pith. sign in

arxiv: 2606.24101 · v1 · pith:CO5Z4ETQnew · submitted 2026-06-23 · 💻 cs.RO · cs.CV

NavWM: A Unified Navigation World Model for Foresight-Driven Planning

Yanghong Mei , Longteng Guo , Ming-Ming Yu , Guiyu Zhao , Xingjian He , Jing Liu This is my paper

Pith reviewed 2026-06-26 00:40 UTC · model grok-4.3

classification 💻 cs.RO cs.CV
keywords navigation world modellatent world tokensmultimodal trajectory forecastingvisual foresightclosed-loop plannerzero-shot navigationrobotics datasets
0
0 comments X

The pith

NavWM unifies perception, generation and control into one world model that uses visual foresight for closed-loop navigation planning.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes NavWM to fix myopic decisions and mode collapse in visual navigation by bringing perception, future-state generation and action selection into a single framework. Latent world tokens capture geometric and semantic structure while an anchor-based forecasting step produces multiple possible trajectories instead of one deterministic path. The resulting model generates controllable future images that let the agent evaluate options and pick the best one inside a closed loop. Experiments on multiple robotics datasets report gains in accurate future-state prediction and in zero-shot success rates on unseen navigation tasks.

Core claim

NavWM is a unified navigation world model that integrates latent world reasoning, multimodal action prediction and controllable visual generation. It distills geometric and semantic priors into latent world tokens and employs an anchor-based multimodal trajectory forecasting framework to create a diverse action space. This diversity allows the generative world model to serve as a robust closed-loop planner that evaluates candidate paths through visual foresight and selects the optimal one.

What carries the argument

Latent world tokens that distill geometric and semantic priors, together with an anchor-based multimodal trajectory forecasting framework that produces diverse candidate actions.

If this is right

  • The model produces higher-fidelity future visual states than isolated generation pipelines.
  • Diverse trajectory forecasting removes the mode-collapse problem of deterministic policies.
  • Visual foresight inside the loop raises zero-shot navigation success across multiple robotics datasets.
  • The closed-loop planner evaluates paths directly from generated images rather than from separate policy outputs.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same token-plus-forecast structure could be tested on manipulation or locomotion tasks that also need long-horizon visual prediction.
  • Controllable generation might let the planner adapt online when the environment changes after the initial forecast.
  • If the latent tokens already encode geometry, the model might support sim-to-real transfer with less additional fine-tuning than separate perception and planning stacks.

Load-bearing premise

Isolating perception, generation and control is the primary reason navigation policies fail, and unifying them through shared latent tokens will capture the missing spatio-temporal dynamics.

What would settle it

If the reported experiments on the robotics datasets showed no measurable improvement in future-state prediction fidelity or zero-shot navigation success compared with prior separate-component methods, the unification claim would be falsified.

Figures

Figures reproduced from arXiv: 2606.24101 by Guiyu Zhao, Jing Liu, Longteng Guo, Ming-Ming Yu, Xingjian He, Yanghong Mei.

Figure 1
Figure 1. Figure 1: Comparison of world model paradigms. (a) Decoupled world and action models. (b) A unified world model with independent outputs. (c) Our NavWM integrates latent world reasoning and multimodal actions, enabling the world model to act as a planner via visual foresight. existing methods model action prediction as a single trajectory, collapsing the multi-modal action space into one mode. Consequently, the pred… view at source ↗
Figure 2
Figure 2. Figure 2: Overview of the NavWM framework. The unified navigation world model learns latent scene abstractions from historical observations and goals via latent world reasoning, supervised by depth and semantic predictions. It then proposes multimodal trajectory hypotheses and predicts future observations through world modeling, enabling closed-loop navigation planing via visual foresight. Layer to compress the enco… view at source ↗
Figure 3
Figure 3. Figure 3: Qualitative comparison across indoor and outdoor environments. Left: Trajectory plots illustrating the alignment of predicted paths from different methods with the Ground Truth (GT). Right: Visual generation results of camera viewpoint control during navigation. 4.1.2 Evaluation Metrics. For the offline evaluation of the navigation policy, we employ Absolute Trajectory Error (ATE) and Relative Pose Error (… view at source ↗
Figure 4
Figure 4. Figure 4: Training stage ablation. Performing stage two fine-tuning significantly improves image reconstruc￾tion quality. To answer Q1, we conduct module ablation study on the latent world reasoning, action prediction, and world model, with the quantitative results summarized in ta￾ble 3. To assess the raw multimodal policy, we compute metrics directly on probabilistically sampled trajectories without world model pl… view at source ↗
Figure 5
Figure 5. Figure 5: Navigation performance vs. candidate trajectory count (K). NavWM shows sustained gains up to K ≈ 7, outperforming Diffusion (K ≈ 5) and GMM (earliest saturation), balancing diversity and accuracy. navigation performance. Furthermore, we observe that these performance gains are significantly more pronounced for our anchor-based multimodal prediction compared to the GMM and diffusion-based NoMaD baselines. T… view at source ↗
read the original abstract

