publications.json

{
  "publications": [
    {
      "title": "Continual Robot Learning via Language-Guided Skill Acquisition",
      "authors": "Shuo Cheng*, Zhaoyi Li*, Kelin Yu*, Danfei Xu",
      "venue": "TMLR 2026",
      "abstract": "An LLM-powered pipeline for automatic task decomposition, policy learning, and planning for continual skill acquisition and adaptation.",
      "awards": [
        "J2C Certification (Present at NeurIPS 2026)"
      ],
      "thumbnail": {
        "type": "image",
        "url": "lgsail_cheng2026.png"
      },
      "links": {
        "paper": "https://openreview.net/forum?id=oYRNxxGN9u",
        "website": "https://sites.google.com/view/continuallearning"
      }
    },
    {
      "title": "Compositional Visual Planning via Inference-Time Diffusion Scaling",
      "authors": "Yixin Zhang, Yunhao Luo, Utkarsh A. Mishra, Woo Chul Shin, Yongxin Chen, Danfei Xu",
      "venue": "ICLR 2026",
      "abstract": "An inference-time compositional sampling approach that scales to unseen and long-horizon tasks.",
      "thumbnail": {
        "type": "image",
        "url": "cvp_yixin2026.png"
      },
      "links": {
        "paper": "https://openreview.net/forum?id=EEONns7ae4",
        "website": "https://comp-visual-planning.github.io/"
      }
    },
    {
      "title": "Compositional Diffusion with Guided Search for Long-Horizon Planning",
      "authors": "Utkarsh A. Mishra, David He, Yongxin Chen, Danfei Xu",
      "venue": "ICLR 2026",
      "abstract": "Inference time scaling of compositional diffusion planners with guided search.",
      "awards": [
        "Oral"
      ],
      "thumbnail": {
        "type": "image",
        "url": "cdgs_mishra2026.png"
      },
      "links": {
        "paper": "https://arxiv.org/pdf/2601.00126",
        "website": "https://cdgsearch.github.io/",
        "code": "https://github.com/cdgsearch/getting_started_with_CDGS"
      }
    },
    {
      "title": "EMMA: Scaling Mobile Manipulation via Egocentric Human Data",
      "authors": "Lawrence Yunzhou Zhu, Pranav Kuppili*, Ryan Punamiya*, Patcharapong Aphiwetsa**, Dhruv Patel**, Simar Kareer, Sehoon Ha, Danfei Xu",
      "venue": "IEEE RA-L 2025",
      "abstract": "Scaling mobile manipulation from co-training static robot data and egocentric human full-body data.",
      "thumbnail": {
        "type": "video",
        "url": "emma_zhu2025.mp4"
      },
      "links": {
        "paper": "https://arxiv.org/pdf/2509.04443",
        "website": "https://ego-moma.github.io/",
        "video": "https://youtu.be/Qq1Jp52Zj3Q?si=NW_HGs_TeXnXMkJ9",
        "x-post": "https://x.com/LawrenceZhu22/status/1965430612283850978?s=20"
      }
    },
    {
      "title": "Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training",
      "authors": "Shuo Cheng*, Liqian Ma*, Zhenyang Chen, Ajay Mandlekar*, Caelan Garrett*, Danfei Xu",
      "venue": "NeurIPS 2025",
      "abstract": "A sim-and-real co-training framework for learning generalizable manipulation policies.",
      "thumbnail": {
        "type": "image",
        "url": "ot_sim2real.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2509.18631",
        "website": "https://ot-sim2real.github.io/"
      }
    },
    {
      "title": "EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data",
      "authors": "Ryan Punamiya, Dhruv Patel, Elmo Aphiwetsa, Pranav Kuppili, Lawrence Y. Zhu, Simar Kareer*, Judy Hoffman*, Danfei Xu*",
      "venue": "NeurIPS 2025",
      "abstract": "Joint observation-action domain adaptation using Optimal Transport to enable robot generalization from egocentric human data.",
      "thumbnail": {
        "type": "video",
        "url": "egobridge.mp4"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2509.19626",
        "website": "https://ego-bridge.github.io/"
      }
    },
    {
      "title": "Generative Trajectory Stitching through Diffusion Composition",
      "authors": "Yunhao Luo, Utkarsh A. Mishra, Yilun Du*, Danfei Xu*",
      "venue": "NeurIPS 2025",
      "abstract": "A compositional diffusion planner that constructs long-horizon plans from short-horizon training data.",
      "awards": [
        "Spotlight"
      ],
      "thumbnail": {
        "type": "video",
        "url": "2025/2025-compdfu-web-v4-rl2-v2.mp4"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2503.05153",
        "website": "https://comp-diffuser.github.io/"
      }
    },
    {
      "title": "ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation",
      "authors": "Yangcen Liu*, Woo Chul Shin*, Yunhai Han, Zhenyang Chen, Harish Ravichandar, Danfei Xu",
