KF
Katerina Fragkiadaki
cs.CVcs.ROcs.LGcs.AIcs.CLcs.GRAlgorithmscs.NEneuroscience
On Valency
published · living versionsW_rpzhv4hz·v1 · currentpublished
GPWM: Modeling the World as 3D Particle Motion
with Robert Ren, Matthew Bronars, He Zhu, Yikai Tang +3
1 version
W_2xmxm4wx·v1published
W_734wmyny·v1published
Preprints & journals
79 papers in the corpus · 2012–2026VLM-Guided Contact Retargeting and Generative Partner Modeling for Humanoid-Human Interaction2610.28523v1 · Yuto Shibata, Kotaro Amaya, Kashu Yamazaki et al.2026 · 0 citationsarXivon Valency
Learning Adaptable Dexterous Skills via Hybrid Dexterous Mimicking2610.28628v1 · Yuxuan Kuang, Jiashun Wang, Yixuan Sun et al.2026 · 0 citationsarXivon Valency
SkillWeaver: Agentic Exploration over Neural Interaction Skills for Scalable Robot Data Generation2609.36171v1 · He Zhu, Lusen Zhao, Kwan Man Cheng et al.2026 · 0 citationsarXiv
TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations2609.30222v1 · Ayush Jain, Sreeharsha Paruchuri, Ishita Gupta et al.2026 · 0 citationsarXiv
EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics2609.27308v2 · Zeyu Shen, Haoxiang You, Yilang Liu et al.2026 · 0 citationsarXiv
HIGenNTO: Scalable Humanoid Interaction Generation via Noise-Space Trajectory Optimization2609.22611v1 · Lalit Jayanti, Kashu Yamazaki, Yuto Shibata et al.2026 · 0 citationsarXiv
GeomVLA: Unifying Scene, Motion, and Action in 3D2609.13812v2 · Ziyin Xiong, Nikolaos Gkanatsios, Moritz Reuss et al.2026 · 0 citationsarXiv
Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding2608.02980v2 · Lucy Lin, Ayush Jain, Yifan Liu et al.2026 · 0 citationsarXiv
Tactile Genesis: Exploring Tactile Sensors at Scale for Learning Dexterous Tasks2606.22332v2 · Trinity Chung, Kashu Yamazaki, Dhruv Patel et al.2026 · 0 citationsarXiv
Solving Physics Olympiad via Reinforcement Learning on Physics Simulators2604.11805v1 · Mihir Prabhudesai, Aryan Satpathy, Yangmin Li et al.2026 · 0 citationsarXiv
Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning2603.11346v2 · Yuto Shibata, Kashu Yamazaki, Lalit Jayanti et al.2026 · 0 citationsarXiv
Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulation2602.15828v2 · Yuxuan Kuang, Sungjae Park, Katerina Fragkiadaki et al.2026 · 0 citationsarXiv
RoboTAG: End-to-end Robot Configuration Estimation via Topological Alignment Graph2511.07717v2 · Yifan Liu, Fangneng Zhan, Wanhua Li et al.2025 · 0 citationsarXiv
RobotArena : Scalable Robot Benchmarking via Real-to-Sim Translation2510.23571v3 · Yash Jangir, Yidi Zhang, Pang-Chi Lo et al.2025 · 0 citationsarXiv
3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation2508.11002v2 · Nikolaos Gkanatsios, Jiahe Xu, Matthew Bronars et al.2025 · 0 citationsarXiv
Self-Questioning Language Models2508.03682v4 · Lili Chen, Mihir Prabhudesai, Katerina Fragkiadaki et al.2025 · 1 citationarXiv
Diffusion Beats Autoregressive in Data-Constrained Settings2507.15857v7 · Mihir Prabhudesai, Mengning Wu, Amir Zadeh et al.2025 · 1 citationarXiv
MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second2507.10065v2 · Chenguo Lin, Yuchen Lin, Panwang Pan et al.2025 · 0 citationsarXiv
Generative 4D Scene Gaussian Splatting with Object View-Synthesis Priors2506.12716v1 · Wen-Hsuan Chu, Lei Ke, Jianmeng Liu et al.2025 · 0 citationsarXiv
AllTracker: Efficient Dense Point Tracking at High Resolution2506.07310v2 · Adam W. Harley, Yang You, Xinglong Sun et al.2025 · 11 citationsarXiv
PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers2506.05573v1 · Yuchen Lin, Chenguo Lin, Panwang Pan et al.2025 · 9 citationsarXiv
Grounded Reinforcement Learning for Visual Reasoning2505.23678v3 · Gabriel Sarch, Snigdha Saha, Naitik Khandelwal et al.2025 · 8 citationsarXiv
Maximizing Confidence Alone Improves Reasoning2505.22660v4 · Mihir Prabhudesai, Lili Chen, Alex Ippoliti et al.2025 · 0 citationsarXiv
TAPIP3D: Tracking Any Point in Persistent 3D Geometry2504.14717v3 · Bowei Zhang, Lei Ke, Adam W. Harley et al.2025 · 6 citationsarXiv