Conventional visual navigation policies often struggle with myopic decision-making and mode collapse in complex environments. While world models offer a promising alternative, existing paradigms typically isolate perception, generation, and control, failing to capture their shared spatio-temporal dynamics. In this paper, we propose NavWM, a unified navigation world model that seamlessly integrates latent world reasoning, multimodal action prediction, and controllable visual generation. At its core, NavWM leverages latent world tokens to distill geometric and semantic priors, endowing the agent with robust structural understanding. To overcome the limitations of deterministic policies, we introduce an anchor-based multimodal trajectory forecasting framework that generates a diverse action space. This inherent diversity explicitly empowers the generative world model to act as a robust closed-loop planner, utilizing visual foresight to evaluate and select the optimal path. Extensive experiments across diverse robotics datasets demonstrate that NavWM significantly advances the state-of-the-art, delivering remarkable improvements in both high-fidelity future state generation and zero-shot navigation success.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper proposes NavWM, a unified navigation world model that integrates latent world reasoning (via latent world tokens distilling geometric and semantic priors), multimodal action prediction (via anchor-based multimodal trajectory forecasting for diverse action spaces), and controllable visual generation to enable foresight-driven closed-loop planning. It claims this addresses myopic decision-making and mode collapse in conventional policies by capturing shared spatio-temporal dynamics, with extensive experiments on diverse robotics datasets demonstrating significant SOTA advances in high-fidelity future state generation and zero-shot navigation success.

Significance. If the unification and claimed performance gains hold, the work could advance world-model approaches in robotics by providing a more integrated framework for perception, generation, and control, potentially yielding more robust planners than isolated-component paradigms.

major comments (1)
  1. [Abstract] Abstract: the central claim that 'extensive experiments across diverse robotics datasets demonstrate that NavWM significantly advances the state-of-the-art, delivering remarkable improvements in both high-fidelity future state generation and zero-shot navigation success' supplies no quantitative results, baselines, ablation studies, error analysis, or tables, rendering the SOTA assertion unverifiable from the manuscript.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their comment on the abstract. We address it point-by-point below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that 'extensive experiments across diverse robotics datasets demonstrate that NavWM significantly advances the state-of-the-art, delivering remarkable improvements in both high-fidelity future state generation and zero-shot navigation success' supplies no quantitative results, baselines, ablation studies, error analysis, or tables, rendering the SOTA assertion unverifiable from the manuscript.

    Authors: We agree that the abstract, being a high-level summary, does not embed specific numerical results, which can make the SOTA claim harder to verify at first reading. The full manuscript contains the supporting quantitative evidence, including baseline comparisons, ablation studies, and error analyses with tables and figures in the experiments section. To strengthen verifiability, we will revise the abstract to include key quantitative highlights from our results (e.g., specific navigation success rates and generation metrics) while preserving its conciseness. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The provided abstract and context describe NavWM as a novel architectural integration of latent world tokens, multimodal trajectory forecasting, and visual foresight for closed-loop planning. No equations, derivations, fitted parameters, or self-citations are presented that reduce any claimed prediction or result to its own inputs by construction. The unification argument and SOTA claims rest on experimental outcomes rather than definitional or self-referential steps. This is the expected outcome for a high-level architectural paper without visible load-bearing reductions.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no explicit free parameters, axioms, or invented entities can be extracted or audited.