      "venue": "CoRL 2025",
      "abstract": "Embodiment-agnostic pipeline to learn from human videos",
      "awards": [
        "Oral Presentation"
      ],
      "thumbnail": {
        "type": "image",
        "url": "immimic.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2509.10952",
        "website": "https://sites.google.com/view/immimic"
      }
    },
    {
      "title": "SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies",
      "authors": "Nadun Ranawaka Arachchige*, Zhenyang Chen*, Wonsuhk Jung, Woo Chul Shin, Rohan Bansal, Pierre Barroso, Yu Hang He, Yingyan Celine Lin, Benjamin Joffe, Shreyas Kousik*, Danfei Xu*",
      "venue": "CoRL 2025",
      "abstract": "System to execute imitation learning policies faster than human demonstrations",
      "awards": [
        "Oral Presentation"
      ],
      "thumbnail": {
        "type": "image",
        "url": "sail.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2506.11948",
        "website": "https://nadunranawaka1.github.io/sail-policy/"
      }
    },
    {
      "title": "Joint Model-based Model-free Diffusion for Planning with Constraints",
      "authors": "Wonsuhk Jung*, Utkarsh A Mishra*, Nadun Ranawaka Arachchige, Yongxin Chen*, Danfei Xu*, Shreyas Kousik*",
      "venue": "CoRL 2025",
      "abstract": "A unified diffusion framework for planning and optimization",
      "thumbnail": {
        "type": "video",
        "url": "jm2d.mp4"
      }
    },
    {
      "title": "EgoMimic: Scaling Imitation Learning through Egocentric Video",
      "authors": "Simar Kareer, Dhruv Patel*, Ryan Punamiya*, Pranay Mathur*, Shuo Cheng, Chen Wang, Judy Hoffman*, Danfei Xu*",
      "venue": "ICRA 2025",
      "abstract": "Robot Learning from Egocentric Human Data",
      "thumbnail": {
        "type": "video",
        "url": "egomimic.mp4"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2410.24221",
        "website": "https://egomimic.github.io/"
      }
    },
    {
      "title": "RAIL: Reachability-Aided Imitation Learning for Safe Policy Execution",
      "authors": "Wonsuhk Jung, Dennis Anthony, Utkarsh A Mishra, Nadun Ranawaka Arachchige, Matthew Bronars, Danfei Xu*, Shreyas Kousik*",
      "venue": "ICRA 2025",
      "abstract": "Plug-and-play safety filters for policy models.",
      "thumbnail": {
        "type": "image",
        "url": "rail_jung2025.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2409.19190",
        "website": "https://rail2024.github.io/"
      }
    },
    {
      "title": "What Matters in Learning from Large-Scale Datasets for Robot Manipulation",
      "authors": "Vaibhav Saxena, Matthew Bronars*, Nadun Ranawaka Arachchige*, Kuancheng Wang, Woo Chul Shin, Soroush Nasiriany, Ajay Mandlekar*, Danfei Xu*",
      "venue": "ICLR 2025",
      "abstract": "MimicLabs, a large-scale data generation framework and data composition study for imitation learning.",
      "thumbnail": {
        "type": "image",
        "url": "mimiclabs_saxena2025.png"
      },
      "links": {
        "paper": "https://arxiv.org/pdf/2506.13536",
        "website": "https://robo-mimiclabs.github.io/"
      }
    },
    {
      "title": "NOD-TAMP: Multi-Step Manipulation Planning with Neural Object Descriptors",
      "authors": "Shuo Cheng, Caelan Garrett*, Ajay Mandlekar*, Danfei Xu",
      "venue": "CoRL 2024",
      "abstract": "Solving multi-step manipulation problems with zero-shot generalization.",
      "thumbnail": {
        "type": "image",
        "url": "nod_cheng2023.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2311.01530"
      }
    },
    {
      "title": "MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation",
      "authors": "Kelin Yu*, Yunhai Han*, Qixian Wang, Vaibhav Saxena, Danfei Xu*, Ye Zhao*",
      "venue": "CoRL 2024",
      "abstract": "Learning tactile control policies from human hand demonstrations.",
      "thumbnail": {
        "type": "image",
        "url": "mmt_yu2024.png"
      },
      "links": {
        "paper": "https://openreview.net/forum?id=7yMZAUkXa4"
      }
    },
    {
      "title": "Generative Factor Chaining: Coordinated Manipulation with Diffusion-based Factor Graph",
      "authors": "Utkarsh Mishra, Yongxin Chen, Danfei Xu",
      "venue": "CoRL 2024",
      "abstract": "A compositional generative model that can plan for long-horizon, complex coordinated manipulation tasks.",
      "thumbnail": {
        "type": "image",
        "url": "gfc_mishra2024.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2409.16275"
      }
    },
    {
      "title": "Legibility Diffuser: Offline Imitation for Intent Expressive Motion",
