# NVIDIA at CoRL and Humanoids 2025 September 27 - October 2 COEX Convention & Exhibition Center Seoul, Korea ## Discover What’s Possible With NVIDIA Robotics The [Conference on Robot Learning (CoRL)](https://www.corl.org/) and [IEEE-RAS Humanoids](https://2025humanoids.org/) are premier international events advancing the frontiers of robotics, machine learning, and intelligent humanoid systems. Explore the work to see how [NVIDIA Research](https://www.nvidia.com/en-us/research/robotics.md) is accelerating breakthroughs in AI-powered robotics. ## Featured Talks **Monday, September 29, 1:45 p.m. KST** ### Keynote: Accelerating the Path to Generalist Humanoid Robots For researchers advancing the field of robot learning, generalization, and adaptive control, the emergence of highly capable humanoid platforms represents profound new opportunities, as well as unique challenges. NVIDIA is building the Isaac™ GR00T open platform for developing humanoid robots to meet these opportunities. Isaac GR00T consists of four parts: robot foundation models for cognition and control, simulation frameworks built on NVIDIA Omniverse™ and Cosmos™, data pipelines for generating synthetic data and environments, and the NVIDIA® Jetson AGX Thor™ supercomputer. This talk will introduce our latest research progress on building the Isaac GR00T foundation models and present new updates with the platform. [Learn More](https://www.corl.org/program/diamond-sponsor-talks) **Tuesday, September 30, 11:30 a.m-12:30 p.m. KST** ### CoRL 2025: Humanoid Robot Learning Industry Panel NVIDIA’s Scott Reed joins leading practitioners and researchers in humanoid robotics for a panel on the challenges, trends, and opportunities of deploying learning-based systems in real-world environments. [Learn More](https://www.corl.org/program/special-panel) **Wednesday, October 1, 5:30–6:30 p.m. KST** ### Humanoids 2025: Industry Panel Discussion NVIDIA’s Spencer Huang will join leading figures in industrial robotics to share their insights on the future of human life with robots and the outlook for the robotics industry. [Learn More](https://2025humanoids.org/industry-panel-discussion/) ## NVIDIA Research at CoRL and Humanoids 1. Papers 2. Workshops NVIDIA’s accepted papers and workshops at CoRL and Humanoids 2025 feature a range of groundbreaking research in the field of robotics. From humanoids to policy, explore the work NVIDIA is bringing to the CoRL and Humanoids community. #### [Fail2Progress: Learning From Real-World Robot Failures With Stein Variational Inference](https://www.arxiv.org/abs/2509.01746) Yixuan Huang, Novella Alvina, Mohanraj Devendran Shanthi, Tucker Hermans --- #### [VT-Refine: Learning Bimanual Assembly With Visuo-Tactile Feedback via Simulation Fine-Tuning](https://openreview.net/pdf/f39062bff2833d275cf322a3d675773e421776b2.pdf) Binghao Huang, Jie Xu, Iretiayo Akinola, Wei Yang, Balakumar Sundaralingam, Rowland O'Flaherty, Dieter Fox, Xiaolong Wang, Arsalan Mousavian, Yu-Wei Chao, Yunzhu Li --- #### [Neural Robot Dynamics](https://arxiv.org/abs/2508.15755) Jie Xu, Eric Heiden, Iretiayo Akinola, Dieter Fox, Miles Macklin, Yashraj Narang --- #### [FLARE: Robot Learning With Implicit World Modeling](https://arxiv.org/abs/2505.15659) Ruijie Zheng, Jing Wang, Scott Reed, Johan Bjorck, Yu Fang, Fengyuan Hu, Joel Jang, Kaushil Kundalia, Zongyu Lin, Loic Magne, Avnish Narayan, You Liang Tan, Guanzhi Wang, Qi Wang, Jiannan Xiang, Yinzhen Xu, Seonghyeon Ye, Jan Kautz, Furong Huang, Yuke Zhu, Linxi Fan --- #### [DreamGen: Unlocking Generalization in Robot Learning With Video World Models](https://arxiv.org/abs/2505.12705) Joel Jang, Seonghyeon Ye, Zongyu Lin, Jiannan Xiang, Johan Bjorck, Yu Fang, Fengyuan Hu, Spencer Huang, Kaushil Kundalia, Yen-Chen Lin, Loic Magne, Ajay Mandlekar, Avnish Narayan, You Liang Tan, Guanzhi Wang, Jing Wang, Qi Wang, Yinzhen Xu, Xiaohui Zeng, Kaiyuan Zheng, Ruijie Zheng, Ming-Yu