GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning.

Pandeng Li https://orcid.org/0000-0002-0717-8659

Kaixun Jiang Yuzheng Wang Junjie Zhou Pandeng Li Zhihang Liu Chen-Wei Xie Zhaoyu Chen 0001 Yun Zheng Wenqiang Zhang GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning. 2026 January abs/2601.18543 CoRR https://doi.org/10.48550/arXiv.2601.18543 db/journals/corr/corr2601.html#abs-2601-18543 streams/journals/corr

Zhaohe Liao Kaixun Jiang Zhihang Liu Yujie Wei 0001 Junqiu Yu Quanhao Li Hong-Tao Yu Pandeng Li Yuzheng Wang Zhen Xing Shiwei Zhang 0001 Chen-Wei Xie Yun Zheng Xihui Liu AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation. 2026 March abs/2603.28068 CoRR https://doi.org/10.48550/arXiv.2603.28068 db/journals/corr/corr2603.html#abs-2603-28068 streams/journals/corr

Quanhao Li Junqiu Yu Kaixun Jiang Yujie Wei 0001 Zhen Xing Pandeng Li Ruihang Chu Shiwei Zhang 0001 Yu Liu Zuxuan Wu DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models. 2026 May abs/2605.15055 CoRR https://doi.org/10.48550/arXiv.2605.15055 db/journals/corr/corr2605.html#abs-2605-15055 streams/journals/corr

Lianghua Huang Zhi-Fan Wu Wei Wang 0354 Yupeng Shi Mengyang Feng Junjie He Chen-Wei Xie Yu Liu 0015 Jingren Zhou 0001 Ang Wang Bang Zhang Baole Ai Chen Liang Cheng Yu Chongyang Zhong Jinwei Qi Kai Zhu 0004 Pandeng Li Peng Zhang Wenyuan Zhang Xinhua Cheng Yitong Huang Yun Zheng Yuzheng Wang Zoubin Bi Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models. 2026 June abs/2606.25041 CoRR https://doi.org/10.48550/arXiv.2606.25041 db/journals/corr/corr2606.html#abs-2606-25041 streams/journals/corr

Lianghua Huang Zhi-Fan Wu Yupeng Shi Wei Wang Mengyang Feng Junjie He Chen-Wei Xie Yu Liu 0015 Jingren Zhou 0001 Ang Wang Bang Zhang Baole Ai Chen Liang Cheng Yu Chongyang Zhong Jinwei Qi Kai Zhu 0004 Pandeng Li Peng Zhang Wenyuan Zhang Xinhua Cheng Yitong Huang Yun Zheng Yuxiang Bao Yuzheng Wang Zoubin Bi Wan-Streamer v0.2: Higher Resolution, Same Latency. 2026 July abs/2607.04443 CoRR https://doi.org/10.48550/arXiv.2607.04443 db/journals/corr/corr2607.html#abs-2607-04443 streams/journals/corr

Binghui Chen Pandeng Li Yu Liu 0015 Jingren Zhou 0001 WanSong v1.0 Technical Report. 2026 July abs/2607.14749 CoRR https://doi.org/10.48550/arXiv.2607.14749 db/journals/corr/corr2607.html#abs-2607-14749 streams/journals/corr

Lianghua Huang Zhi-Fan Wu Yupeng Shi Wei Wang Mengyang Feng Cheng Yu Chen Liang Junjie He Chen-Wei Xie Yu Liu 0015 Jingren Zhou 0001 Ang Wang Bang Zhang Baole Ai Chongyang Zhong Jinwei Qi Kai Zhu 0004 Pandeng Li Peng Zhang Wenyuan Zhang Xinhua Cheng Yitong Huang Yun Zheng Yuxiang Bao Yuzheng Wang Zhiwei Lin Zoubin Bi Video = World + Event Stream. 2026 July abs/2607.15038 CoRR https://doi.org/10.48550/arXiv.2607.15038 db/journals/corr/corr2607.html#abs-2607-15038 streams/journals/corr

Xuran Deng Zhihang Liu Pandeng Li Dual variational network for unsupervised cross-modal hashing. 3729-3746 2025 June 16 Int. J. Mach. Learn. Cybern. 5-6 https://doi.org/10.1007/s13042-024-02477-w db/journals/mlc/mlc16.html#DengLL25 streams/journals/mlc

Wanting Yin Jiannan Ge Lei Zhang 0119 Pandeng Li Yizhi Liu Hongtao Xie 0001 Attention-driven frequency-based Zero-Shot Learning with phase augmentation. 4325-4345 2025 August 16 Int. J. Mach. Learn. Cybern. 7-8 https://doi.org/10.1007/s13042-024-02512-w db/journals/mlc/mlc16.html#YinGZLLX25 streams/journals/mlc