pith-pipeline@v0.9.1-grok · 5709 in / 966 out tokens · 34829 ms · 2026-06-26T00:40:33.024182+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

54 extracted references · 10 linked inside Pith

  1. [1]

    Gnm: A general navigation model to drive any robot.arXiv preprint arXiv:2210.03370, 2022

    Dhruv Shah, Ajay Sridhar, Arjun Bhorkar, Noriaki Hirose, and Sergey Levine. Gnm: A general navigation model to drive any robot.arXiv preprint arXiv:2210.03370, 2022

    arXiv 2022

  2. [2]

    Vint: A foundation model for visual navigation.arXiv preprint arXiv:2306.14846, 2023

    Dhruv Shah, Ajay Sridhar, Nitish Dashora, Kyle Stachowicz, Kevin Black, Noriaki Hirose, and Sergey Levine. Vint: A foundation model for visual navigation.arXiv preprint arXiv:2306.14846, 2023

    arXiv 2023

  3. [3]

    Nomad: Goal masked diffusion policies for navigation and exploration

    Ajay Sridhar, Dhruv Shah, Catherine Glossop, and Sergey Levine. Nomad: Goal masked diffusion policies for navigation and exploration. In2024 IEEE International Conference on Robotics and Automation (ICRA), pages 63–70. IEEE, 2024. 10

    2024

  4. [4]

    Citywalker: Learning embodied urban navigation from web-scale videos

    Xinhao Liu, Jintong Li, Yicheng Jiang, Niranjan Sujay, Zhicheng Yang, Juexiao Zhang, John Abanes, Jing Zhang, and Chen Feng. Citywalker: Learning embodied urban navigation from web-scale videos. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 6875–6885, 2025

    2025

  5. [5]

    Navigation world models

    Amir Bar, Gaoyue Zhou, Danny Tran, Trevor Darrell, and Yann LeCun. Navigation world models. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 15791–15801, 2025

    2025

  6. [6]

    Urbannav: Learning language-guided urban navigation from web-scale human trajectories.arXiv preprint arXiv:2512.09607, 2025

    Yanghong Mei, Yirong Yang, Longteng Guo, Qunbo Wang, Ming-Ming Yu, Xingjian He, Wenjun Wu, and Jing Liu. Urbannav: Learning language-guided urban navigation from web-scale human trajectories.arXiv preprint arXiv:2512.09607, 2025

    arXiv 2025

  7. [7]

    Navigating to objects in the real world.Science Robotics, 8(79):eadf6991, 2023

    Theophile Gervet, Soumith Chintala, Dhruv Batra, Jitendra Malik, and Devendra Singh Chaplot. Navigating to objects in the real world.Science Robotics, 8(79):eadf6991, 2023

    2023

  8. [8]

    A survey on diffusion policy for robotic manipulation: Taxonomy, analysis, and future directions.Authorea Preprints, 2025

    Mingchen Song, Xiang Deng, Zhiling Zhou, Jie Wei, Weili Guan, and Liqiang Nie. A survey on diffusion policy for robotic manipulation: Taxonomy, analysis, and future directions.Authorea Preprints, 2025

    2025

  9. [9]

    Navcot: Boosting llm-based vision-and-language navigation via learning disentangled reasoning

    Bingqian Lin, Yunshuang Nie, Ziming Wei, Jiaqi Chen, Shikui Ma, Jianhua Han, Hang Xu, Xiaojun Chang, and Xiaodan Liang. Navcot: Boosting llm-based vision-and-language navigation via learning disentangled reasoning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

    2025

  10. [10]

    Astranav-world: World model for foresight control and consistency.arXiv preprint arXiv:2512.21714, 2025

    Junjun Hu, Jintao Chen, Haochen Bai, Minghua Luo, Shichao Xie, Ziyi Chen, Fei Liu, Zedong Chu, Xinda Xue, Botao Ren, et al. Astranav-world: World model for foresight control and consistency.arXiv preprint arXiv:2512.21714, 2025

    Pith/arXiv arXiv 2025

  11. [11]