      "authors": "Matthew Bronars, Shuo Cheng, Danfei Xu",
      "venue": "IEEE RA-L 2024",
      "abstract": "Learning to generate legible robot motion (motion with expressive intent) with Conditional Diffusion Models.",
      "thumbnail": {
        "type": "image",
        "url": "ldm_bronars2024.png"
      }
    },
    {
      "title": "Neural Visibility Field for Uncertainty-Driven Active Mapping",
      "authors": "Shangjie Xue, Jesse Dill, Pranay Mathur, Frank Dellaert, Panagiotis Tsiotras, Danfei Xu",
      "venue": "CVPR 2024",
      "abstract": "A principled Bayesian framework to model uncertainty in NeRF for active mapping.",
      "thumbnail": {
        "type": "video",
        "url": "nvf_xue2024.mp4"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2406.06948"
      }
    },
    {
      "title": "Open X-Embodiment: Robotic Learning Datasets and RT-X Models",
      "authors": "Many Authors",
      "venue": "ICRA 2024",
      "abstract": "",
      "awards": [
        "Best Paper Award"
      ],
      "thumbnail": {
        "type": "image",
        "url": "openx.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2310.08864",
        "website": "https://robotics-transformer-x.github.io/"
      }
    },
    {
      "title": "EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision",
      "authors": "Jiawei Yang, Boris Ivanovic, Or Litany, Xinshuo Weng, Seung Wook Kim, Boyi Li, Tong Che, Danfei Xu, Sanja Fidler, Marco Pavone, Yue Wang",
      "venue": "ICLR 2024",
      "abstract": "Unsupervised 4D representation learning from videos.",
      "thumbnail": {
        "type": "image",
        "url": "enerf_yang2023.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2311.02077"
      }
    },
    {
      "title": "C3DM: Constrained-Context Conditional Diffusion Models for Imitation Learning",
      "authors": "Vaibhav Saxena, Yotto Koga, Danfei Xu",
      "venue": "TMLR 2024",
      "abstract": "High-precision manipulation with generative action modeling.",
      "thumbnail": {
        "type": "image",
        "url": "c3dm_saxena2023.png"
      },
      "links": {
        "website": "https://sites.google.com/view/c3dm-imitation-learning"
      }
    },
    {
      "title": "Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models",
      "authors": "Utkarsh Mishra, Shangjie Xue, Yongxin Chen, Danfei Xu",
      "venue": "CoRL 2023",
      "abstract": "A new algorithm to chain together skill-level diffusion models to solve long-horizon manipulation tasks.",
      "thumbnail": {
        "type": "image",
        "url": "gsc_mishra2023.png"
      },
      "links": {
        "paper": "https://generative-skill-chaining.github.io/assets/2023_Generative_Skill_Chaining.pdf",
        "website": "https://generative-skill-chaining.github.io/"
      }
    },
    {
      "title": "Neural Field Dynamics Model for Granular Object Piles Manipulation",
      "authors": "Shangjie Xue, Shuo Cheng, Pujith Kachana, Danfei Xu",
      "venue": "CoRL 2023",
      "abstract": "A new field-based representation (occupancy density) to model and optimize granular object manipulation.",
      "awards": [
        "Best Paper finalist at ICRA'23 Workshop on Representing and Manipulating Deformable Objects"
      ],
      "thumbnail": {
        "type": "image",
        "url": "nfd_xue2023.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2311.00802",
        "website": "https://sites.google.com/view/nfd-corl23/"
      }
    },
    {
      "title": "Learning to Discern: Imitating Heterogeneous Human Demonstrations with Preference and Representation Learning",
      "authors": "Sachit Kuhar, Shuo Cheng, Shivang Chopra, Matthew Bronars, Danfei Xu",
      "venue": "CoRL 2023",
      "abstract": "An offline imitation learning algorithm to learn from mixed-quality human demonstrations.",
      "thumbnail": {
        "type": "image",
        "url": "l2d_kuhar2023.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2310.14196"
      }
    },
    {
      "title": "Human-in-the-Loop Task and Motion Planning for Imitation Learning",
      "authors": "Ajay Mandlekar*, Caelan Garret*, Danfei Xu, Dieter Fox",
      "venue": "CoRL 2023",
      "abstract": "We present HITL-TAMP, a system that merges human teleoperation with automated TAMP to efficiently train robots for complex tasks.",
      "thumbnail": {
        "type": "image",
        "url": "hitltamp_mandlekar2023.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2310.16014",
        "website": "https://hitltamp.github.io/"
      }
    },
    {
      "title": "Language-Guided Traffic Simulation via Scene-Level Diffusion",