Jiannan Ge Zhihang Liu Pandeng Li Lingxi Xie Yongdong Zhang 0001 Qi Tian 0001 Hongtao Xie 0001 Denoised and Dynamic Alignment Enhancement for Zero-Shot Learning. 1501-1515 2025 34 IEEE Trans. Image Process. https://doi.org/10.1109/TIP.2025.3544481 db/journals/tip/tip34.html#GeLLXZTX25 streams/journals/tip

Zhihang Liu Chen-Wei Xie Pandeng Li Liming Zhao Longxiang Tang Yun Zheng Chuanbin Liu 0001 Hongtao Xie 0001 Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models. 8568-8578 2025 CVPR https://openaccess.thecvf.com/content/CVPR2025/html/Liu_Hybrid-Level_Instruction_Injection_for_Video_Token_Compression_in_Multi-modal_Large_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.00801 conf/cvpr/2025 db/conf/cvpr/cvpr2025.html#LiuXLZTZ0X25 Jiannan Ge Lingxi Xie Hongtao Xie 0001 Pandeng Li Sun-Ao Liu Xiaopeng Zhang 0008 Qi Tian 0001 Yongdong Zhang 0001 CLIP-Adapted Region-to-Text Learning for Generative Open-Vocabulary Semantic Segmentation. 2025 ICCV 24034-24044 conf/iccv/2025 https://doi.org/10.1109/ICCV51701.2025.02228 db/conf/iccv/iccv2025.html#GeXXLLZTZ25 streams/conf/iccv Zhihang Liu Chen-Wei Xie Bin Wen Feiwu Yu Jixuan Chen Pandeng Li Boqiang Zhang Nianzu Yang Yinglu Li Zuan Gao Yun Zheng Hongtao Xie 0001 CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness. 2025 NeurIPS http://papers.nips.cc/paper_files/paper/2025/hash/5f2809607f692d79a01c05c43d702883-Abstract-Datasets_and_Benchmarks_Track.html conf/nips/2025 db/conf/nips/neurips2025.html#LiuXWYCLZYLGZX25 Hao Tang 0005 Chen-Wei Xie Haiyang Wang Xiaoyi Bao Tingyu Weng Pandeng Li Yun Zheng Liwei Wang 0001 UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface. 2025 NeurIPS http://papers.nips.cc/paper_files/paper/2025/hash/78a241e1d2ff2366af8cc9a459875a01-Abstract-Conference.html conf/nips/2025 db/conf/nips/neurips2025.html#TangXWBWLZW25

Zhihang Liu Chen-Wei Xie Bin Wen Feiwu Yu Jixuan Chen Boqiang Zhang Nianzu Yang Pandeng Li Yun Zheng Hongtao Xie 0001 What Is a Good Caption? A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Coverage of MLLMs. 2025 February abs/2502.14914 CoRR https://doi.org/10.48550/arXiv.2502.14914 db/journals/corr/corr2502.html#abs-2502-14914 streams/journals/corr

Hao Tang 0005 Chenwei Xie Haiyang Wang Xiaoyi Bao Tingyu Weng Pandeng Li Yun Zheng Liwei Wang 0001 UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface. 2025 March abs/2503.01342 CoRR https://doi.org/10.48550/arXiv.2503.01342 db/journals/corr/corr2503.html#abs-2503-01342 streams/journals/corr

Nianzu Yang Pandeng Li Liming Zhao Yang Li 0197 Chen-Wei Xie Yehui Tang 0002 Xudong Lu Zhihang Liu Yun Zheng Yu Liu 0015 Junchi Yan Rethinking Video Tokenization: A Conditioned Diffusion-based Approach. 2025 March abs/2503.03708 CoRR https://doi.org/10.48550/arXiv.2503.03708 db/journals/corr/corr2503.html#abs-2503-03708 streams/journals/corr

Zhihang Liu Chen-Wei Xie Pandeng Li Liming Zhao Longxiang Tang Yun Zheng Chuanbin Liu 0001 Hongtao Xie 0001 Hybrid-Level Instruction Injection for Video Token Compression in Multi-modal Large Language Models. 2025 March abs/2503.16036 CoRR https://doi.org/10.48550/arXiv.2503.16036 db/journals/corr/corr2503.html#abs-2503-16036 streams/journals/corr