    Unified world models: Memory-augmented planning and foresight for visual navigation.arXiv preprint arXiv:2510.08713, 2025

    Yifei Dong, Fengyi Wu, Guangyu Chen, Zhi-Qi Cheng, Qiyu Hu, Yuxuan Zhou, Jingdong Sun, Jun-Yan He, Qi Dai, and Alexander G Hauptmann. Unified world models: Memory-augmented planning and foresight for visual navigation.arXiv preprint arXiv:2510.08713, 2025

    arXiv 2025

  12. [12]

    Diffusion policy: Visuomotor policy learning via action diffusion.The International Journal of Robotics Research, 44(10-11):1684–1704, 2025

    Cheng Chi, Zhenjia Xu, Siyuan Feng, Eric Cousineau, Yilun Du, Benjamin Burchfiel, Russ Tedrake, and Shuran Song. Diffusion policy: Visuomotor policy learning via action diffusion.The International Journal of Robotics Research, 44(10-11):1684–1704, 2025

    2025

  13. [13]

    Densetnt: End-to-end trajectory prediction from dense goal sets

    Junru Gu, Chen Sun, and Hang Zhao. Densetnt: End-to-end trajectory prediction from dense goal sets. In Proceedings of the IEEE/CVF international conference on computer vision, pages 15303–15312, 2021

    2021

  14. [14]

    Tnt: Target-driven trajectory prediction

    Hang Zhao, Jiyang Gao, Tian Lan, Chen Sun, Ben Sapp, Balakrishnan Varadarajan, Yue Shen, Yi Shen, Yuning Chai, Cordelia Schmid, et al. Tnt: Target-driven trajectory prediction. InConference on robot learning, pages 895–904. PMLR, 2021

    2021

  15. [15]

    Gonet: A semi- supervised deep learning approach for traversability estimation

    Noriaki Hirose, Amir Sadeghian, Marynel Vázquez, Patrick Goebel, and Silvio Savarese. Gonet: A semi- supervised deep learning approach for traversability estimation. In2018 IEEE/RSJ international conference on intelligent robots and systems (IROS), pages 3044–3051. IEEE, 2018

    2018

  16. [16]

    Socially compliant navigation dataset (scand): A large-scale dataset of demonstrations for social navigation.IEEE Robotics and Automation Letters, 7(4):11807–11814, 2022

    Haresh Karnan, Anirudh Nair, Xuesu Xiao, Garrett Warnell, Sören Pirk, Alexander Toshev, Justin Hart, Joydeep Biswas, and Peter Stone. Socially compliant navigation dataset (scand): A large-scale dataset of demonstrations for social navigation.IEEE Robotics and Automation Letters, 7(4):11807–11814, 2022

    2022

  17. [17]

    Rapid exploration for open-world navigation with latent goal models.arXiv preprint arXiv:2104.05859, 2021

    Dhruv Shah, Benjamin Eysenbach, Gregory Kahn, Nicholas Rhinehart, and Sergey Levine. Rapid exploration for open-world navigation with latent goal models.arXiv preprint arXiv:2104.05859, 2021

    arXiv 2021

  18. [18]

    Sacson: Scalable autonomous control for social navigation.IEEE Robotics and Automation Letters, 9(1):49–56, 2023

    Noriaki Hirose, Dhruv Shah, Ajay Sridhar, and Sergey Levine. Sacson: Scalable autonomous control for social navigation.IEEE Robotics and Automation Letters, 9(1):49–56, 2023

    2023

  19. [19]

    Tartandrive: A large-scale dataset for learning off-road dynamics models

    Samuel Triest, Matthew Sivaprakasam, Sean J Wang, Wenshan Wang, Aaron M Johnson, and Sebastian Scherer. Tartandrive: A large-scale dataset for learning off-road dynamics models. In2022 International Conference on Robotics and Automation (ICRA), pages 2546–2552. IEEE, 2022

    2022

  20. [20]

    Learning to explore using active neural slam.arXiv preprint arXiv:2004.05155, 2020

    Devendra Singh Chaplot, Dhiraj Gandhi, Saurabh Gupta, Abhinav Gupta, and Ruslan Salakhutdinov. Learning to explore using active neural slam.arXiv preprint arXiv:2004.05155, 2020

    arXiv 2004

  21. [21]