Unified Multimodal Discrete Diffusion2503.20853v1 · Alexander Swerdlow, Mihir Prabhudesai, Siddharth Gandhi et al.2025 · 0 citationsarXiv
Unifying 2D and 3D Vision-Language Understanding2503.10745v3 · Ayush Jain, Alexander Swerdlow, Yuzhou Wang et al.2025 · 0 citationsarXiv
Video Depth without Video Models2411.19189v2 · Bingxin Ke, Dominik Narnhofer, Shengyu Huang et al.2024 · 11 citationsarXiv
Deep Generative Models in Robotics: A Survey on Learning from Multimodal Demonstrations2408.04380v3 · Julen Urain, Ajay Mandlekar, Yilun Du et al.2024 · 4 citationsarXiv
Video Diffusion Alignment via Reward Gradients2407.08737v1 · Mihir Prabhudesai, Russell Mendonca, Zheyang Qin et al.2024 · 0 citationsarXiv
VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought2406.14596v6 · Gabriel Sarch, Lawrence Jang, Michael J. Tarr et al.2024 · 6 citationsarXiv
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos2405.02280v2 · Wen-Hsuan Chu, Lei Ke, Katerina Fragkiadaki2024 · 16 citationsarXiv
HELPER-X: A Unified Instructable Embodied Agent to Tackle Four Interactive Vision-Language Domains with Memory-Augmented Language Models2404.19065v1 · Gabriel Sarch, Sahil Somani, Raghav Kapoor et al.2024 · 0 citationsarXiv
Tractable Joint Prediction and Planning over Discrete Behavior Modes for Urban Driving2403.07232v1 · Adam Villaflor, Brian Yang, Huangyuan Su et al.2024 · 2 citationsarXiv
3D Diffuser Actor: Policy Diffusion with 3D Scene Representations2402.10885v3 · Tsung-Wei Ke, Nikolaos Gkanatsios, Katerina Fragkiadaki2024 · 4 citationsarXiv
Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following2402.06559v2 · Brian Yang, Huangyuan Su, Nikolaos Gkanatsios et al.2024 · 2 citationsarXiv
ODIN: A Single Model for 2D and 3D Segmentation2401.02416v3 · Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios et al.2024 · 19 citationsarXiv
Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback2311.16102v2 · Mihir Prabhudesai, Tsung-Wei Ke, Alexander C. Li et al.2023 · 7 citationsarXiv
RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation2311.01455v3 · Yufei Wang, Zhou Xian, Feng Chen et al.2023 · 15 citationsarXiv
Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models2310.18308v1 · Pushkal Katara, Zhou Xian, Katerina Fragkiadaki2023 · 21 citationsarXiv
Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models2310.15127v2 · Gabriel Sarch, Yue Wu, Michael J. Tarr et al.2023 · 25 citationsarXiv
Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models2310.06992v2 · Wen-Hsuan Chu, Adam W. Harley, Pavel Tokmakov et al.2023 · 9 citationsarXiv
Aligning Text-to-Image Diffusion Models with Reward Backpropagation2310.03739v5 · Mihir Prabhudesai, Anirudh Goyal, Deepak Pathak et al.2023 · 6 citationsarXiv
Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation2306.17817v2 · Theophile Gervet, Zhou Xian, Nikolaos Gkanatsios et al.2023 · 6 citationsarXiv
Brain Dissection: fMRI-trained Networks Reveal Spatial Selectivity in the Processing of Natural Images10.1101/2023.05.29.542635v2 · Sarch, G. H., Tarr, M. J., Fragkiadaki, K. et al.2023 · 10 citationsbioRxiv
Analogy-Forming Transformers for Few-Shot 3D Parsing2304.14382v2 · Nikolaos Gkanatsios, Mayank Singh, Zhaoyuan Fang et al.2023 · 0 citationsarXiv
Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement2304.14391v4 · Nikolaos Gkanatsios, Ayush Jain, Zhou Xian et al.2023 · 18 citationsarXiv
FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation2303.02346v1 · Zhou Xian, Bo Zhu, Zhenjia Xu et al.2023 · 18 citationsarXiv
Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation2210.15751v2 · Xingyu Lin, Carl Qi, Yunchu Zhang et al.2022 · 17 citationsarXiv
TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors2207.10761v1 · Gabriel Sarch, Zhaoyuan Fang, Adam W. Harley et al.2022 · 40 citationsarXiv
Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?2206.07959v2 · Adam W. Harley, Zhaoyuan Fang, Jie Li et al.2022 · 158 citationsarXiv
Career total: 103 works. 79 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.