ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer.

Jinyi Hu

Jinyi Hu Shengding Hu Yuxuan Song 0002 Yufei Huang 0008 Mingxuan Wang Hao Zhou 0012 Zhiyuan Liu 0001 Wei-Ying Ma Maosong Sun 0001 ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer. 2026 2026 Trans. Mach. Learn. Res. https://openreview.net/forum?id=OuFNXESoCO db/journals/tmlr/tmlr2026.html#HuHSHWZLMS26 streams/journals/tmlr

Jiarui Zhang 0002 Jinyi Hu Mahyar Khayatkhoei Filip Ilievski Maosong Sun 0001 Exploring Perceptual Limitations of Multimodal LLMs on Small Visual Objects. 2026 2026 Trans. Mach. Learn. Res. https://openreview.net/forum?id=D8MjYW8m35 db/journals/tmlr/tmlr2026.html#ZhangHKIS26 streams/journals/tmlr

Ran Li Zeyuan Liu Yinghao Chen Bingxiang He Jiarui Yuan Zixuan Fu Weize Chen Jinyi Hu Zhiyuan Liu Maosong Sun 0001 CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning. 2026 February abs/2602.02979 CoRR https://doi.org/10.48550/arXiv.2602.02979 db/journals/corr/corr2602.html#abs-2602-02979 streams/journals/corr

Wentong Chen Junbo Cui Jinyi Hu Yujia Qin Junjie Fang Yue Zhao Chongyi Wang Jun Liu Guirong Chen Yupeng Huo Yuan Yao 0013 Yankai Lin 0001 Zhiyuan Liu 0001 Maosong Sun 0001 GUICourse: From General Vision Language Model to Versatile GUI Agent. 21936-21959 2025 ACL (1) https://doi.org/10.18653/v1/2025.acl-long.1065 https://aclanthology.org/2025.acl-long.1065/ conf/acl/2025-1 db/conf/acl/acl2025-1.html#ChenCHQFZWLCHYL25 Zhijian Liu Ligeng Zhu Baifeng Shi Zhuoyang Zhang Yuming Lou Shang Yang Haocheng Xi Shiyi Cao Yuxian Gu Dacheng Li Xiuyu Li Haotian Tang Yunhao Fang Yukang Chen Cheng-Yu Hsieh De-An Huang An-Chieh Cheng Jinyi Hu Sifei Liu Ranjay Krishna Pavlo Molchanov 0001 Jan Kautz Hongxu Yin Song Han 0003 Yao Lu 0006 NVILA: Efficient Frontier Visual Language Models. 4122-4134 2025 CVPR https://openaccess.thecvf.com/content/CVPR2025/html/Liu_NVILA_Efficient_Frontier_Visual_Language_Models_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.00390 conf/cvpr/2025 db/conf/cvpr/cvpr2025.html#LiuZSZLYXCGLLTF25 Yecheng Wu Junyu Chen 0003 Zhuoyang Zhang Enze Xie Jincheng Yu Junsong Chen Jinyi Hu Yao Lu 0006 Song Han 0003 Han Cai DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer. 2025 ICCV 18034-18045 conf/iccv/2025 https://doi.org/10.1109/ICCV51701.2025.01676 db/conf/iccv/iccv2025.html#WuCZXYCHLHC25 streams/conf/iccv

Zhili Cheng Yuge Tu Ran Li Shiqi Dai Jinyi Hu Shengding Hu Jiahao Li Yang Shi Tianyu Yu 0002 Weize Chen Lei Shi Maosong Sun 0001 EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents. 2025 January abs/2501.11858 CoRR https://doi.org/10.48550/arXiv.2501.11858 db/journals/corr/corr2501.html#abs-2501-11858 streams/journals/corr

Yecheng Wu Junyu Chen 0003 Zhuoyang Zhang Enze Xie Jincheng Yu Junsong Chen Jinyi Hu Yao Lu 0006 Song Han 0003 Han Cai DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer. 2025 July abs/2507.04947 CoRR https://doi.org/10.48550/arXiv.2507.04947 db/journals/corr/corr2507.html#abs-2507-04947 streams/journals/corr

