Katerina Fragkiadaki

収録論文 35本 ・ フィジカルAI/ロボット学習

※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。

論文

• Tactile Genesis: Exploring Tactile Sensors at Scale for Learning Dexterous Tasks
  2026/6/1
• Solving Physics Olympiad via Reinforcement Learning on Physics Simulators
  2026/4/1
• Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning
  2026/3/1
• Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation
  2026/2/1
• Iterative Refinement Improves Compositional Image Generation
  2026/1/1
• RoboTAG: End-to-end Robot Configuration Estimation via Topological Alignment Graph
  2025/11/1
• RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation
  2025/10/27
• RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation
  2025/10/1
• 3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation
  2025/8/1
• Diffusion Beats Autoregressive in Data-Constrained Settings
  2025/7/1
• Unified Multimodal Discrete Diffusion
  2025/3/1
• Unifying 2D and 3D Vision-Language Understanding
  2025/3/1
• Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations
  2024/8/1
• Video Diffusion Alignment via Reward Gradients
  2024/7/1
• Tractable Joint Prediction and Planning over Discrete Behavior Modes for Urban Driving
  2024/3/1
• 3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
  2024/2/1
• Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following
  2024/2/1
• ODIN: A Single Model for 2D and 3D Segmentation
  2024/1/1
• RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation
  2023/11/1
• Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback
  2023/11/1
• Aligning Text-to-Image Diffusion Models with Reward Backpropagation
  2023/10/1
• Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models
  2023/10/1
• Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models
  2023/10/1
• Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation
  2023/6/1
• Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement
  2023/4/1
• FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation
  2023/3/1
• Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation
  2022/10/1
• Test-time Adaptation with Slot-Centric Models
  2022/3/1
• HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks
  2021/3/1
• 3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators
  2020/11/1
• Embodied Language Grounding with 3D Visual Feature Representations
  2019/10/1
• Graph-Structured Visual Imitation
  2019/7/1
• Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions
  2018/11/1
• Model Learning for Look-ahead Exploration in Continuous Control
  2018/11/1
• Reward Learning from Narrated Demonstrations
  2018/4/1