Nikolaos Gkanatsios

Most-cited papers

1. 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations

   Tsung-Wei Ke, Nikolaos Gkanatsios, Katerina Fragkiadaki

   2024Conference on Robot Learning427 citations

   Semantic Scholar

   Save

2. Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation

   Théophile Gervet, Zhou Xian, Nikolaos Gkanatsios, Katerina Fragkiadaki

   2023Conference on Robot Learning217 citations

   Semantic Scholar

   Save

3. Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds

   Ayush Jain, Nikolaos Gkanatsios, Ishita Mediratta, Katerina Fragkiadaki

   2021European Conference on Computer Vision191 citations Open access

   Semantic Scholar

   Save

4. ChainedDiffuser: Unifying Trajectory Diffusion and Keypose Prediction for Robotic Manipulation

   Zhou Xian, Nikolaos Gkanatsios, Théophile Gervet, Tsung-Wei Ke +1 more

   2023Conference on Robot Learning169 citations

   Semantic Scholar

   Save

5. Diffusion-ES: Gradient-Free Planning with Diffusion for Autonomous and Instruction-Guided Driving

   Brian Yang, Huangyuan Su, Nikolaos Gkanatsios, Tsung-Wei Ke +3 more

   2024Computer Vision and Pattern Recognition83 citations

   Semantic Scholar

   Save

6. Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following

   Brian Yang, Huangyuan Su, Nikolaos Gkanatsios, Tsung-Wei Ke +3 more

   2024arXiv.org61 citations

   Semantic Scholar

   Save

7. Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement

   Nikolaos Gkanatsios, Ayush Jain, Zhou Xian, Yunchu Zhang +2 more

   2023Robotics: Science and Systems Conference50 citations Open access

   Semantic Scholar

   Save

8. ODIN: A Single Model for 2D and 3D Segmentation

   Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley +4 more

   2024Computer Vision and Pattern Recognition38 citations Open access

   Semantic Scholar

   Save

9. 3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation

   Nikolaos Gkanatsios, Jia-He Xu, Matthew Bronars, A. Mousavian +2 more

   2025arXiv.org30 citations

   Semantic Scholar

   Save

10. Looking Outside the Box to Ground Language in 3D Scenes

    Ayush Jain, Nikolaos Gkanatsios, Ishita Mediratta, Katerina Fragkiadaki

    202110 citations

    Semantic Scholar

    Save

11. ODIN: A Single Model for 2D and 3D Perception

    Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley +4 more

    2024arXiv.org7 citations

    Semantic Scholar

    Save

12. Embodied Symbiotic Assistants that See, Act, Infer and Chat

    Yuchen Cao, Nilay Pande, Ayush Jain, Shikhar Sharma +4 more

    20236 citations

    Semantic Scholar

    Save

13. Analogy-Forming Transformers for Few-Shot 3D Parsing

    Nikolaos Gkanatsios, M. Singh, Zhaoyuan Fang, Shubham Tulsiani +1 more

    2023International Conference on Learning Representations2 citations Open access

    Semantic Scholar

    Save

14. GeomVLA: Unifying Scene, Motion, and Action in 3D

    Zi-Yin Xiong, Nikolaos Gkanatsios, Moritz Reuss, Katerina Fragkiadaki

    20261 citations

    Semantic Scholar

    Save

15. Energy-based Models as Zero-Shot Planners for Compositional Scene Rearrangement

    Nikolaos Gkanatsios, Ayush Jain, Zhou Xian, Yunchu Zhang +2 more

    2023arXiv.org1 citations Open access

    Semantic Scholar

    Save

16. ODIN: A Single Model for 2D and 3D Segmentation Supplementary Materials

    Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley +4 more

    0 citations

    Semantic Scholar

    Save

17. Learning Distributional Models for Relative Placement in Robotics

    Jenny Wang, David Held, Oliver Kroemer, Shubham Tulsiani +1 more

    0 citations

    Semantic Scholar

    Save