Jonathan Lorraine ![Jonathan Lorraine](/sites/default/files/person/nvr_headshot_2024_homepage.jpg) ### Publications ### 2026 [Addressable Memory for Video World Models](/index.php/publication/2026-08_addressable-memory-video-world-models) Xindi Wu, Sven Elflein, James Lucas, Olga Russakovsky, Laura Leal-Taixé, Despoina Paschalidou, [Jonathan Lorraine](/index.php/person/jonathan-lorraine), Aljoša Ošep [ICML](https://icml.cc/Conferences/2026) Best Paper, Oral — ICML 2026 F2S Workshop [NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation](/publication/2026-06_nvidia-omnidreams-real-time-generative-world-model-closed-loop-autonomous) Aarti Basant, Amlan Kar, Despoina Paschalidou, Fangyin Wei, [Francesco Ferroni](/person/francesco-ferroni), Guillermo Garcia Cobo, [Haithem Turki](/person/haithem-turki), Huan Ling, Jaewoo Seo, James Lucas, Jay Zhangjie Wu, [Jialiang Wang](/person/jialiang-wang), [Jonathan Lorraine](/person/jonathan-lorraine), Jun Gao, Kai He, Katarina Tothova, Kevin Xie, Michał Tyszkiewicz, Qi Wu, Riccardo de Lutio, Ruilong Li, Sanja Fidler, Seung Wook Kim, Tianchang Shen, Tianshi Cao, Tobias Pfaff, William Lew, Xindi Wu, Xuanchi Ren, Yifan Lu, Yuxuan Zhang, Zan Gojcic, Zian Wang [Variance Reduction for Expectations with Diffusion Teachers](/index.php/publication/2026-05_variance-reduction-expectations-diffusion-teachers) Jesse Bettencourt, Xindi Wu, Matan Atzmon, James Lucas, [Jonathan Lorraine](/index.php/person/jonathan-lorraine) [ICML](https://icml.cc/Conferences/2026) [Motion Attribution for Video Generation](/publication/2026-01_motion-attribution-video-generation) Xindi Wu, Despoina Paschalidou, Jun Gao, Antonio Torralba, Laura Leal-Taixé, Olga Russakovsky, Sanja Fidler, [Jonathan Lorraine](/person/jonathan-lorraine) [ICML](https://icml.cc/Conferences/2026) Oral, Outstanding Paper Honorable Mention ### 2025 [Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond](/index.php/publication/2025-05_score-distillation-sampling-audio-source-separation-synthesis-and-beyond) Jessie Richter-Powell, Antonio Torralba, [Jonathan Lorraine](/index.php/person/jonathan-lorraine) [ICML](https://icml.cc/Conferences/2025) [LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models](/publication/2025-03_llama-mesh-unifying-3d-mesh-generation-language-models) Zhengyi Wang, [Jonathan Lorraine](/person/jonathan-lorraine), Yikai Wang, [Hang Su](/person/hang-su), Jun Zhu, Sanja Fidler, Xiaohui Zeng [arXiv](https://arxiv.org/abs/2411.09595) [Multi-student Diffusion Distillation for Better One-step Generators](/index.php/publication/2025-03_multi-student-diffusion-distillation-better-one-step-generators) Yanke Song, [Jonathan Lorraine](/index.php/person/jonathan-lorraine), Weili Nie, [Karsten Kreis](/index.php/person/karsten-kreis), James Lucas [ICML](https://icml.cc/Conferences/2025) ### 2024 [JacNet: Learning Functions with Structured Jacobians](/publication/2024-08_jacnet-learning-functions-structured-jacobians) Jonathan Lorraine, Safwan Hossain [ICML](https://icml.cc/Conferences/2019) [Scalable Nested Optimization for Deep Learning](/publication/2024-07_scalable-nested-optimization-deep-learning) Jonathan Lorraine [Improving Hyperparameter Optimization with Checkpointed Model Weights](/index.php/publication/2024-06_improving-hyperparameter-optimization-checkpointed-model-weights) Nikhil Mehta, [Jonathan Lorraine](/index.php/person/jonathan-lorraine), Steve Masson, Ramanathan Arunachalam, Zaid Pervaiz Bhat, James Lucas, Arun George Zachariah [ECCV](https://eccv2024.ecva.net/Conferences/2024) [Training Data Attribution via Approximate Unrolled Differentiation](/publication/2024-05_training-data-attribution-approximate-unrolled-differentiation) Juhan Bae, Wu Lin, [Jonathan Lorraine](/person/jonathan-lorraine), Roger Grosse [NeurIPS](https://neurips.cc/Conferences/2024) [LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis](/publication/2024-03_latte3d-large-scale-amortized-text-enhanced3d-synthesis) Kevin Xie, [Jonathan Lorraine](/person/jonathan-lorraine), Tianshi Cao, Jun Gao, James Lucas, Antonio Torralba, Sanja Fidler, Xiaohui Zeng [ECCV](https://eccv2024.ecva.net/Conferences/2024) ### 2023 [Using Large Language Models for Hyperparameter Optimization](/publication/2023-12_using-large-language-models-hyperparameter-optimization) Michael R. Zhang, Nishkrit Desai, Juhan Bae, Jonathan Lorraine, Jimmy Ba [NeurIPS](https://neurips.cc/Conferences/2023) Oral [Graph Metanetworks for Processing Diverse Neural Architectures](/publication/2023-12_graph-metanetworks-processing-diverse-neural-architectures) Derek Lim, [Haggai Maron](/person/haggai-maron), Marc T. Law, [Jonathan Lorraine](/person/jonathan-lorraine), James Lucas [ICLR](https://iclr.cc/Conferences/2024) Spotlight [ATT3D: Amortized Text-To-3D Object Synthesis](/publication/2023-10_att3d-amortized-text-3d-object-synthesis) [Jonathan Lorraine](/person/jonathan-lorraine), Kevin Xie, Xiaohui Zeng, [Chen-Hsuan Lin](/person/chen-hsuan-lin), Towaki Takikawa, Nicholas Sharp, [Tsung-Yi Lin](/person/tsung-yi-lin), [Ming-Yu Liu](/person/ming-yu-liu), Sanja Fidler, James Lucas [ICCV](https://iccv2023.thecvf.com/)