Jiangjie Chen Wenxiang Chen Jiacheng Du Jinyi Hu Zhicheng Jiang Allan Jie Xiaoran Jin Xing Jin Chenggang Li Wenlei Shi Zhihong Wang Mingxuan Wang Chenrui Wei Shufa Wei Huajian Xin Fan Yang Weihao Gao Zheng Yuan Tianyang Zhan Zeyu Zheng Tianxi Zhou Thomas Hanwen Zhu Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience. 2025 December abs/2512.17260 CoRR https://doi.org/10.48550/arXiv.2512.17260 db/journals/corr/corr2512.html#abs-2512-17260 streams/journals/corr

Zhili Cheng Zhitong Wang Jinyi Hu Shengding Hu An Liu Yuge Tu Pengkai Li Lei Shi Zhiyuan Liu 0001 Maosong Sun 0001 LEGENT: Open Platform for Embodied Agents. 335-345 2024 ACL (3) https://doi.org/10.18653/v1/2024.acl-demos.32 conf/acl/2024-3 db/conf/acl/acl2024-3.html#ChengWHHLTLS0024 Chaoqun He Renjie Luo Yuzhuo Bai Shengding Hu Zhen Leng Thai Junhao Shen Jinyi Hu Xu Han 0007 Yujie Huang Yuxiang Zhang Jie Liu Lei Qi Zhiyuan Liu 0001 Maosong Sun 0001 OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems. 3828-3850 2024 ACL (1) https://doi.org/10.18653/v1/2024.acl-long.211 https://aclanthology.org/2024.acl-long.211 https://www.wikidata.org/entity/Q131457836 conf/acl/2024-1 db/conf/acl/acl2024-1.html#HeLBHTSHHHZLQL024 Zanlin Ni Yulin Wang 0002 Renping Zhou Jiayi Guo Jinyi Hu Zhiyuan Liu 0001 Shiji Song Yuan Yao 0013 Gao Huang 0001 Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis. 7007-7016 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.00669 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#NiWZGHLSYH24 Tianyu Yu 0002 Yuan Yao 0013 Haoye Zhang Taiwen He Yifeng Han Ganqu Cui Jinyi Hu Zhiyuan Liu 0001 Hai-Tao Zheng 0002 Maosong Sun 0001 RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-Grained Correctional Human Feedback. 13807-13816 2024 CVPR https://doi.org/10.1109/CVPR52733.2024.01310 conf/cvpr/2024 db/conf/cvpr/cvpr2024.html#YuYZHHCHL0024 Zanlin Ni Yulin Wang 0002 Renping Zhou Rui Lu 0001 Jiayi Guo Jinyi Hu Zhiyuan Liu 0001 Yuan Yao 0013 Gao Huang 0001 AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation. 302-319 2024 ECCV (16) https://doi.org/10.1007/978-3-031-72640-8_17 conf/eccv/2024-16 db/conf/eccv/eccv2024-16.html#NiWZLGHLYH24 streams/conf/eccv Jinyi Hu Yuan Yao 0013 Chongyi Wang Shan Wang 0015 Yinxu Pan Qianyu Chen Tianyu Yu 0002 Hanghao Wu Yue Zhao Haoye Zhang Xu Han 0007 Yankai Lin 0001 Jiao Xue Dahai Li Zhiyuan Liu 0001 Maosong Sun 0001 Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages. 2024 ICLR https://openreview.net/forum?id=Kuh5qgCGCp conf/iclr/2024 db/conf/iclr/iclr2024.html#Hu0WWPCYWZZ0LXL24 Haiyang Bian Yixin Chen Xiaomin Dong Chen Li 0001 Minsheng Hao Sijie Chen Jinyi Hu Maosong Sun 0001 Lei Wei 0009 Xuegong Zhang scMulan: A Multitask Generative Pre-Trained Language Model for Single-Cell Analysis. 479-482 2024 RECOMB https://doi.org/10.1007/978-1-0716-3989-4_57 conf/recomb/2024 db/conf/recomb/recomb2024.html#BianCDLHCHSWZ24

Jiarui Zhang 0002 Jinyi Hu Mahyar Khayatkhoei Filip Ilievski Maosong Sun 0001 Exploring Perceptual Limitation of Multimodal Large Language Models. 2024 abs/2402.07384 CoRR https://doi.org/10.48550/arXiv.2402.07384 db/journals/corr/corr2402.html#abs-2402-07384

