{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:48:12Z","timestamp":1791686892100,"version":"4.3.4"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172073"],"award-info":[{"award-number":["62172073"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872224"],"award-info":[{"award-number":["61872224"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025207"],"award-info":[{"award-number":["62025207"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFA1003002"],"award-info":[{"award-number":["2021YFA1003002"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109461","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T15:20:40Z","timestamp":1785770440000},"page":"109461","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["JointConn-v2: Learning a joint vector field with diffusion transformers for cross-modal connectivity and dual-timestep modeling"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6531-9142","authenticated-orcid":false,"given":"Honggang","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Jun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109461_bib0001","series-title":"International conference on machine learning","first-page":"1692","article-title":"One transformer fits all distributions in multi-modal diffusion at scale","author":"Bao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109461_bib0002","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18392","article-title":"Instructpix2pix: Learning to follow image editing instructions","author":"Brooks","year":"2023"},{"key":"10.1016\/j.neunet.2026.109461_bib0003","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"25261","article-title":"Jointdit: Enhancing rgb-depth joint modeling with diffusion transformers","author":"Byung-Ki","year":"2025"},{"key":"10.1016\/j.neunet.2026.109461_bib0004","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"22560","article-title":"Masactrl: Tuning-free mutual self-attention control for consistent image synthesis and editing","author":"Cao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109461_bib0005","unstructured":"Chefer, H., Esser, P., Lorenz, D., Podell, D., Raja, V., Tong, V., Torralba, A., & Rombach, R. (2026). Self-supervised flow matching for scalable multi-modal synthesis. arXiv preprint arXiv: 2603.06507."},{"key":"10.1016\/j.neunet.2026.109461_bib0006","doi-asserted-by":"crossref","first-page":"24081","DOI":"10.52202\/079017-0759","article-title":"Diffusion forcing: Next-token prediction meets full-sequence diffusion","volume":"37","author":"Chen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109461_bib0007","first-page":"6571","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109461_bib0008","series-title":"Forty-first international conference on machine learning","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"10.1016\/j.neunet.2026.109461_bib0009","doi-asserted-by":"crossref","first-page":"27199","DOI":"10.52202\/075280-1185","article-title":"Addressing negative transfer in diffusion models","volume":"36","author":"Go","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109461_bib0010","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"13743","article-title":"Plug-and-play diffusion distillation","author":"Hsiao","year":"2024"},{"issue":"2","key":"10.1016\/j.neunet.2026.109461_bib0011","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"10.1016\/j.neunet.2026.109461_bib0012","series-title":"2021\u202fIEEE International conference on robotics and automation (ICRA)","first-page":"13656","article-title":"Penet: Towards precise and efficient image guided depth completion","author":"Hu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109461_bib0013","unstructured":"Hu, M., Zheng, C., Zheng, H., Cham, T.-J., Wang, C., Yang, Z., Tao, D., & Suganthan, P. N. (2022b). Unified discrete diffusion for simultaneous vision-language generation. arXiv preprint arXiv: 2211.14842."},{"key":"10.1016\/j.neunet.2026.109461_bib0014","unstructured":"Huang, L., Chen, D., Liu, Y., Shen, Y., Zhao, D., & Zhou, J. (2023). Composer: Creative and controllable image synthesis with composable conditions. arXiv preprint arXiv: 2302.09778."