    Lavira: Language-vision-robot actions translation for zero-shot vision language navigation in continuous environments.arXiv preprint arXiv:2510.19655, 2025

    Hongyu Ding, Ziming Xu, Yudong Fang, You Wu, Zixuan Chen, Jieqi Shi, Jing Huo, Yifan Zhang, and Yang Gao. Lavira: Language-vision-robot actions translation for zero-shot vision language navigation in continuous environments.arXiv preprint arXiv:2510.19655, 2025

    arXiv 2025

  22. [22]

    Fast traversabil- ity estimation for wild visual navigation.arXiv preprint arXiv:2305.08510, 2023

    Jonas Frey, Matias Mattamala, Nived Chebrolu, Cesar Cadena, Maurice Fallon, and Marco Hutter. Fast traversabil- ity estimation for wild visual navigation.arXiv preprint arXiv:2305.08510, 2023

    arXiv 2023

  23. [23]

    Unigoal: Towards universal zero-shot goal-oriented navigation

    Hang Yin, Xiuwei Xu, Linqing Zhao, Ziwei Wang, Jie Zhou, and Jiwen Lu. Unigoal: Towards universal zero-shot goal-oriented navigation. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 19057–19066, 2025. 11

    2025

  24. [24]

    C-nav: Towards self-evolving continual object navigation in open world.arXiv preprint arXiv:2510.20685, 2025

    Ming-Ming Yu, Fei Zhu, Wenzhuo Liu, Yirong Yang, Qunbo Wang, Wenjun Wu, and Jing Liu. C-nav: Towards self-evolving continual object navigation in open world.arXiv preprint arXiv:2510.20685, 2025

    Pith/arXiv arXiv 2025

  25. [25]

    World models.arXiv preprint arXiv:1803.10122, 2(3), 2018

    David Ha and Jürgen Schmidhuber. World models.arXiv preprint arXiv:1803.10122, 2(3), 2018

    Pith/arXiv arXiv 2018

  26. [26]

    Self-supervised learning from images with a joint-embedding predictive architecture

    Mahmoud Assran, Quentin Duval, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael Rabbat, Yann LeCun, and Nicolas Ballas. Self-supervised learning from images with a joint-embedding predictive architecture. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 15619–15629, 2023

    2023

  27. [27]

    Video generation models as world simulators.OpenAI Blog, 1(8):1, 2024

    Tim Brooks, Bill Peebles, Connor Holmes, Will DePue, Yufei Guo, Leo Jing, David Schnurr, Joe Taylor, Troy Luhman, Eric Luhman, et al. Video generation models as world simulators.OpenAI Blog, 1(8):1, 2024

    2024

  28. [28]

    Genie: Generative interactive environments

    Jake Bruce, Michael D Dennis, Ashley Edwards, Jack Parker-Holder, Yuge Shi, Edward Hughes, Matthew Lai, Aditi Mavalankar, Richie Steigerwald, Chris Apps, et al. Genie: Generative interactive environments. InForty-first International Conference on Machine Learning, 2024

    2024

  29. [29]

    Cosmos world foundation model platform for physical ai.arXiv preprint arXiv:2501.03575, 2025

    Niket Agarwal, Arslan Ali, Maciej Bala, Yogesh Balaji, Erik Barker, Tiffany Cai, Prithvijit Chattopadhyay, Yongxin Chen, Yin Cui, Yifan Ding, et al. Cosmos world foundation model platform for physical ai.arXiv preprint arXiv:2501.03575, 2025

    Pith/arXiv arXiv 2025

  30. [30]

    I2vcontrol-camera: Precise video camera control with adjustable motion strength.arXiv preprint arXiv:2411.06525, 2024

    Wanquan Feng, Jiawei Liu, Pengqi Tu, Tianhao Qi, Mingzhen Sun, Tianxiang Ma, Songtao Zhao, Siyu Zhou, and Qian He. I2vcontrol-camera: Precise video camera control with adjustable motion strength.arXiv preprint arXiv:2411.06525, 2024

    arXiv 2024

  31. [31]