Ang Wang Baole Ai Bin Wen Chaojie Mao Chen-Wei Xie Di Chen Feiwu Yu Haiming Zhao Jianxiao Yang Jianyuan Zeng Jiayu Wang Jingfeng Zhang Jingren Zhou 0001 Jinkai Wang Jixuan Chen Kai Zhu 0004 Kang Zhao Keyu Yan Lianghua Huang Xiaofeng Meng 0001 Ningyi Zhang Pandeng Li Pingyu Wu Ruihang Chu Ruili Feng Shiwei Zhang 0001 Siyang Sun Tao Fang Tianxing Wang 0006 Tianyi Gui Tingyu Weng Tong Shen Wei Lin 0016 Wei Wang 0354 Wei Wang 0377 Wenmeng Zhou Wente Wang Wenting Shen Wenyuan Yu Xianzhong Shi Xiaoming Huang Xin Xu Yan Kou Yangyu Lv Yifei Li Yijing Liu Yiming Wang 0011 Yingya Zhang Yitong Huang Yong Li 0045 You Wu Yu Liu 0015 Yulin Pan Yun Zheng Yuntao Hong Yupeng Shi Yutong Feng Zeyinzi Jiang Zhen Han Zhi-Fan Wu Ziyu Liu Wan: Open and Advanced Large-Scale Video Generative Models. 2025 March abs/2503.20314 CoRR https://doi.org/10.48550/arXiv.2503.20314 db/journals/corr/corr2503.html#abs-2503-20314 streams/journals/corr

Hao Tang 0005 Chenwei Xie Xiaoyi Bao Tingyu Weng Pandeng Li Yun Zheng Liwei Wang 0001 UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing. 2025 July abs/2507.23278 CoRR https://doi.org/10.48550/arXiv.2507.23278 db/journals/corr/corr2507.html#abs-2507-23278 streams/journals/corr

Zhihang Liu Xiaoyi Bao Pandeng Li Junjie Zhou Zhaohe Liao Yefei He Kaixun Jiang Chen-Wei Xie Yun Zheng Hongtao Xie 0001 ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement. 2025 December abs/2512.13303 CoRR https://doi.org/10.48550/arXiv.2512.13303 db/journals/corr/corr2512.html#abs-2512-13303 streams/journals/corr

Tianhao Qi Hongtao Xie 0001 Pandeng Li Jiannan Ge Yongdong Zhang 0001 Balanced Classification: A Unified Framework for Long-Tailed Object Detection. 3088-3101 2024 26 IEEE Trans. Multim. https://doi.org/10.1109/TMM.2023.3306968 db/journals/tmm/tmm26.html#QiXLGZ24

Hongtao Xie 0001 Yan Jiang Lei Zhang 0119 Pandeng Li Dongming Zhang 0004 Yongdong Zhang 0001 Semantic-Enhanced Proxy-Guided Hashing for Long-Tailed Image Retrieval. 9499-9514 2024 26 IEEE Trans. Multim. https://doi.org/10.1109/TMM.2024.3394684 db/journals/tmm/tmm26.html#XieJZLZZ24 streams/journals/tmm

Jiannan Ge Hongtao Xie 0001 Pandeng Li Lingxi Xie Shaobo Min Yongdong Zhang 0001 Towards Discriminative Feature Generation for Generalized Zero-Shot Learning. 10514-10529 2024 26 IEEE Trans. Multim. https://doi.org/10.1109/TMM.2024.3408048 db/journals/tmm/tmm26.html#GeXLXMZ24 streams/journals/tmm

Zhihang Liu Jun Li Hongtao Xie 0001 Pandeng Li Jiannan Ge Sun'ao Liu Guoqing Jin Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval. 3855-3863 2024 AAAI https://doi.org/10.1609/aaai.v38i4.28177 conf/aaai/2024 db/conf/aaai/aaai2024.html#LiuLXLGLJ24 Jiannan Ge Lingxi Xie Hongtao Xie 0001 Pandeng Li Xiaopeng Zhang 0008 Yong-Dong Zhang 0001 Qi Tian 0001 AlignZeg: Mitigating Objective Misalignment for Zero-Shot Semantic Segmentation. 142-161 2024 ECCV (43) https://doi.org/10.1007/978-3-031-72775-7_9 conf/eccv/2024-43 db/conf/eccv/eccv2024-43.html#GeXXLZZT24 streams/conf/eccv Chen-Wei Xie Siyang Sun Liming Zhao Pandeng Li Shuailei Ma Yun Zheng FuseTeacher: Modality-Fused Encoders are Strong Vision Supervisors. 287-304 2024 ECCV (48) https://doi.org/10.1007/978-3-031-73195-2_17 conf/eccv/2024-48 db/conf/eccv/eccv2024-48.html#XieSZLMZ24 streams/conf/eccv

