论文
亦可查看 Google Scholar。
按发表年份倒序排列，同一年内按首次公开日期倒序排列。* 表示共同贡献。主要研究方向的详细介绍见研究页面。
2026
仅需最后一层的键值缓存
Last Layer Key-Value Cache is All You Need
Zefan Cai, Sai Bi, Lin Zhang, Yicong Hong, Chongjian Ge, Xun Huang, Jiuxiang Gu, Junjie Hu, Hao Tan
COLM 2026 ER 研讨会 （Spotlight）
PDF · 详情
测试时生成
Test-Time Generation
Zefan Cai, Hao Tan, Yuchen Zhu, Tianyuan Zhang, Sai Bi, Haoyi Qiu, Yicong Hong, Jason Kuen, Haoliang Wang, Haozhe Zhao, Ruiyi Zhang, Ryan A. Rossi, Wanrong Zhu, Molei Tao, Wen Xiao, Rajiv Jain, Junjie Hu, Jiuxiang Gu
COLM 2026 ER 研讨会 （Spotlight）
PDF · 详情
通用测试时训练
Universal Test-Time Training
Zefan Cai*, Qinzhe Hu*, Ziqiao Ma, Hao Tan, Junjie Hu
COLM 2026 ER 研讨会 （Spotlight）
PDF · 项目主页 · 代码 · 详情
Chimera：混合视觉扩散 Transformer 的设计与 Chinchilla 扩展
Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers
Chongjian Ge, Hanwen Jiang, Tianyu Wang, Jiuxiang Gu, Yiran Xu, Ziwen Chen, Shaoteng Liu, Jing Shi, Yicong Hong, Zefan Cai, Hailin Jin, Hao Tan
预印本 2026
PDF
多头注意力残差
Multi-Head Attention Residuals
Cheng Luo*, Zefan Cai*, Junjie Hu
预印本 2026
PDF · 项目主页 · 代码 · 权重: MHAR 8B · 权重: CPT control 8B · 详情
利用下一词元预测进行测试时训练
Test-Time Training with Next-Token Prediction
Xuan Ouyang*, Zefan Cai*, Junjie Hu
Findings of EMNLP 2026
PDF · 代码 · 详情
UniTemp：通过自回归蒸馏实现任意时间顺序的视频生成
UniTemp: Unlocking Video Generation in Any Temporal Order via Autoregressive Distillation
Lin Zhang, Sicheng Mo, Zefan Cai, Jinhong Lin, Zihao Lin, Jiuxiang Gu, Krishna Kumar Singh, Yuheng Li, Yin Li
ECCV 2026 （海报）
PDF · 项目主页 · 代码 · 数据 · 权重
Delta 注意力残差
Delta Attention Residuals
Cheng Luo*, Zefan Cai*, Junjie Hu
预印本 2026
PDF · 代码 · 详情
BabyVision：超越语言的视觉推理
BabyVision: Visual Reasoning Beyond Language
Liang Chen, Weichu Xie, Yiyan Liang, Hongfeng He, Haozhe Zhao, Zhibo Yang, Zhiqi Huang, Haoning Wu, Haoyu Lu, Y. Charles, Yiping Bao, Yuantao Fan, Guopeng Li, Haiyang Shen, Xuanzhong Chen, Wendong Xu, Shuzheng Si, Zefan Cai, Wenhao Chai, Ziqi Huang, Fangfu Liu, Tianyu Liu, Baobao Chang, Ming Wu, Xiaobo Hu, Kaiyuan Chen, Yixin Ren, Yang Liu, Yuan Gong, Kuan Li
ICML 2026
PDF · arXiv · 项目主页 · 代码 · 排行榜 · 数据: BabyVision · 数据: BabyVision-Gen
MMGR：多模态生成式推理基准与评估
MMGR: Multi-Modal Generative Reasoning Benchmark and Evaluation
Zefan Cai, Haoyi Qiu, Tianyi Ma, Haozhe Zhao, Gengze Zhou, Kung-Hsiang Huang, Parisa Kordjamshidi, Minjia Zhang, Wen Xiao, Jiuxiang Gu, Nanyun Peng, Junjie Hu
EMNLP 2026 （主会，海报）
PDF
从偏好到偏见：对齐微调如何塑造视频扩散模型中的社会偏见
From Preferences to Prejudice: The Role of Alignment Tuning in Shaping Social Bias in Video Diffusion Models
Zefan Cai*, Haoyi Qiu*, Haozhe Zhao*, Ke Wan, Jiachen Li, Jiuxiang Gu, Wen Xiao, Nanyun Peng, Junjie Hu
TMLR 2026 · MSLD 2026 （海报）
PDF · arXiv · 代码 · 详情
MENTOR：具有均衡多模态控制能力的高效自回归图像生成
MENTOR: Efficient Autoregressive Image Generation with Balanced Multimodal Control