},{"key":"10.1016\/j.neunet.2026.109461_bib0015","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9492","article-title":"Repurposing diffusion-based image generators for monocular depth estimation","author":"Ke","year":"2024"},{"key":"10.1016\/j.neunet.2026.109461_bib0016","doi-asserted-by":"crossref","unstructured":"Krishnan, A., Yan, X., Casser, V., & Kundu, A. (2025). Orchid: Image latent diffusion for joint appearance and geometry generation. arXiv preprint arXiv: 2501.13087.","DOI":"10.1109\/ICCV51701.2025.02620"},{"key":"10.1016\/j.neunet.2026.109461_bib0017","first-page":"1","article-title":"Enhanced deep image prior for unsupervised hyperspectral image super-resolution","volume":"63","author":"Li","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109461_bib0018","first-page":"1","article-title":"Model-informed multistage unsupervised network for hyperspectral image super-resolution","volume":"62","author":"Li","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109461_bib0019","first-page":"1","article-title":"Model-guided coarse-to-fine fusion network for unsupervised hyperspectral image super-resolution","volume":"20","author":"Li","year":"2023","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"10.1016\/j.neunet.2026.109461_bib0020","series-title":"International conference on learning representations","first-page":"41705","article-title":"A simple approach to unifying diffusion-based conditional generation","volume":"vol. 2025","author":"Li","year":"2025"},{"key":"10.1016\/j.neunet.2026.109461_bib0021","unstructured":"Li, X., Herrmann, C., Chan, K. C. K., Li, Y., Sun, D., Ma, C., & Yang, M.-H. (2024b). A simple approach to unifying diffusion-based conditional generation. arXiv preprint arXiv: 2410.11439."},{"key":"10.1016\/j.neunet.2026.109461_bib0022","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"2779","article-title":"Dual diffusion for unified image generation and understanding","author":"Li","year":"2025"},{"key":"10.1016\/j.neunet.2026.109461_bib0023","unstructured":"Lin, H., Cho, J., Zala, A., & Bansal, M. (2024). Ctrl-adapter: An efficient and versatile framework for adapting diverse controls to any diffusion model. arXiv preprint arXiv: 2404.09967."},{"key":"10.1016\/j.neunet.2026.109461_bib0024","unstructured":"Lipman, Y., Chen, R. T. Q., Ben-Hamu, H., Nickel, M., & Le, M. (2022). Flow matching for generative modeling. arXiv preprint arXiv: 2210.02747."},{"key":"10.1016\/j.neunet.2026.109461_bib0025","unstructured":"Liu, X., Gong, C., & Liu, Q. (2022). Flow straight and fast: Learning to generate and transfer data with rectified flow. arXiv preprint arXiv: 2209.03003."},{"key":"10.1016\/j.neunet.2026.109461_bib0026","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"26439","article-title":"Unified-IO 2: Scaling autoregressive multimodal models with vision language audio and action","author":"Lu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109461_bib0027","unstructured":"Ma, Y., Yang, H., Wang, W., Fu, J., & Liu, J. (2023). Unified multi-modal latent diffusion for joint subject and text conditional image generation. arXiv preprint arXiv: 2303.09319."},{"key":"10.1016\/j.neunet.2026.109461_bib0028","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4296","article-title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models","volume":"vol. 38","author":"Mou","year":"2024"},{"issue":"285\u2013296","key":"10.1016\/j.neunet.2026.109461_bib0029","first-page":"23","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Otsu","year":"1975","journal-title":"Automatica"},{"key":"10.1016\/j.neunet.2026.109461_bib0030","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"4195","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2023"},{"key":"10.1016\/j.neunet.2026.109461_bib0031","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., & Rombach, R. (2023). Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv: 2307.01952."},{"key":"10.1016\/j.neunet.2026.109461_bib0032","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"15932","article-title":"Fatezero: Fusing attentions for zero-shot text-based video editing","author":"Qi","year":"2023"},{"key":"10.1016\/j.neunet.2026.109461_bib0033","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"issue":"3","key":"10.1016\/j.neunet.2026.109461_bib0034","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1109\/TPAMI.2020.3019967","article-title":"Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer","volume":"44","author":"Ranftl","year":"2020","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"10.1016\/j.neunet.2026.109461_bib0035","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.neunet.2026.109461_bib0036","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"9339","article-title":"Habitat: A platform for embodied ai research","author":"Savva","year":"2019"},{"key":"10.1016\/j.neunet.2026.109461_bib0037","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"8543","article-title":"Instantbooth: Personalized text-to-image generation without test-time finetuning","author":"Shi","year":"2024"},{"key":"10.1016\/j.neunet.2026.109461_bib0038","unstructured":"Stan, G. B. M., Wofk, D., Fox, S., Redden, A., Saxton, W., Yu, J., Aflalo, E., Tseng, S.-Y., Nonato, F., Muller, M. et al. (2023). LDM3D: Latent diffusion model for 3D. arXiv preprint arXiv: 2305.10853."