Jiannan Ge Lingxi Xie Hongtao Xie 0001 Pandeng Li Xiaopeng Zhang 0008 Yongdong Zhang 0001 Qi Tian 0001 AlignZeg: Mitigating Objective Misalignment for Zero-shot Semantic Segmentation. 2024 abs/2404.05667 CoRR https://doi.org/10.48550/arXiv.2404.05667 db/journals/corr/corr2404.html#abs-2404-05667

Pandeng Li Hongtao Xie 0001 Yan Jiang Jiannan Ge Yongdong Zhang 0001 Neighborhood-Adaptive Multi-Cluster Ranking for Deep Metric Learning. 1952-1965 2023 April 33 IEEE Trans. Circuits Syst. Video Technol. 4 https://doi.org/10.1109/TCSVT.2022.3213680 db/journals/tcsv/tcsv33.html#LiXJGZ23

Peishuo Li Pandeng Li Wanting Yin Self-supervised Weighted Hashing with Topology Mining. 143-148 2023 CCEAI https://doi.org/10.1145/3580219.3580245 conf/cceai/2023 db/conf/cceai/cceai2023.html#LiLY23 Pandeng Li Chen-Wei Xie Liming Zhao Hongtao Xie 0001 Jiannan Ge Yun Zheng Deli Zhao Yongdong Zhang 0001 Progressive Spatio-Temporal Prototype Matching for Text-Video Retrieval. 4077-4087 2023 ICCV https://doi.org/10.1109/ICCV51070.2023.00379 conf/iccv/2023 db/conf/iccv/iccv2023.html#LiXZXGZZ023 Wanting Yin Hongtao Xie 0001 Lei Zhang 0119 Jiannan Ge Pandeng Li Chuanbin Liu 0001 Yongdong Zhang 0001 Frequency-based Zero-Shot Learning with Phase Augmentation. 3181-3189 2023 ACM Multimedia https://doi.org/10.1145/3581783.3611990 conf/mm/2023 db/conf/mm/mm2023.html#YinXZGLL023 Yan Jiang Hongtao Xie 0001 Lei Zhang 0119 Pandeng Li Dongming Zhang 0004 Yongdong Zhang 0001 Dual Dynamic Proxy Hashing Network for Long-tailed Image Retrieval. 8942-8953 2023 ACM Multimedia https://doi.org/10.1145/3581783.3612328 conf/mm/2023 db/conf/mm/mm2023.html#JiangXZLZZ23 Pandeng Li Chen-Wei Xie Hongtao Xie 0001 Liming Zhao Lei Zhang 0119 Yun Zheng Deli Zhao Yongdong Zhang 0001 MomentDiff: Generative Video Moment Retrieval from Random to Real. 2023 NeurIPS http://papers.nips.cc/paper_files/paper/2023/hash/d01bda31bbcd780774ff15b534e03c40-Abstract-Conference.html conf/nips/2023 db/conf/nips/neurips2023.html#LiXXZZZZ023

Pandeng Li Chen-Wei Xie Hongtao Xie 0001 Liming Zhao Lei Zhang 0119 Yun Zheng Deli Zhao Yongdong Zhang 0001 MomentDiff: Generative Video Moment Retrieval from Random to Real. 2023 abs/2307.02869 CoRR https://doi.org/10.48550/arXiv.2307.02869 db/journals/corr/corr2307.html#abs-2307-02869

Tianhao Qi Hongtao Xie 0001 Pandeng Li Jiannan Ge Yongdong Zhang 0001 Balanced Classification: A Unified Framework for Long-Tailed Object Detection. 2023 abs/2308.02213 CoRR https://doi.org/10.48550/arXiv.2308.02213 db/journals/corr/corr2308.html#abs-2308-02213

Pandeng Li Hongtao Xie 0001 Jiannan Ge Lei Zhang 0119 Shaobo Min Yongdong Zhang 0001 Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval. 2023 abs/2310.08009 CoRR https://doi.org/10.48550/arXiv.2310.08009 db/journals/corr/corr2310.html#abs-2310-08009

Zhihang Liu Jun Li Hongtao Xie 0001 Pandeng Li Jiannan Ge Sun'ao Liu Guoqing Jin Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval. 2023 abs/2312.12155 CoRR https://doi.org/10.48550/arXiv.2312.12155 db/journals/corr/corr2312.html#abs-2312-12155