    Cameractrl: Enabling camera control for text-to-video generation.arXiv preprint arXiv:2404.02101, 2024

    Hao He, Yinghao Xu, Yuwei Guo, Gordon Wetzstein, Bo Dai, Hongsheng Li, and Ceyuan Yang. Cameractrl: Enabling camera control for text-to-video generation.arXiv preprint arXiv:2404.02101, 2024

    Pith/arXiv arXiv 2024

  32. [32]

    Cameractrl ii: Dynamic scene exploration via camera-controlled video diffusion models

    Hao He, Ceyuan Yang, Shanchuan Lin, Yinghao Xu, Meng Wei, Liangke Gui, Qi Zhao, Gordon Wetzstein, Lu Jiang, and Hongsheng Li. Cameractrl ii: Dynamic scene exploration via camera-controlled video diffusion models. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 13416–13426, 2025

    2025

  33. [33]

    Navmorph: A self-evolving world model for vision-and-language navigation in continuous environments

    Xuan Yao, Junyu Gao, and Changsheng Xu. Navmorph: A self-evolving world model for vision-and-language navigation in continuous environments. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 5536–5546, 2025

    2025

  34. [34]

    Stable video diffusion: Scaling latent video diffusion models to large datasets.arXiv preprint arXiv:2311.15127, 2023

    Andreas Blattmann, Tim Dockhorn, Sumith Kulal, Daniel Mendelevitch, Maciej Kilian, Dominik Lorenz, Yam Levi, Zion English, Vikram V oleti, Adam Letts, et al. Stable video diffusion: Scaling latent video diffusion models to large datasets.arXiv preprint arXiv:2311.15127, 2023

    Pith/arXiv arXiv 2023

  35. [35]

    Mamba: Linear-time sequence modeling with selective state spaces

    Albert Gu and Tri Dao. Mamba: Linear-time sequence modeling with selective state spaces. InFirst conference on language modeling, 2024

    2024

  36. [36]

    Depth anything v2.Advances in Neural Information Processing Systems, 37:21875–21911, 2024

    Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. Depth anything v2.Advances in Neural Information Processing Systems, 37:21875–21911, 2024

    2024

  37. [37]

    Segment anything

    Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C Berg, Wan-Yen Lo, et al. Segment anything. InProceedings of the IEEE/CVF international conference on computer vision, pages 4015–4026, 2023

    2023

  38. [38]

    Depth map prediction from a single image using a multi-scale deep network.Advances in neural information processing systems, 27, 2014

    David Eigen, Christian Puhrsch, and Rob Fergus. Depth map prediction from a single image using a multi-scale deep network.Advances in neural information processing systems, 27, 2014

    2014

  39. [39]

    Multimodal trajectory predictions for autonomous driving using deep convolu- tional networks

    Henggang Cui, Vladan Radosavljevic, Fang-Chieh Chou, Tsung-Han Lin, Thi Nguyen, Tzu-Kuo Huang, Jeff Schneider, and Nemanja Djuric. Multimodal trajectory predictions for autonomous driving using deep convolu- tional networks. In2019 international conference on robotics and automation (icra), pages 2090–2096. IEEE, 2019

    2090

  40. [40]

    Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction.arXiv preprint arXiv:1910.05449, 2019

    Yuning Chai, Benjamin Sapp, Mayank Bansal, and Dragomir Anguelov. Multipath: Multiple probabilistic anchor trajectory hypotheses for behavior prediction.arXiv preprint arXiv:1910.05449, 2019

    arXiv 1910

  41. [41]

    It is not the journey but the destination: Endpoint conditioned trajectory prediction

    Karttikeya Mangalam, Harshayu Girase, Shreyas Agarwal, Kuan-Hui Lee, Ehsan Adeli, Jitendra Malik, and Adrien Gaidon. It is not the journey but the destination: Endpoint conditioned trajectory prediction. InEuropean conference on computer vision, pages 759–776. Springer, 2020

    2020

  42. [42]

    Scalable diffusion models with transformers

    William Peebles and Saining Xie. Scalable diffusion models with transformers. InProceedings of the IEEE/CVF international conference on computer vision, pages 4195–4205, 2023

