{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:04:41Z","timestamp":1784228681577,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811038","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GPC: Large-Scale Generative Pretraining for Transferable Motor Control"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3360-6706","authenticated-orcid":false,"given":"Yi","family":"Shi","sequence":"first","affiliation":[{"name":"NVIDIA, Santa Clara, USA and Simon Fraser University, Burnaby, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2063-8903","authenticated-orcid":false,"given":"Yifeng","family":"Jiang","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6447-9864","authenticated-orcid":false,"given":"Chen","family":"Tessler","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3677-5655","authenticated-orcid":false,"given":"Xue Bin","family":"Peng","sequence":"additional","affiliation":[{"name":"NVIDIA, Vancouver, Canada and Simon Fraser University, Burnaby, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00527"},{"key":"e_1_3_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730637"},{"key":"e_1_3_3_2_4_1","doi-asserted-by":"publisher","unstructured":"Jinseok Bae Jungdam Won Donggeun Lim Inwoo Hwang and Young\u00a0Min Kim. 2025b. Versatile Physics-based Character Control with Hybrid Latent Representation. Computer Graphics Forum (2025). 10.1111\/cgf.70018","DOI":"10.1111\/cgf.70018"},{"key":"e_1_3_3_2_5_1","unstructured":"Alexei Baevski Steffen Schneider and Michael Auli. 2020. vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations. arxiv:https:\/\/arXiv.org\/abs\/1910.05453\u00a0[cs.CL]"},{"key":"e_1_3_3_2_6_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023. Qwen Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2309.16609\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2309.16609"},{"key":"e_1_3_3_2_7_1","unstructured":"Yoshua Bengio Nicolas L\u00e9onard and Aaron Courville. 2013. Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1308.3432 (2013)."},{"key":"e_1_3_3_2_8_1","unstructured":"Bones Studio. 2026. BONES-SEED: Skeletal Everyday Embodied Dataset. https:\/\/bones.studio\/datasets."},{"key":"e_1_3_3_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3274247.3274506"},{"key":"e_1_3_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1457515.1409066"},{"key":"e_1_3_3_2_11_1","doi-asserted-by":"crossref","unstructured":"Marco da Silva Yeuhi Abe and Jovan Popovi\u0107. 2008. Simulation of Human Motion Data Using Short-Horizon Model-Predictive Control. Computer Graphics Forum 27 2 (2008) 371\u2013380.","DOI":"10.1111\/j.1467-8659.2008.01134.x"},{"key":"e_1_3_3_2_12_1","doi-asserted-by":"crossref","unstructured":"Tim Dettmers Artidoro Pagnoni Ari Holtzman and Luke Zettlemoyer. 2023. QLoRA: Efficient Finetuning of Quantized LLMs. arxiv:https:\/\/arXiv.org\/abs\/2305.14314\u00a0[cs.LG]","DOI":"10.52202\/075280-0441"},{"key":"e_1_3_3_2_13_1","unstructured":"Zhiyang Dou Xuelin Chen Qingnan Fan Taku Komura and Wenping Wang. 2023. C\u00b7ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters. (2023). arxiv:https:\/\/arXiv.org\/abs\/2309.11351"},{"key":"e_1_3_3_2_14_1","doi-asserted-by":"crossref","unstructured":"Patrick Esser Robin Rombach and Bj\u00f6rn Ommer. 2021. Taming Transformers for High-Resolution Image Synthesis. arxiv:https:\/\/arXiv.org\/abs\/2012.09841\u00a0[cs.CV]","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_3_2_15_1","unstructured":"Ian\u00a0J. Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative Adversarial Networks. arxiv:https:\/\/arXiv.org\/abs\/1406.2661\u00a0[stat.ML]"},{"key":"e_1_3_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"e_1_3_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/218380.218414"},{"key":"e_1_3_3_2_18_1","unstructured":"Ari Holtzman Jan Buys Li Du Maxwell Forbes and Yejin Choi. 2020. The Curious Case of Neural Text Degeneration. arxiv:https:\/\/arXiv.org\/abs\/1904.09751\u00a0[cs.CL]"},{"key":"e_1_3_3_2_19_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin de Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-Efficient Transfer Learning for NLP. In Proceedings of the 36th International Conference on Machine Learning (ICML)."},{"key":"e_1_3_3_2_20_1","unstructured":"Edward\u00a0J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2021. LoRA: Low-Rank Adaptation of Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2106.09685\u00a0[cs.CL]"},{"key":"e_1_3_3_2_21_1","doi-asserted-by":"crossref","unstructured":"Xiaoyu Huang Takara Truong Yunbo Zhang Fangzhou Yu Jean\u00a0Pierre Sleiman Jessica Hodgins Koushil Sreenath and Farbod Farshidian. 