Liu, Luke Zettlemoyer, Dieter Fox, Jan Kautz, Scott Reed, Yuke Zhu, Linxi Fan --- #### [Learning Deployable Locomotion Control via Differentiable Simulation](https://arxiv.org/abs/2404.02887) Clemens Schwarke, Victor Klemm, Joshua Bagajo, Jean-Pierre Sleiman, Ignat Georgiev, Jesus Tordesillas, Marco Hutter --- #### [Pseudo-Simulation for Autonomous Driving](https://arxiv.org/abs/2506.04218) Wei Cao, Marcel Hallgarten, Tianyu Li, Daniel Dauner, Xunjiang Gu, Caojun Wang, Yakov Miron, Marco Aiello, Hongyang Li, Igor Gilitschenski, Boris Ivanovic, Marco Pavone, Andreas Geiger, Kashyap Chitta --- #### [CaRL: Learning Scalable Planning Policies With Simple Rewards](https://arxiv.org/abs/2504.17838) Bernhard Jaeger, Daniel Dauner, Jens Beißwenger, Simon Gerstenecker, Kashyap Chitta, Andreas Geiger --- #### [Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning](https://arxiv.org/abs/2505.10547) Milan Ganai, Rohan Sinha, Christopher Agia, Daniel Morton, Marco Pavone --- #### [Sim2Val: Leveraging Correlation Across Test Platforms for Variance-Reduced Metric Estimation](https://www.arxiv.org/abs/2506.20553) Rachel Luo, Heng Yang, Michael Watson, Apoorva Sharma, Sushant Veer, Edward Schmerling, Marco Pavone --- #### [CUPID: Curating Data Your Robot Loves With Influence Functions](https://arxiv.org/abs/2506.19121) Christopher Agia, Rohan Sinha, Jingyun Yang, Rika Antonova, Marco Pavone, Haruki Nishimura, Masha Itkina, Jeannette Bohg --- #### [RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models](https://arxiv.org/abs/2506.17811) Jacky Kwok, Christopher Agia, Rohan Sinha, Matt Foutter, Shulu Li, Ion Stoica, Azalia Mirhoseini, Marco Pavone --- #### [Divide, Discover, Deploy: Factorized Skill Learning With Symmetry and Style Priors](https://arxiv.org/abs/2508.19953) Rafael Cathomen, Mayank Mittal, Marin Vlastelica, Marco Hutter --- #### [Dexplore: Scalable Neural Control for Dexterous Manipulation From Reference-Scoped Exploration](https://arxiv.org/abs/2509.09671) Sirui Xu, Yu-Wei Chao, Liuyu Bian, Arsalan Mousavian, Yu-Xiong Wang, Liang-Yan Gui, Wei Yang --- #### [Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids](https://arxiv.org/abs/2502.20396) Toru Lin, Kartik Sachdev, Linxi Fan, Jitendra Malik, Yuke Zhu --- #### [DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation](https://arxiv.org/abs/2505.21864) Mengda Xu, Han Zhang, Yifan Hou, Zhenjia Xu, Linxi Fan, Manuela Veloso, Shuran Song --- Load More Load Less ### Saturday, September 27 #### [Evaluation and Deployment Across the Robot Learning Lifecycle](https://eval-deploy.github.io/) Explore scalable, reproducible robot evaluation and safe deployment strategies that connect researchers tackling real-world challenges in robotics performance, monitoring, and lifecycle design. --- #### [Making Sense of Data in Robotics: Composition, Curation, and Interpretability at Scale](https://sites.google.com/stanford.edu/corldata25/home) Connect with experts shaping the future of robot learning data—tackling composition, curation, and interpretability to drive more robust, scalable, and trustworthy robotics research. --- #### [2nd Workshop on Safe and Robust Robot Learning for Operation in the Real World](https://sites.google.com/view/corl-2025-safe-rol-workshop) Advance safe and reliable robot learning at CoRL 2025 by joining experts focused on data curation, generalization, and rigorous validation methods for trustworthy real-world applications. --- #### [Resource-Rational Robot Learning](https://rational-robots.github.io/) Drive the shift toward resource-rational robot learning by addressing trade-offs in compute, simulation, and human feedback to ensure that robot systems are efficient, scalable, and practical for real-world deployment. --- #### [Robotics World Modeling](https://robot-world-modeling.github.io/) This workshop unites researchers to explore how advances in world models can enable more