Chaoqun He Renjie Luo Yuzhuo Bai Shengding Hu Zhen Leng Thai Junhao Shen Jinyi Hu Xu Han 0007 Yujie Huang Yuxiang Zhang Jie Liu Lei Qi Zhiyuan Liu 0001 Maosong Sun 0001 OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems. 2024 abs/2402.14008 CoRR https://doi.org/10.48550/arXiv.2402.14008 db/journals/corr/corr2402.html#abs-2402-14008

Zhili Cheng Zhitong Wang Jinyi Hu Shengding Hu An Liu Yuge Tu Pengkai Li Lei Shi Zhiyuan Liu 0001 Maosong Sun 0001 LEGENT: Open Platform for Embodied Agents. 2024 abs/2404.18243 CoRR https://doi.org/10.48550/arXiv.2404.18243 db/journals/corr/corr2404.html#abs-2404-18243

Zanlin Ni Yulin Wang 0002 Renping Zhou Jiayi Guo Jinyi Hu Zhiyuan Liu 0001 Shiji Song Yuan Yao 0011 Gao Huang 0001 Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis. 2024 abs/2406.05478 CoRR https://doi.org/10.48550/arXiv.2406.05478 db/journals/corr/corr2406.html#abs-2406-05478

Zanlin Ni Yulin Wang 0002 Renping Zhou Rui Lu 0001 Jiayi Guo Jinyi Hu Zhiyuan Liu 0001 Yuan Yao 0011 Gao Huang 0001 AdaNAT: Exploring Adaptive Policy for Token-Based Image Generation. 2024 abs/2409.00342 CoRR https://doi.org/10.48550/arXiv.2409.00342 db/journals/corr/corr2409.html#abs-2409-00342 streams/journals/corr

Zhijian Liu Ligeng Zhu Baifeng Shi Zhuoyang Zhang Yuming Lou Shang Yang Haocheng Xi Shiyi Cao Yuxian Gu Dacheng Li Xiuyu Li Yunhao Fang Yukang Chen Cheng-Yu Hsieh De-An Huang An-Chieh Cheng Vishwesh Nath Jinyi Hu Sifei Liu Ranjay Krishna Daguang Xu Xiaolong Wang 0004 Pavlo Molchanov 0001 Jan Kautz Hongxu Yin Song Han 0003 Yao Lu 0006 NVILA: Efficient Frontier Visual Language Models. 2024 abs/2412.04468 CoRR https://doi.org/10.48550/arXiv.2412.04468 db/journals/corr/corr2412.html#abs-2412-04468 streams/journals/corr

Jinyi Hu Shengding Hu Yuxuan Song 0002 Yufei Huang 0008 Mingxuan Wang Hao Zhou 0012 Zhiyuan Liu 0001 Wei-Ying Ma Maosong Sun 0001 ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer. 2024 abs/2412.07720 CoRR https://doi.org/10.48550/arXiv.2412.07720 db/journals/corr/corr2412.html#abs-2412-07720 streams/journals/corr

Jiarui Zhang 0002 Ollie Liu Tianyu Yu Jinyi Hu Willie Neiswanger Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions. 2024 abs/2412.08737 CoRR https://doi.org/10.48550/arXiv.2412.08737 db/journals/corr/corr2412.html#abs-2412-08737 streams/journals/corr

Jinyi Hu Xu Han 0007 Xiaoyuan Yi Yutong Chen Wenhao Li 0003 Zhiyuan Liu 0001 Maosong Sun 0001 Efficient Cross-Lingual Transfer for Chinese Stable Diffusion with Images as Pivots. 2023 abs/2305.11540 CoRR https://doi.org/10.48550/arXiv.2305.11540 db/journals/corr/corr2305.html#abs-2305-11540

