Qifan Wang

RESEARCH SCIENTIST | MENLO PARK, UNITED STATES

Qifan Wang is a Research Scientist at Facebook AI, working on innovative Deep Learning and Natural Language Processing models for AI Integrity. Before joining Facebook, Qifan worked as a Research Engineer at Google Research, focusing on deep domain representations and large-scale object understanding.

Qifan's Publications

April 05, 2024

CONVERSATIONAL AI

NLP

MART: Improving LLM Safety with Multi-round Automatic Red-Teaming

Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa, Yi-Chia Wang, Qifan Wang, Jiawei Han, Yuning Mao

April 05, 2024

November 28, 2023

NLP

ROAST: Robustifying Language Models via Adversarial Perturbation with Selective Training

Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, Madian Khabsa

November 28, 2023

October 31, 2022

NLP

ML APPLICATIONS

AD-Drop: Attribution Driven Dropout for Robust Language Model Finetuning

Qifan Wang, Shaoliang Nie, Jinghao Deng, Tao Yang, Xiaojun Quan

October 31, 2022

July 20, 2022

Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian

Qifan Wang, Dongfang Liu, Yingjie Victor Chen, Zhiwen Cao

July 20, 2022

May 04, 2022

GL-RG: Global-Local Representation Granularity for Video Captioning

Qifan Wang, Dongfang Liu, Fuli Feng, Liqi Yan, Xiangyu Zhang, Xiaojun Quan, Yiming Cui

May 04, 2022

February 09, 2022

WebFormer: The Web-page Transformer for Structure Information Extraction

Qifan Wang, Anirudh Ravula, Dongfang Liu, Fuli Feng, Xiaojun Quan, Yi Fang

February 09, 2022