Haozhe Zhao*, Zefan Cai*, Shuzheng Si, Liang Chen, Jiuxiang Gu, Wen Xiao, Minjia Zhang, Junjie Hu
Findings of ACL 2026
PDF · 项目主页 · 代码 · 数据: Stage 1 · 数据: Stage 2 · 权重 · 详情
从经验中学习选择视觉工具
Learning to Select Visual Tools from Experience
Zeyi Huang, Yuyang Ji, Anirudh Sundara Rajan, Zefan Cai, Wen Xiao, Haohan Wang, Junjie Hu, Yong Jae Lee
CVPR 2026
PDF · 项目主页 · 代码
2025
扩展音频同步视觉动画：一种高效训练范式
Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm
Lin Zhang, Zefan Cai, Yufan Zhou, Shentong Mo, Jinhong Lin, Cheng-En Wu, Yibing Wei, Yijing Zhang, Ruiyi Zhang, Wen Xiao, Tong Sun, Junjie Hu, Pedro Morgado
预印本 2025
PDF · 数据
潜在空间推理综述
A Survey on Latent Reasoning
RuiJie Zhu, Tianhao Peng, Tianhao Cheng, Xingwei Qu, Jinfa Huang, Dawei Zhu, Hao Wang, Kaiwen Xue, Xuanliang Zhang, Yong Shan, Tianle Cai, Taylor Kergan, Assel Kembay, Andrew Smith, Chenghua Lin, Binh Nguyen, Yuqi Pan, Yuhong Chou, Zefan Cai, Zhenhe Wu, Yongchi Zhao, Tianyu Liu, Jian Yang, Wangchunshu Zhou, Chujie Zheng, Chongxuan Li, Yuyin Zhou, Zhoujun Li, Zhaoxiang Zhang, Jiaheng Liu, Ge Zhang, Wenhao Huang, Jason Eshraghian
预印本 2025
PDF · 资源
R-KV：感知冗余的推理模型 KV 缓存压缩
R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
Zefan Cai, Wen Xiao, Hanshi Sun, Cheng Luo, Yikai Zhang, Ke Wan, Yucheng Li, Yeyang Zhou, Li-Wen Chang, Jiuxiang Gu, Zhen Dong, Animashree Anandkumar, Abedelkadir Asi, Junjie Hu
NeurIPS 2025
PDF · 项目主页 · 代码 · 视频 · 动态 · 详情
AdaptiveStep：依据模型置信度自动划分推理步骤
AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
Yuliang Liu, Junjie Lu, Chaofeng Qu, Zhaoling Chen, Zefan Cai, Jason Klein Liu, Chonghan Liu, Yunhui Xia, Li Zhao, Jiang Bian, Chuheng Zhang, Wei Shen, Zhouhan Lin
ICML 2025 （海报）
PDF · arXiv · 代码
数据: Eval: Math · Eval: Code · Train: L · Train: M · Train: D
权重: L · M · D
HeadInfer：通过按注意力头卸载实现内存高效的大语言模型推理
HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading
Cheng Luo, Zefan Cai, Hanshi Sun, Jinqi Xiao, Bo Yuan, Wen Xiao, Junjie Hu, Jiawei Zhao, Beidi Chen, Anima Anandkumar
ICML 2025 长上下文基础模型研讨会
PDF · arXiv · 代码 · 详情
不遗漏任何偏好：群体分布偏好优化
No Preference Left Behind: Group Distributional Preference Optimization
Binwei Yao, Zefan Cai, Yun-Shiuan Chuang, Shanglin Yang, Ming Jiang, Diyi Yang, Junjie Hu
ICLR 2025 （海报）
PDF · arXiv · 代码
数据: MMOQA USA · MMOQA USA (large) · MMOQA PK · MMOQA PK (large) · MMOQA SA · MMOQA SA (large) · Movie reviews · Movie reviews (large)
并非所有注意力头都同样重要：融合检索与推理的注意力头级 KV 缓存压缩方法
Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning
Yu Fu, Zefan Cai, Abedelkadir Asi, Wayne Xiong, Yue Dong, Wen Xiao
ICLR 2025 （海报）
PDF · arXiv · 代码 · 详情 · 数据: Evaluation · 数据: Reasoning
Omni-Math：面向大语言模型的通用奥林匹克级数学基准
Omni-MATH: A Universal Olympiad Level Mathematic Benchmark for Large Language Models
