Zefan Cai - researchr alias

researchr

You are not signed in
Sign in
Sign up

Viewing Publication 1 - 21 from 21

2026

From Preferences to Prejudice: The Role of Alignment Tuning in Shaping Social Bias in Video Diffusion ModelsZefan Cai, Haoyi Qiu, Haozhe Zhao, Ke Wan, Jiachen Li, Jiuxiang Gu, Wen Xiao, Nanyun Peng 0001, Junjie Hu 0001. tmlr, 2026, 2026. [doi]

2025

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image GenerationLiang Chen 0024, Sinan Tan, Zefan Cai, Weichu Xie, Haozhe Zhao, Yichi Zhang, Junyang Lin, Jinze Bai, Tianyu Liu 0001, Baobao Chang. iclr 2025: [doi]

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image GenerationLiang Chen 0024, Sinan Tan, Zefan Cai, Weichu Xie, Haozhe Zhao, Yichi Zhang, Junyang Lin, Jinze Bai, Tianyu Liu 0001, Baobao Chang. iclr 2025: [doi]

Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and ReasoningYu Fu, Zefan Cai, Abedelkadir Asi, Wayne Xiong, Yue Dong 0002, Wen Xiao. iclr 2025: [doi]

LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language FeedbackBofei Gao, Zefan Cai, Runxin Xu, Peiyi Wang, Ce Zheng, Runji Lin, Keming Lu, Dayiheng Liu, Chang Zhou, Wen Xiao, Tianyu Liu, Baobao Chang. acl 2025: 14588-14604 [doi]

AdaptiveStep: Automatically Dividing Reasoning Step through Model ConfidenceYuliang Liu, Junjie Lu, Chaofeng Qu, Zhaoling Chen, Zefan Cai, Jason Klein Liu, Chonghan Liu, Yunhui Xia, Li Zhao 0007, Jiang Bian 0002, Chuheng Zhang, Wei Shen 0005, Zhouhan Lin. icml 2025: [doi]

COMMA: A Communicative Multimodal Multi-Agent BenchmarkTimothy Ossowski, Danyal Maqbool, Jixuan Chen, Zefan Cai, Tyler J. Bradshaw, Junjie Hu 0001. tmlr, 2025, 2025. [doi]

No Preference Left Behind: Group Distributional Preference OptimizationBinwei Yao, Zefan Cai, Yun-Shiuan Chuang, Shanglin Yang, Ming Jiang 0018, Diyi Yang, Junjie Hu. iclr 2025: [doi]

2024

PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action ChainLiang Chen 0024, Yichi Zhang, Shuhuai Ren, Haozhe Zhao, Zefan Cai, YuChi Wang, Peiyi Wang, Xiangdi Meng, Tianyu Liu 0001, Baobao Chang. acl 2014: 1086-1104 [doi]

DialogVCS: Robust Natural Language Understanding in Dialogue System UpgradeZefan Cai, Xin Zheng, Tianyu Liu 0001, Haoran Meng, Jiaqi Han, Gang Yuan, Binghuai Lin, Baobao Chang, Yunbo Cao. naacl 2014: 5431-5452 [doi]

Improving Event Definition Following For Zero-Shot Event DetectionZefan Cai, Po-Nien Kung, Ashima Suvarna, Mingyu Derek Ma, Hritik Bansal, Baobao Chang, P. Jeffrey Brantingham, Wei Wang 0010, Nanyun Peng. acl 2024: 2842-2863 [doi]

Improving the Robustness of Distantly-Supervised Named Entity Recognition via Uncertainty-Aware Teacher Learning and Student-Student Collaborative LearningShuzheng Si, Helan Hu, Haozhe Zhao, Shuang Zeng, Kaikai An, Zefan Cai, Baobao Chang. acl 2014: 5533-5546 [doi]

Large Language Models are not Fair EvaluatorsPeiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Lingpeng Kong, Qi Liu, Tianyu Liu, Zhifang Sui. acl 2024: 9440-9450 [doi]

VeCAF: Vision-language Collaborative Active Finetuning with Training Objective AwarenessRongyu Zhang, Zefan Cai, Huanrui Yang, Zidong Liu, Denis A. Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Baobao Chang, Yuan Du, Li Du, Shanghang Zhang. mm 2024: 5451-5459 [doi]

Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-DistillationHaozhe Zhao, Zefan Cai, Shuzheng Si, Liang Chen 0024, Yufeng He, Kaikai An, Baobao Chang. naacl 2014: 2893-2907 [doi]

MMICL: Empowering Vision-language Model with Multi-Modal In-Context LearningHaozhe Zhao, Zefan Cai, Shuzheng Si, Xiaojian Ma, Kaikai An, Liang Chen 0024, Zixuan Liu, Sheng Wang, Wenjuan Han, Baobao Chang. iclr 2024: [doi]

2023

2019

Using Feature Tree Model to Track High Speed Flying Soccer in Complicated BackgroundZhiPeng Yu, Zefan Cai. iske 2019: 880-885 [doi]

Sign in or sign up to see more results.

runs on WebDSL