Jinyi Hu Yuan Yao 0013 Chongyi Wang Shan Wang 0015 Yinxu Pan Qianyu Chen Tianyu Yu 0002 Hanghao Wu Yue Zhao Haoye Zhang Xu Han 0007 Yankai Lin 0001 Jiao Xue Dahai Li Zhiyuan Liu 0001 Maosong Sun 0001 Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages. 2023 abs/2308.12038 CoRR https://doi.org/10.48550/arXiv.2308.12038 db/journals/corr/corr2308.html#abs-2308-12038

Tianyu Yu 0002 Jinyi Hu Yuan Yao 0013 Haoye Zhang Yue Zhao Chongyi Wang Shan Wang 0015 Yinxv Pan Jiao Xue Dahai Li Zhiyuan Liu 0001 Hai-Tao Zheng 0002 Maosong Sun 0001 Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants. 2023 abs/2310.00653 CoRR https://doi.org/10.48550/arXiv.2310.00653 db/journals/corr/corr2310.html#abs-2310-00653

Tianyu Yu 0002 Yuan Yao 0013 Haoye Zhang Taiwen He Yifeng Han Ganqu Cui Jinyi Hu Zhiyuan Liu 0001 Hai-Tao Zheng 0002 Maosong Sun 0001 Tat-Seng Chua RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback. 2023 abs/2312.00849 CoRR https://doi.org/10.48550/arXiv.2312.00849 db/journals/corr/corr2312.html#abs-2312-00849

Jinyi Hu Xiaoyuan Yi Wenhao Li 0003 Maosong Sun 0001 Xing Xie 0001 Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation. 6306-6320 2022 EMNLP (Findings) https://doi.org/10.18653/v1/2022.findings-emnlp.470 https://aclanthology.org/2022.findings-emnlp.470 conf/emnlp/2022f db/conf/emnlp/emnlp2022f.html#HuYLS022 Wenhao Li 0003 Xiaoyuan Yi Jinyi Hu Maosong Sun 0001 Xing Xie 0001 Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention. 10834-10858 2022 EMNLP https://doi.org/10.18653/v1/2022.emnlp-main.745 https://aclanthology.org/2022.emnlp-main.745 conf/emnlp/2022 db/conf/emnlp/emnlp2022.html#LiYHS022 Jinyi Hu Xiaoyuan Yi Wenhao Li 0003 Maosong Sun 0001 Xing Xie 0001 Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation. 697-716 2022 NAACL-HLT https://doi.org/10.18653/v1/2022.naacl-main.51 https://aclanthology.org/2022.naacl-main.51 conf/naacl/2022 db/conf/naacl/naacl2022.html#HuYLSX22

Jinyi Hu Xiaoyuan Yi Wenhao Li 0003 Maosong Sun 0001 Xing Xie 0001 Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation. 2022 abs/2207.06130 CoRR https://doi.org/10.48550/arXiv.2207.06130 db/journals/corr/corr2207.html#abs-2207-06130

Jinyi Hu Xiaoyuan Yi Wenhao Li 0003 Maosong Sun 0001 Xing Xie 0001 Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation. 2022 abs/2210.12409 CoRR https://doi.org/10.48550/arXiv.2210.12409 db/journals/corr/corr2210.html#abs-2210-12409

Wenhao Li 0003 Xiaoyuan Yi Jinyi Hu Maosong Sun 0001 Xing Xie 0001 Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention. 2022 abs/2211.07164 CoRR https://doi.org/10.48550/arXiv.2211.07164 db/journals/corr/corr2211.html#abs-2211-07164

Huimin Chen Yankai Lin 0001 Fanchao Qi Jinyi Hu Peng Li 0030 Jie Zhou 0016 Maosong Sun 0001 Aspect-Level Sentiment-Controllable Review Generation with Mutual Learning Framework. 12639-12647 2021 AAAI https://doi.org/10.1609/aaai.v35i14.17497 conf/aaai/2021 db/conf/aaai/aaai2021.html#ChenLQHLZS21 Jinyi Hu Maosong Sun 0001 Generating Major Types of Chinese Classical Poetry in a Uniformed Framework. 4658-4663 2020 LREC https://aclanthology.org/2020.lrec-1.573/ conf/lrec/2020 db/conf/lrec/lrec2020.html#HuS20 Wangchunshu Zhou Jinyi Hu Hanlin Zhang 0002 Xiaodan Liang Maosong Sun 0001 Chenyan Xiong Jian Tang 0005 Towards Interpretable Natural Language Understanding with Explanations as Latent Variables. 2020 NeurIPS https://proceedings.neurips.cc/paper/2020/hash/4be2c8f27b8a420492f2d44463933eb6-Abstract.html conf/nips/2020 db/conf/nips/neurips2020.html#ZhouHZLSXT20