Pandeng Li Hongtao Xie 0001 Shaobo Min Jiannan Ge Xun Chen 0001 Yongdong Zhang 0001 Deep Fourier Ranking Quantization for Semi-Supervised Image Retrieval. 5909-5922 2022 31 IEEE Trans. Image Process. https://doi.org/10.1109/TIP.2022.3203612 db/journals/tip/tip31.html#LiXMGCZ22

Pandeng Li Hongtao Xie 0001 Shaobo Min Zheng-Jun Zha Yongdong Zhang 0001 Online Residual Quantization Via Streaming Data Correlation Preserving. 981-994 2022 24 IEEE Trans. Multim. https://doi.org/10.1109/TMM.2021.3062480 db/journals/tmm/tmm24.html#LiXMZZ22

Pandeng Li Yan Li 0068 Hongtao Xie 0001 Lei Zhang 0119 Neighborhood-Adaptive Structure Augmented Metric Learning. 1367-1375 2022 AAAI https://doi.org/10.1609/aaai.v36i2.20025 conf/aaai/2022 db/conf/aaai/aaai2022.html#LiLXZ22 Pandeng Li Hongtao Xie 0001 Jiannan Ge Lei Zhang 0119 Shaobo Min Yongdong Zhang 0001 Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval. 181-197 2022 ECCV (14) https://doi.org/10.1007/978-3-031-19781-9_11 conf/eccv/2022-14 db/conf/eccv/eccv2022-14.html#LiXGZMZ22 Jiannan Ge Hongtao Xie 0001 Shaobo Min Pandeng Li Yongdong Zhang 0001 Dual Part Discovery Network for Zero-Shot Learning. 3244-3252 2022 ACM Multimedia https://doi.org/10.1145/3503161.3547889 conf/mm/2022 db/conf/mm/mm2022.html#GeXML022 Baole Ai Xiaoyi Bao Yuxiang Bao Zoubin Bi Binghui Chen Di Chen Jixuan Chen Xun Chen 0001 Zhaoyu Chen 0001 Xinhua Cheng Ruihang Chu Xuran Deng Tao Fang Mengyang Feng Ruili Feng Yutong Feng Zuan Gao Jiannan Ge Tianyi Gui Zhen Han Junjie He Yefei He Yuntao Hong Lianghua Huang Xiaoming Huang Yitong Huang Kaixun Jiang Yan Jiang Zeyinzi Jiang Guoqing Jin Yan Kou Jun Li Peishuo Li Quanhao Li Yan Li 0068 Yang Li 0197 Yifei Li Yinglu Li Yong Li 0045 Chen Liang Zhaohe Liao Wei Lin 0016 Zhiwei Lin Chuanbin Liu 0001 Sun-Ao Liu Sun'ao Liu Xihui Liu Yijing Liu Yizhi Liu Yu Liu Yu Liu 0015 Zhihang Liu Ziyu Liu Xudong Lu Yangyu Lv Shuailei Ma Chaojie Mao Xiaofeng Meng 0001 Shaobo Min Yulin Pan Jinwei Qi Tianhao Qi Tong Shen Wenting Shen Xianzhong Shi Yupeng Shi Siyang Sun Hao Tang 0005 Longxiang Tang Yehui Tang 0002 Qi Tian 0001 Ang Wang Haiyang Wang Jiayu Wang Jinkai Wang Liwei Wang 0001 Tianxing Wang 0006 Wei Wang Wei Wang 0354 Wei Wang 0377 Wente Wang Yiming Wang 0011 Yuzheng Wang Yujie Wei 0001 Bin Wen Tingyu Weng Pingyu Wu You Wu Zhi-Fan Wu Zuxuan Wu Chen-Wei Xie Chenwei Xie Hongtao Xie 0001 Lingxi Xie Zhen Xing Xin Xu Junchi Yan Keyu Yan Jianxiao Yang Nianzu Yang Wanting Yin Cheng Yu Feiwu Yu Hong-Tao Yu Junqiu Yu Wenyuan Yu Jianyuan Zeng Zhengjun ZhaZheng-Jun Zha Bang Zhang Boqiang Zhang Dongming Zhang 0004 Jingfeng Zhang Lei Zhang 0119 Ningyi Zhang Peng Zhang Shiwei Zhang 0001 Wenqiang Zhang Wenyuan Zhang Xiaopeng Zhang 0008 Yingya Zhang Yongdong Zhang 0001Yong-Dong Zhang 0001 Deli Zhao Haiming Zhao Kang Zhao Liming Zhao Yun Zheng Chongyang Zhong Jingren Zhou 0001 Junjie Zhou Wenmeng Zhou Kai Zhu 0004