    2023

  43. [43]

    Light field networks: Neural scene representations with single-evaluation rendering.Advances in Neural Information Processing Systems, 34:19313–19325, 2021

    Vincent Sitzmann, Semon Rezchikov, Bill Freeman, Josh Tenenbaum, and Fredo Durand. Light field networks: Neural scene representations with single-evaluation rendering.Advances in Neural Information Processing Systems, 34:19313–19325, 2021. 12

    2021

  44. [44]

    Understanding and improving layer normalization.Advances in neural information processing systems, 32, 2019

    Jingjing Xu, Xu Sun, Zhiyuan Zhang, Guangxiang Zhao, and Junyang Lin. Understanding and improving layer normalization.Advances in neural information processing systems, 32, 2019

    2019

  45. [45]

    Flow straight and fast: Learning to generate and transfer data with rectified flow.arXiv preprint arXiv:2209.03003, 2022

    Xingchao Liu, Chengyue Gong, and Qiang Liu. Flow straight and fast: Learning to generate and transfer data with rectified flow.arXiv preprint arXiv:2209.03003, 2022

    Pith/arXiv arXiv 2022

  46. [46]

    Flow matching for generative modeling.arXiv preprint arXiv:2210.02747, 2022

    Yaron Lipman, Ricky TQ Chen, Heli Ben-Hamu, Maximilian Nickel, and Matt Le. Flow matching for generative modeling.arXiv preprint arXiv:2210.02747, 2022

    Pith/arXiv arXiv 2022

  47. [47]

    Diffusion for world modeling: Visual details matter in atari.Advances in Neural Information Processing Systems, 37:58757–58791, 2024

    Eloi Alonso, Adam Jelley, Vincent Micheli, Anssi Kanervisto, Amos J Storkey, Tim Pearce, and François Fleuret. Diffusion for world modeling: Visual details matter in atari.Advances in Neural Information Processing Systems, 37:58757–58791, 2024

    2024

  48. [48]

    Anole: An open, autoregressive, native large multimodal models for interleaved image-text generation.arXiv preprint arXiv:2407.06135, 2024

    Ethan Chern, Jiadi Su, Yan Ma, and Pengfei Liu. Anole: An open, autoregressive, native large multimodal models for interleaved image-text generation.arXiv preprint arXiv:2407.06135, 2024

    arXiv 2024

  49. [49]

    Multi-task learning using uncertainty to weigh losses for scene geometry and semantics

    Alex Kendall, Yarin Gal, and Roberto Cipolla. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 7482–7491, 2018

    2018

  50. [50]

    Evaluating egomotion and structure-from-motion ap- proaches using the tum rgb-d benchmark

    Jürgen Sturm, Wolfram Burgard, and Daniel Cremers. Evaluating egomotion and structure-from-motion ap- proaches using the tum rgb-d benchmark. InProc. of the Workshop on Color-Depth Camera Fusion in Robotics at the IEEE/RJS International Conference on Intelligent Robot Systems (IROS), volume 13, page 6, 2012

    2012

  51. [51]

    Image quality assessment: from error visibility to structural similarity.IEEE transactions on image processing, 13(4):600–612, 2004

    Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. Image quality assessment: from error visibility to structural similarity.IEEE transactions on image processing, 13(4):600–612, 2004

    2004

  52. [52]

    The unreasonable effectiveness of deep features as a perceptual metric

    Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shechtman, and Oliver Wang. The unreasonable effectiveness of deep features as a perceptual metric. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 586–595, 2018

    2018

  53. [53]

    Dream- sim: Learning new dimensions of human visual similarity using synthetic data.arXiv preprint arXiv:2306.09344, 2023

    Stephanie Fu, Netanel Tamir, Shobhita Sundaram, Lucy Chai, Richard Zhang, Tali Dekel, and Phillip Isola. Dream- sim: Learning new dimensions of human visual similarity using synthetic data.arXiv preprint arXiv:2306.09344, 2023

    Pith/arXiv arXiv 2023

  54. [54]

    Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101, 2017

    Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101, 2017. 13

    Pith/arXiv arXiv 2017