Jinyi Hu Maosong Sun 0001 Generating Major Types of Chinese Classical Poetry in a Uniformed Framework. 2020 abs/2003.11528 CoRR https://arxiv.org/abs/2003.11528 db/journals/corr/corr2003.html#abs-2003-11528

Wangchunshu Zhou Jinyi Hu Hanlin Zhang 0002 Xiaodan Liang Maosong Sun 0001 Chenyan Xiong Jian Tang 0005 Towards Interpretable Natural Language Understanding with Explanations as Latent Variables. 2020 abs/2011.05268 CoRR https://arxiv.org/abs/2011.05268 db/journals/corr/corr2011.html#abs-2011-05268

Yuzhuo Bai Haiyang Bian Han Cai Shiyi Cao Guirong Chen Huimin Chen Jiangjie Chen Junsong Chen Junyu Chen 0003 Qianyu Chen Sijie Chen Weize Chen Wentong Chen Wenxiang Chen Yinghao Chen Yixin Chen Yukang Chen Yutong Chen An-Chieh Cheng Zhili Cheng Tat-Seng Chua Ganqu Cui Junbo Cui Shiqi Dai Xiaomin Dong Jiacheng Du Junjie Fang Yunhao Fang Zixuan Fu Weihao Gao Yuxian Gu Jiayi Guo Song Han 0003 Xu Han 0007 Yifeng Han Minsheng Hao Bingxiang He Chaoqun He Taiwen He Cheng-Yu Hsieh Shengding Hu De-An Huang Gao Huang 0001 Yufei Huang 0008 Yujie Huang Yupeng Huo Filip Ilievski Zhicheng Jiang Allan Jie Xiaoran Jin Xing Jin Jan Kautz Mahyar Khayatkhoei Ranjay Krishna Chen Li 0001 Chenggang Li Dacheng Li Dahai Li Jiahao Li Peng Li 0030 Pengkai Li Ran Li Wenhao Li 0003 Xiuyu Li Xiaodan Liang Yankai Lin 0001 An Liu Jie Liu Jun Liu Ollie Liu Sifei Liu Zeyuan Liu Zhijian Liu Zhiyuan Liu Zhiyuan Liu 0001 Yuming Lou Rui Lu 0001 Yao Lu 0006 Renjie Luo Wei-Ying Ma Pavlo Molchanov 0001 Vishwesh Nath Willie Neiswanger Zanlin Ni Yinxu Pan Yinxv Pan Fanchao Qi Lei Qi Yujia Qin Junhao Shen Baifeng Shi Lei Shi Wenlei Shi Yang Shi Shiji Song Yuxuan Song 0002 Maosong Sun 0001 Haotian Tang Jian Tang 0005 Zhen Leng Thai Yuge Tu Chongyi Wang Mingxuan Wang Shan Wang 0015 Xiaolong Wang 0004 Yulin Wang 0002 Zhihong Wang Zhitong Wang Chenrui Wei Lei Wei 0009 Shufa Wei Hanghao Wu Yecheng Wu Haocheng Xi Enze Xie Xing Xie 0001 Huajian Xin Chenyan Xiong Daguang Xu Jiao Xue Fan Yang Shang Yang Yuan Yao 0011 Yuan Yao 0013 Xiaoyuan Yi Hongxu Yin Jincheng Yu Tianyu Yu Tianyu Yu 0002 Jiarui Yuan Zheng Yuan Tianyang Zhan Hanlin Zhang 0002 Haoye Zhang Jiarui Zhang 0002 Xuegong Zhang Yuxiang Zhang Zhuoyang Zhang Yue Zhao Hai-Tao Zheng 0002 Zeyu Zheng Hao Zhou 0012 Jie Zhou 0016 Renping Zhou Tianxi Zhou Wangchunshu Zhou Ligeng Zhu Thomas Hanwen Zhu