2025. Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control. ACM Transactions on Graphics (TOG) 44 4 (2025) 1\u201313. SIGGRAPH 2025.","DOI":"10.1145\/3731206"},{"key":"e_1_3_3_2_22_1","doi-asserted-by":"crossref","unstructured":"Biao Jiang Xin Chen Wen Liu Jingyi Yu Gang Yu and Tao Chen. 2023. Motiongpt: Human motion as a foreign language. Advances in Neural Information Processing Systems 36 (2023) 20067\u201320079.","DOI":"10.52202\/075280-0880"},{"key":"e_1_3_3_2_23_1","unstructured":"Yoon Kim Yacine Jernite David Sontag and Alexander\u00a0M. Rush. 2015. Character-Aware Neural Language Models. arxiv:https:\/\/arXiv.org\/abs\/1508.06615\u00a0[cs.CL]"},{"key":"e_1_3_3_2_24_1","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2022. Auto-Encoding Variational Bayes. arxiv:https:\/\/arXiv.org\/abs\/1312.6114\u00a0[stat.ML]"},{"key":"e_1_3_3_2_25_1","unstructured":"Shih-Yang Liu Chien-Yi Wang Hongxu Yin Pavlo Molchanov Yu-Chiang\u00a0Frank Wang Kwang-Ting Cheng and Min-Hung Chen. 2024. DoRA: Weight-Decomposed Low-Rank Adaptation. arxiv:https:\/\/arXiv.org\/abs\/2402.09353\u00a0[cs.CL]"},{"key":"e_1_3_3_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01000"},{"key":"e_1_3_3_2_27_1","unstructured":"Zhengyi Luo Jinkun Cao Josh Merel Alexander Winkler Jing Huang Kris Kitani and Weipeng Xu. 2024. Universal Humanoid Motion Representations for Physics-Based Control. arxiv:https:\/\/arXiv.org\/abs\/2310.04582\u00a0[cs.CV]"},{"key":"e_1_3_3_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"e_1_3_3_2_29_1","unstructured":"Viktor Makoviychuk Lukasz Wawrzyniak Yunrong Guo Michelle Lu Kier Storey Miles Macklin David Hoeller Nikita Rudin Arthur Allshire Ankur Handa and Gavriel State. 2021. Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning. arxiv:https:\/\/arXiv.org\/abs\/2108.10470\u00a0[cs.RO]"},{"key":"e_1_3_3_2_30_1","unstructured":"Fabian Mentzer David Minnen Eirikur Agustsson and Michael Tschannen. 2023. Finite Scalar Quantization: VQ-VAE Made Simple. arxiv:https:\/\/arXiv.org\/abs\/2309.15505\u00a0[cs.CV]"},{"key":"e_1_3_3_2_31_1","unstructured":"Josh Merel Leonard Hasenclever Alexandre Galashov Arun Ahuja Vu Pham Greg Wayne Yee\u00a0Whye Teh and Nicolas Heess. 2019. Neural probabilistic motor primitives for humanoid control. arxiv:https:\/\/arXiv.org\/abs\/1811.11711\u00a0[cs.LG]"},{"key":"e_1_3_3_2_32_1","doi-asserted-by":"crossref","unstructured":"Xue\u00a0Bin Peng Pieter Abbeel Sergey Levine and Michiel Van\u00a0de Panne. 2018. Deepmimic: Example-guided deep reinforcement learning of physics-based character skills. ACM Transactions On Graphics (TOG) 37 4 (2018) 1\u201314.","DOI":"10.1145\/3197517.3201311"},{"key":"e_1_3_3_2_33_1","doi-asserted-by":"crossref","unstructured":"Xue\u00a0Bin Peng Glen Berseth KangKang Yin and Michiel Van De\u00a0Panne. 2017. Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning. Acm transactions on graphics (tog) 36 4 (2017) 1\u201313.","DOI":"10.1145\/3072959.3073602"},{"key":"e_1_3_3_2_34_1","doi-asserted-by":"crossref","unstructured":"Xue\u00a0Bin Peng Yunrong Guo Lina Halper Sergey Levine and Sanja Fidler. 2022. Ase: Large-scale reusable adversarial skill embeddings for physically simulated characters. ACM Transactions On Graphics (TOG) 41 4 (2022) 1\u201317.","DOI":"10.1145\/3528223.3530110"},{"key":"e_1_3_3_2_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"e_1_3_3_2_36_1","doi-asserted-by":"crossref","unstructured":"Jonas Pfeiffer Aishwarya Kamath Andreas R\u00fcckl\u00e9 Kyunghyun Cho and Iryna Gurevych. 2021. AdapterFusion: Non-Destructive Task Composition for Transfer Learning. arxiv:https:\/\/arXiv.org\/abs\/2005.00247\u00a0[cs.CL]","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"e_1_3_3_2_37_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving Language Understanding by Generative Pre-Training. OpenAI technical report."},{"key":"e_1_3_3_2_38_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"e_1_3_3_2_40_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1707.06347 (2017)."