hongzhan Lin, Ziyang Luo, Mingfei Cheng, Jing Ma, and Guang Chen.

Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models
WWW 2024: The ACM Web Conference 2024, (Codes).
Hongzhan Lin, Ziyang Luo, Wei Gao, Jing Ma, Bo Wang, and Ruichao Yang.

WizardCoder: Empowering Code Large Language Models with Evol-Instruct
ICLR 2024: Proceedings of the Twelfth International Conference on Learning Representations.
Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma, Qingwei Lin, and Daxin Jiang.
[2024/01/04] We released WizardCoder-33B-V1.1, the SOTA OSS Code LLM on EvalPlus Leaderboard.
[2023/08/26] We released WizardCoder-Python-34B-V1.0, which achieves the 73.2 pass@1 and surpasses GPT4 (2023/03/15), ChatGPT-3.5, and Claude2 on the HumanEval.
[2023/06/16] Our WizardCoder-15B-V1.0 achieves 57.3 pass@1 score on HumanEval, more than 20 points higher than the SOTA open-source LLMs.

LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval.
ICCV 2023: Proceedings of the IEEE/CVF International Conference on Computer Vision. (Codes).
Ziyang Luo, Pu Zhao, Can Xu, Xiubo Geng, Tao Shen, Chongyang Tao, Jing Ma, Qingwei Lin, and Daxin Jiang.

Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models
EMNLP 2023: Findings of the 2023 Conference on Empirical Methods in Natural Language Processing. (Codes).
Hongzhan Lin*, Ziyang Luo*, Jing Ma, and Long Chen.

Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning
AAAI 2023: Proceedings of the 2023 AAAI Conference on Artificial Intelligence.
Hongzhan Lin, Pengyao Yi, Jing Ma, Haiyun Jiang, Ziyang Luo, Shuming Shi, Ruifang Liu.

A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection
COLING 2022: Proceedings of the 29th International Conference on Computational Linguistics.
Zhiwei Yang, Jing Ma, Hechang Chen, Hongzhan Lin, Ziyang Luo, Yi Chang.

Conditioned Masked Language and Image Modeling for Image-Text Dense Retrieval
EMNLP 2022: Findings of the 2022 Conference on Empirical Methods in Natural Language Processing.
Ziyang Luo, Yadong Xi, Rongsheng Zhang, Gongzheng Li, Zeng Zhao, and Jing Ma.

DecBERT: Enhancing the Language Understanding of BERT with Causal Attention Masks
NAACL 2022: Findings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
Ziyang Luo, Yadong Xi, Jing Ma, Zhiwei Yang, Xiaoxi Mao, Changjie Fan, Rongsheng Zhang.

Easy and Efficient Transformer: Scalable Inference Solution for Large NLP Model
NAACL 2022: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers.
Yadong Xi, Gongzheng Li, Jingzhen Ding, Duan Wang, Ziyang Luo, Rongsheng Zhang, Bai Liu, Changjie Fan, Xiaoxi Mao, Zeng Zhao.

Positional Artefacts Propagate Through Masked Language Model Embeddings
ACL 2021: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics.
Ziyang Luo, Artur Kulmizev, and Xiaoxi Mao.

Smoothing with Fake Label
CIKM 2021: Proceedings of the 30th ACM International Conference on Information and Knowledge Management.
Ziyang Luo, Yadong Xi, and Xiaoxi Mao.

Gender Bias Hidden Behind Chinese Word Embeddings: The Case of Chinese Adjectives
GeBNLP 2021: Proceedings of the 3rd Workshop on Gender Bias in Natural Language Processing.
Meichun Jiao, Ziyang Luo.

Have Attention Heads in BERT Learned Constituency Grammar?
EACL 2021 SRW: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop.
Ziyang Luo.

Selective Open-Source Projects

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs. (Code, 2024). VideoLLaMA Team@Alibaba.

AURORA-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order. (Models, 2024). Aurora-M Open-Source Community.

WizardCoder: Empowering Code Large Language Models with Evol-Instruct (Code, 2023). WizardLM Team@Microsoft.

Master Thesis

Ziyang Luo. Analyzing the Anisotropy Phenomenon in Transformer-based Masked Language Models. (Supervised by Artur Kulmizev, Uppsala University, 2021)