robust, generalizable robotics, focusing on combining visual and physical understanding, leveraging pre-trained models, and integrating learning with physics priors. --- ### Thursday, October 2 #### [Bridging Humanoid Robotics and Foundation Models: Embodied Intelligence and AI Integration](https://humanoids-x-fm-2025.github.io/) This workshop examines how foundation models can transform humanoid robots’ perception, reasoning, and interaction to chart a path toward generalizable, human-aligned systems. --- #### [Can We Build Baymax?](https://baymax.org/workshop/2025/) This workshop will bring together robotics researchers working on robots like Baymax, including HRI, sensing, compliant hardware, and internal humanoid structures. --- #### [Sim-to-Real Transfer for Humanoid Robots](https://arxiv.org/abs/2505.12705) Discover specific engineering and algorithmic decisions that make robust sim-to-real transfer possible. Through talks and discussions, we’ll share practical insights and foster collaboration among researchers and industry practitioners tackling this challenge. We’ll also share lessons from real deployments to help accelerate the development of capable, real-world humanoid robots. --- Load More Load Less ### Turn Your Research into a Startup Join Launching Legends at CoRL to transform your technological advancements into a world-changing startup. Connect with a supportive network of venture capital investors, industry mentors, and NVIDIA partners to launch your own company at this premier event. [RSVP For Launching Legends](https://events.nvidia.com/launchinglegendsatcorl) ## Our Ecosystem Partners ## NVIDIA Research Learn about NVIDIA Research and our passion for developing ‌technology and finding breakthroughs that bring positive change to the world. Beyond publishing our work in papers and at conferences, we apply it to NVIDIA solutions and services, share resources and code, and offer hands-on experiences with technical demos. [Explore Here](https://www.nvidia.com/en-us/research/robotics.md) ## NVIDIA Solutions for Robotics ### Robotics The NVIDIA Isaac™ platform accelerates the development of AI-driven robots, streamlining processes from design and simulation to deployment. It enables key functions like navigation, mobility, grasping, and vision, supporting robotics across industries such as manufacturing, agriculture, logistics, and healthcare. [Explore Robotics](https://www.nvidia.com/en-us/industries/robotics.md) ### Vision AI The NVIDIA Metropolis platform simplifies the development, deployment, and scaling of visual AI agents from edge to cloud. These agents enhance operational efficiency, worker productivity, and safety in manufacturing, warehousing, logistics, and retail. [Explore Vision AI](https://www.nvidia.com/en-us/autonomous-machines/intelligent-video-analytics-platform.md) ### Edge AI NVIDIA brings the power of AI to edge devices, processing data at the source to provide actionable, real-time insights. This enhances decision-making, improves services, and streamlines operations, while boosting security and reducing costs through local processing. [Learn About Edge AI](https://www.nvidia.com/en-us/edge-computing.md) ## Like No Place You’ve Ever Worked Working at NVIDIA, you’ll solve some of the world’s hardest problems and discover never-before-seen ways to improve the quality of life for people everywhere. From healthcare to robots, self-driving cars to blockbuster movies, you’ll experience it all. Plus, there’s a growing list of new opportunities every single day. Explore all of our open roles, including internships and new college graduate positions. Learn more about our current job openings, as well as university jobs. [Explore Here](https://nvidia.wd5.myworkdayjobs.com/NVIDIAExternalCareerSite?source=eventcorl2025) Get the latest Robotics news, technologies, breakthroughs, and more sent straight to your inbox. [Stay Informed](#stay-inf)