},{"key":"e_1_3_3_2_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"e_1_3_3_2_42_1","doi-asserted-by":"crossref","unstructured":"Sebastian Starke Paul Starke Nicky He Taku Komura and Yuting Ye. 2024. Categorical codebook matching for embodied character controllers. ACM Transactions on Graphics (TOG) 43 4 (2024) 1\u201314.","DOI":"10.1145\/3658209"},{"key":"e_1_3_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_3_2_44_1","doi-asserted-by":"crossref","unstructured":"Chen Tessler Yunrong Guo Ofir Nabati Gal Chechik and Xue\u00a0Bin Peng. 2024. MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting. ACM Transactions on Graphics (TOG) (2024).","DOI":"10.1145\/3687951"},{"key":"e_1_3_3_2_45_1","unstructured":"Chen Tessler Yifeng Jiang Xue\u00a0Bin Peng Erwin Coumans Yi Shi Haotian Zhang Davis Rempe Gal Chechik\u2020 and Sanja Fidler. 2025. ProtoMotions3: An Open-source Framework for Humanoid Simulation and Control. https:\/\/github.com\/NVLabs\/ProtoMotions\/."},{"key":"e_1_3_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591541"},{"key":"e_1_3_3_2_47_1","unstructured":"Guy Tevet Sigal Raab Setareh Cohan Daniele Reda Zhengyi Luo Xue\u00a0Bin Peng Amit\u00a0H Bermano and Michiel van\u00a0de Panne. 2024. Closd: Closing the loop between simulation and diffusion for multi-task character control. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.03441 (2024)."},{"key":"e_1_3_3_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687683"},{"key":"e_1_3_3_2_49_1","unstructured":"Aaron van\u00a0den Oord Oriol Vinyals and Koray Kavukcuoglu. 2018. Neural Discrete Representation Learning. arxiv:https:\/\/arXiv.org\/abs\/1711.00937\u00a0[cs.LG]"},{"key":"e_1_3_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00075"},{"key":"e_1_3_3_2_51_1","doi-asserted-by":"crossref","unstructured":"Jungdam Won Deepak Gopinath and Jessica Hodgins. 2022. Physics-based Character Controllers Using Conditional VAEs. ACM Trans. Graph. 41 4 Article 96 (2022).","DOI":"10.1145\/3528223.3530067"},{"key":"e_1_3_3_2_52_1","doi-asserted-by":"publisher","unstructured":"Jungdam Won and Jehee Lee. 2019. Learning body shape variation in physics-based characters. ACM Transactions on Graphics (TOG) 38 6 (2019) 1\u201312. 10.1145\/3355089.3356499","DOI":"10.1145\/3355089.3356499"},{"key":"e_1_3_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730616"},{"key":"e_1_3_3_2_54_1","doi-asserted-by":"crossref","unstructured":"Heyuan Yao Zhenhua Song Yuyang Zhou Tenglong Ao Baoquan Chen and Libin Liu. 2024. Moconvq: Unified physics-based motion control via scalable discrete representations. ACM Transactions on Graphics (TOG) 43 4 (2024) 1\u201321.","DOI":"10.1145\/3658137"},{"key":"e_1_3_3_2_55_1","doi-asserted-by":"crossref","unstructured":"Yuting Ye and C.\u00a0Karen Liu. 2010. Optimal feedback control for character animation using an abstract model. ACM Trans. Graph. 29 4 Article 74 (July 2010) 9\u00a0pages.","DOI":"10.1145\/1778765.1778811"},{"key":"e_1_3_3_2_56_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Ye Yuan","year":"2023","unstructured":"Yuan Ye, Jiaming Song, Umar Iqbal, Arash Vahdat, and Jan Kautz. 2023. PhysDiff: Physics-Guided Human Motion Diffusion Model. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_3_2_57_1","doi-asserted-by":"crossref","unstructured":"KangKang Yin Kevin Loken and Michiel Van\u00a0de Panne. 2007. Simbicon: Simple biped locomotion control. ACM Transactions on Graphics (TOG) 26 3 (2007) 105\u2013es.","DOI":"10.1145\/1276377.1276509"},{"key":"e_1_3_3_2_58_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023b. Adding Conditional Control to Text-to-Image Diffusion Models.","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_2_59_1","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zhang Qingru","year":"2023","unstructured":"Qingru Zhang, Minshuo Chen, Alexander Bukharin, Pengcheng He, Yu Cheng, Weizhu Chen, and Tuo Zhao. 2023a. Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763819"},{"key":"e_1_3_3_2_61_1","doi-asserted-by":"crossref","unstructured":"Qingxu Zhu He Zhang Mengting Lan and Lei Han. 2023. Neural categorical priors for physics-based character control. ACM Transactions on Graphics (TOG) 42 6 (2023) 1\u201316.","DOI":"10.1145\/3618397"}],"event":{"name":"SIGGRAPH Conference Papers '26: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Los Angeles CA USA","acronym":"SIGGRAPH Conference Papers '26","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:14:00Z","timestamp":1784225640000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811038"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":60,"alternative-id":["10.1145\/3799902.3811038","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811038","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}