Katerina Fragkiadaki

Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning CVPR 2026 MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second CVPR 2026 RoboTAG: End-to-end Robot Pose Estimation via Topological Alignment Graph CVPR 2026 AllTracker: Efficient Dense Point Tracking at High Resolution ICCV 2025 Robust Multi-Object 4D Generation for In-the-wild Videos CVPR 2025 Unifying 2D and 3D Vision-Language Understanding ICML 2025 Video Depth without Video Models CVPR 2025 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations CoRL 2024 Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous and Instruction-guided Driving CVPR 2024 DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos NeurIPS 2024 ODIN: A Single Model for 2D and 3D Segmentation CVPR 2024 RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation ICML 2024 VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought NeurIPS 2024 Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation CoRL 2023 Analogy-Forming Transformers for Few-Shot 3D Parsing ICLR 2023 Brain Dissection: fMRI-trained Networks Reveal Spatial Selectivity in the Processing of Natural Images NeurIPS 2023 ChainedDiffuser: Unifying Trajectory Diffusion and Keypose Prediction for Robotic Manipulation CoRL 2023 Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback NeurIPS 2023 Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement RSS 2023 FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation ICLR 2023 Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models EMNLP 2023 Test-time Adaptation with Slot-Centric Models ICML 2023 Bottom Up Top down Detection Transformers for Language Grounding in Images and Point Clouds ECCV 2022 Particle Video Revisited: Tracking through Occlusions Using Point Trajectories ECCV 2022 Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation CoRL 2022 TIDEE: Tidying Up Novel Rooms Using Visuo-Semantic Commonsense Priors ECCV 2022 CoCoNets: Continuous Contrastive 3D Scene Representations CVPR 2021 Disentangling 3D Prototypical Networks for Few-Shot Concept Learning ICLR 2021 HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks ICLR 2021 Track, Check, Repeat: An EM Approach to Unsupervised Tracking CVPR 2021 Visually-Grounded Library of Behaviors for Manipulating Diverse Objects across Diverse Configurations and Views CoRL 2021 3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators CoRL 2020 Embodied Language Grounding With 3D Visual Feature Representations CVPR 2020 Epipolar Transformers CVPR 2020 Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D Mapping ICLR 2020 Tracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping ECCV 2020 Graph-Structured Visual Imitation CoRL 2019 Learning Spatial Common Sense With Geometry-Aware Recurrent Networks CVPR 2019 Model Learning for Look-Ahead Exploration in Continuous Control AAAI 2019 Geometry-Aware Recurrent Neural Networks for Active Visual Recognition NeurIPS 2018 Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions CoRL 2018 Reward Learning From Narrated Demonstrations CVPR 2018 Adversarial Inverse Graphics Networks: Learning 2D-To-3D Lifting and Image-To-Image Translation From Unpaired Supervision ICCV 2017 Self-supervised Learning of Motion Capture NeurIPS 2017 Human Pose Estimation With Iterative Error Feedback CVPR 2016 Learning to Segment Moving Objects in Videos CVPR 2015 Recurrent Network Models for Human Dynamics ICCV 2015 Grouping-Based Low-Rank Trajectory Completion and 3D Reconstruction NeurIPS 2014 Pose from Flow and Flow from Pose CVPR 2013