},{"key":"10.1016\/j.neunet.2026.109461_bib0039","doi-asserted-by":"crossref","first-page":"16083","DOI":"10.52202\/075280-0707","article-title":"Any-to-any generation via composable diffusion","volume":"36","author":"Tang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109461_bib0040","unstructured":"Tong, A., Fatras, K., Malkin, N., Huguet, G., Zhang, Y., Rector-Brooks, J., Wolf, G., & Bengio, Y. (2023). Improving and generalizing flow-based generative models with minibatch optimal transport. arXiv preprint arXiv: 2302.00482."},{"issue":"12","key":"10.1016\/j.neunet.2026.109461_bib0041","doi-asserted-by":"crossref","first-page":"5929","DOI":"10.1007\/s11263-024-02168-7","article-title":"Exploiting diffusion prior for real-world image super-resolution","volume":"132","author":"Wang","year":"2024","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109461_bib0042","series-title":"European conference on computer vision","first-page":"399","article-title":"Dynamicrafter: Animating open-domain images with video diffusion priors","author":"Xing","year":"2024"},{"key":"10.1016\/j.neunet.2026.109461_bib0043","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"7754","article-title":"Versatile diffusion: Text, images and variations all in one diffusion model","author":"Xu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109461_bib0044","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1481","article-title":"Magicanimate: Temporally consistent human image animation using diffusion model","author":"Xu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109461_bib0045","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18381","article-title":"Paint by example: Exemplar-based image editing with diffusion models","author":"Yang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109461_bib0046","doi-asserted-by":"crossref","first-page":"21875","DOI":"10.52202\/079017-0688","article-title":"Depth anything v2","volume":"37","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109461_bib0047","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16227","article-title":"Holodeck: Language guided generation of 3D embodied ai environments","author":"Yang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109461_bib0048","doi-asserted-by":"crossref","first-page":"47455","DOI":"10.52202\/079017-1505","article-title":"Improved distribution matching distillation for fast image synthesis","volume":"37","author":"Yin","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109461_bib0049","series-title":"European conference on computer vision","first-page":"134","article-title":"Idol: Unified dual-modal latent diffusion for human-centric joint video-depth generation","author":"Zhai","year":"2024"},{"key":"10.1016\/j.neunet.2026.109461_bib0050","unstructured":"Zhang, J., Li, S., Lu, Y., Fang, T., McKinnon, D., Tsin, Y., Quan, L., & Yao, Y. (2023a). Jointnet: Extending text-to-image diffusion for dense distribution modeling. arXiv preprint arXiv: 2310.06347."},{"key":"10.1016\/j.neunet.2026.109461_bib0051","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3836","article-title":"Adding conditional control to text-to-image diffusion models","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109461_bib0052","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2023.104836","article-title":"Sde-rae: Clip-based realistic image reconstruction and editing network using stochastic differential diffusion","volume":"139","author":"Zhao","year":"2023","journal-title":"Image and Vision Computing"},{"key":"10.1016\/j.neunet.2026.109461_bib0053","doi-asserted-by":"crossref","first-page":"11127","DOI":"10.52202\/075280-0491","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","volume":"36","author":"Zhao","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"4","key":"10.1016\/j.neunet.2026.109461_bib0054","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3731167","article-title":"Sketch2anim: Towards transferring sketch storyboards into 3d animation","volume":"44","author":"Zhong","year":"2025","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"10.1016\/j.neunet.2026.109461_bib0055","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., & Wang, X. (2024). Vision mamba: Efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv: 2401.09417."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009196?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026009196?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:28:45Z","timestamp":1791685725000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026009196"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":55,"alternative-id":["S0893608026009196"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109461","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"JointConn-v2: Learning a joint vector field with diffusion transformers for cross-modal connectivity and dual-timestep modeling","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109461","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109461"}}