Bofei Gao, Feifan Song, Zhe Yang, Zefan Cai, Yibo Miao, Qingxiu Dong, Lei Li, Chenghao Ma, Liang Chen, Runxin Xu, Zhengyang Tang, Benyou Wang, Daoguang Zan, Shanghaoran Quan, Ge Zhang, Lei Sha, Yichang Zhang, Xuancheng Ren, Tianyu Liu, Baobao Chang
ICLR 2025 （海报）
PDF · arXiv · 项目主页 · 代码 · 数据 · 权重
COMMA：具备通信能力的多模态多智能体基准
COMMA: A Communicative Multimodal Multi-Agent Benchmark
Timothy Ossowski, Danyal Maqbool, Jixuan Chen, Zefan Cai, Tyler J. Bradshaw, Junjie Hu
TMLR 2025
PDF · arXiv · 代码
视觉语言智能的火花：用于高效精细图像生成的二维自回归 Transformer
A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
Liang Chen, Sinan Tan, Zefan Cai, Weichu Xie, Haozhe Zhao, Yichi Zhang, Junyang Lin, Jinze Bai, Tianyu Liu, Baobao Chang
ICLR 2025 （海报）
PDF · arXiv · 代码 · 权重
大语言模型评审器助力发现数学错误：利用自然语言反馈构建更好的数学验证器
LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
Bofei 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 (Findings)
PDF · 论文页面 · 代码 · 数据: Feedback · 数据: Math-Shepherd
PyramidKV：基于金字塔式信息汇聚的动态 KV 缓存压缩
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Zefan Cai, Yichi Zhang, Bofei Gao, Yuliang Liu, Yucheng Li, Tianyu Liu, Keming Lu, Wayne Xiong, Yue Dong, Junjie Hu, Wen Xiao
COLM 2025 （Spotlight）
PDF · arXiv · 项目主页 · 代码 · 动态 · 详情
ML-Bench：评估大语言模型与智能体在代码仓库级机器学习任务中的表现
ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code
Xiangru Tang*, Yuliang Liu*, Zefan Cai*, Yanjun Shao*, Junjie Lu, Yichi Zhang, Zexuan Deng, Helan Hu, Kaikai An, Ruijun Huang, Shuzheng Si, Sheng Chen, Haozhe Zhao, Liang Chen, Yan Wang, Tianyu Liu, Zhiwei Jiang, Baobao Chang, Yin Fang, Yujia Qin, Wangchunshu Zhou, Yilun Zhao, Arman Cohan, Mark Gerstein
作者名单以最新 arXiv 版本（v5）为准。
ICLR DL4C 研讨会 2025 · ICLR Agentic AI for Science 研讨会 2025 （口头报告）
PDF · 研讨会 PDF · 项目主页 · 代码 · 数据 · 详情
2024
迈向多模态智能的下一词元预测：综合综述
Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey
Liang Chen, Zekun Wang, Shuhuai Ren, Lei Li, Haozhe Zhao, Yunshui Li, Zefan Cai, Hongcheng Guo, Lei Zhang, Yizhe Xiong, Yichi Zhang, Ruoyu Wu, Qingxiu Dong, Ge Zhang, Jian Yang, Lingwei Meng, Shujie Hu, Yulong Chen, Junyang Lin, Shuai Bai, Andreas Vlachos, Xu Tan, Minjia Zhang, Wen Xiao, Aaron Yee, Tianyu Liu, Baobao Chang
预印本 2024
PDF · 资源
大语言模型偏好学习的统一视角：综述
Towards a Unified View of Preference Learning for Large Language Models: A Survey
Bofei Gao, Feifan Song, Yibo Miao, Zefan Cai, Zhe Yang, Liang Chen, Helan Hu, Runxin Xu, Qingxiu Dong, Ce Zheng, Shanghaoran Quan, Wen Xiao, Ge Zhang, Daoguang Zan, Keming Lu, Bowen Yu, Dayiheng Liu, Zeyu Cui, Jian Yang, Lei Sha, Houfeng Wang, Zhifang Sui, Peiyi Wang, Tianyu Liu, Baobao Chang
预印本 2024
PDF · 项目主页 · 资源
通过不确定性感知教师学习与学生间协同学习提升远程监督命名实体识别的鲁棒性
Improving the Robustness of Distantly-Supervised Named Entity Recognition via Uncertainty-Aware Teacher Learning and Student-Student Collaborative Learning
Shuzheng Si, Helan Hu, Haozhe Zhao, Shuang Zeng, Kaikai An, Zefan Cai, Baobao Chang
Findings of ACL 2024
PDF · 论文页面 · 代码 · 数据
通过教师语言选择与跨语言自蒸馏缓解多语言预训练语言模型的语言间性能差异
Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-Distillation
Haozhe Zhao*, Zefan Cai*, Shuzheng Si*, Liang Chen, Yufeng He, Kaikai An, Baobao Chang
NAACL 2024
PDF · 论文页面 · 代码 · 详情
提升零样本事件检测中的事件定义遵循能力
Improving Event Definition Following For Zero-Shot Event Detection
Zefan Cai*, Po-Nien Kung*, Ashima Suvarna, Mingyu Derek Ma, Hritik Bansal, Baobao Chang, P. Jeffrey Brantingham, Wei Wang, Nanyun Peng
ACL 2024 （主会） · 长文
PDF · 论文页面 · 代码 · 数据 · 详情
VeCAF：感知训练目标的视觉语言协同主动微调
VeCAF: Vision-language Collaborative Active Finetuning with Training Objective Awareness
Rongyu Zhang*, Zefan Cai*, Huanrui Yang*, Zidong Liu, Denis Gudovskiy, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Baobao Chang, Yuan Du, Li Du, Shanghang Zhang
ACM Multimedia 2024
PDF · 代码 · 详情
PCA-Bench：在感知、认知与行动链中评估多模态大语言模型
PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain
Liang Chen, Yichi Zhang, Shuhuai Ren, Haozhe Zhao, Zefan Cai, Yuchi Wang, Peiyi Wang, Xiangdi Meng, Tianyu Liu, Baobao Chang
Findings of ACL 2024 · NeurIPS 2023 决策基础模型研讨会
早期研讨会版本：Towards End-to-End Embodied Decision Making with Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond。
PDF · 论文页面 · 项目主页 · 代码 · 研讨会 PDF · 研讨会 arXiv · 数据: PCA-Bench V1 · 数据: Original v1.0
MMICL：通过多模态上下文学习增强视觉语言模型
MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
Haozhe Zhao*, Zefan Cai*, Shuzheng Si*, Xiaojian Ma, Kaikai An, Liang Chen, Zixuan Liu, Sheng Wang, Wenjuan Han, Baobao Chang
ICLR 2024 （海报）
PDF · arXiv · 代码 · 详情
数据: MIC full · MIC sampled
权重: T5 XXL · T5 XL
大语言模型并非公平的评估者
Large Language Models are not Fair Evaluators
Peiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Lingpeng Kong, Qi Liu, Tianyu Liu, Zhifang Sui
ACL 2024 （主会，长文）
PDF · 论文页面 · 代码 · 数据
DialogVCS：对话系统升级中的鲁棒自然语言理解
DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade
Zefan Cai*, Xin Zheng*, Tianyu Liu*, Xu Wang, Haoran Meng, Jiaqi Han, Gang Yuan, Binghuai Lin, Yunbo Cao, Baobao Chang
NAACL 2024 （主会） · 长文
PDF · 代码 · 数据 · 详情
2023
通过思维链实现人在回路中的参与
Human-in-the-Loop through Chain-of-Thought
Zefan Cai, Baobao Chang, Wenjuan Han
预印本 2023
PDF · 详情
DiffCap：探索用于图像描述的连续扩散
DiffCap: Exploring Continuous Diffusion on Image Captioning
Yufeng He*, Zefan Cai*, Xu Gan, Baobao Chang
预印本 2023
PDF · 代码 · 详情
SANTA：针对远程监督命名实体识别中不准确与不完整标注噪声的独立策略
SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition
Shuzheng Si*, Zefan Cai*, Shuang Zeng, Guoqiang Feng, Jiaxing Lin, Baobao Chang
Findings of ACL 2023
PDF · 代码 · 数据 · 详情
大语言模型的组合式任务表示
Compositional Task Representations for Large Language Models
Nan Shao*, Zefan Cai*, Hanwei Xu, Chonghua Liao, Yanan Zheng, Zhilin Yang
ICLR 2023 （海报）
PDF · 代码 · 数据: Processed · 数据: No prompt · 权重 · 详情