      "authors": "Ziyuan Zhong, Davis Rempe, Yuxiao Chen, Boris Ivanovic, Yulong Cao, Danfei Xu, Marco Pavone, Baishakhi Ray",
      "venue": "CoRL 2023",
      "abstract": "GPT4-guided trajectory diffusion model.",
      "awards": [
        "Oral Presentation"
      ],
      "thumbnail": {
        "type": "image",
        "url": "gptdiff_zhong2023.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2306.06344"
      }
    },
    {
      "title": "MimicPlay: Long-Horizon Imitation Learning by Watching Human Play",
      "authors": "Chen Wang, Linxi Fan, Jiankai Sun, Ruohan Zhang, Li Fei-Fei, Danfei Xu, Yuke Zhu, Anima Anandkumar",
      "venue": "CoRL 2023",
      "abstract": "We leverage human video data to train a planner to guide robust low-level task execution.",
      "awards": [
        "Best Paper",
        "Best Systems Paper Finalist"
      ],
      "thumbnail": {
        "type": "image",
        "url": "mimicplay_wang2023.png"
      },
      "links": {
        "paper": "https://mimic-play.github.io/assets/MimicPlay.pdf"
      }
    },
    {
      "title": "LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation",
      "authors": "Shuo Cheng, Danfei Xu",
      "venue": "Robotics and Automation Letters (RA-L)",
      "abstract": "We use Task and Motion Planning (TAMP) as guidance for learning generalizable and composable sensorimotor skills.",
      "awards": [
        "2023 Best Paper Honorable Mention"
      ],
      "thumbnail": {
        "type": "image",
        "url": "league_cheng2022.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2210.12631"
      }
    },
    {
      "title": "ProgPrompt: Generating Situated Robot Task Plans using Large Language Models",
      "authors": "Ishika Singh, Valts Blukis, Arsalan Mousavian, Ankit Goyal, Danfei Xu, Jonathan Tremblay, Dieter Fox, Jesse Thomason, Animesh Garg",
      "venue": "ICRA 2023",
      "abstract": "We harness the power of large language model to generate program-like task plans.",
      "thumbnail": {
        "type": "image",
        "url": "progp_singh2022.png"
      },
      "links": {
        "website": "https://progprompt.github.io/"
      }
    },
    {
      "title": "BITS: Bi-level Imitation for Traffic Simulation",
      "authors": "Danfei Xu*, Yuxiao Chen*, Boris Ivanovic, Marco Pavone",
      "venue": "ICRA 2023",
      "abstract": "Hierarchical imitation for generating diverse, realistic, and robust traffic behaviors.",
      "thumbnail": {
        "type": "image",
        "url": "bits_xu2022.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2208.12403"
      }
    },
    {
      "title": "Guided Conditional Diffusion for Controllable Traffic Simulation",
      "authors": "Ziyuan Zhong, Davis Rempe, Danfei Xu, Yuxiao Chen, Sushant Veer, Tong Che, Baishakhi Ray, Marco Pavone",
      "venue": "ICRA 2023",
      "abstract": "Learn behavior prior through diffusion-based imitation. Sample desired behaviors by conditional diffusion and Signal-Temporal Logic (STL) rules.",
      "thumbnail": {
        "type": "image",
        "url": "ctg_zhong2022.png"
      },
      "links": {
        "website": "https://aiasd.github.io/ctg.github.io/"
      }
    },
    {
      "title": "Robust Trajectory Prediction against Adversarial Attacks",
      "authors": "Yulong Cao, Danfei Xu, Xinshuo Weng, Zhuoqing Mao, Anima Anandkumar, Chaowei Xiao, Marco Pavone",
      "venue": "CoRL 2022",
      "abstract": "Defending against attacks that target generative behavior models.",
      "awards": [
        "Oral Presentation"
      ],
      "thumbnail": {
        "type": "image",
        "url": "rob_cao2022.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2208.00094"
      }
    },
    {
      "title": "AdvDO: Realistic Adversarial Attacks for Trajectory Prediction",
      "authors": "Yulong Cao, Chaowei Xiao, Anima Anandkumar, Danfei Xu, Marco Pavone",
      "venue": "ECCV 2022",
      "abstract": "Physically-plausible attack on behavior forecasting models.",
      "thumbnail": {
        "type": "image",
        "url": "adv_cao2022.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2209.08744"
      }
    },
    {
      "title": "Generalizable Task Planning through Representation Pretraining",
      "authors": "Chen Wang, Danfei Xu, Li Fei-Fei",
      "venue": "Robotics and Automation Letters (RA-L) 2022",
      "abstract": "Building generalizable world models for planning with unseen objects and environments.",
      "thumbnail": {
        "type": "image",
        "url": "wang_gentp2022.gif"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2205.07993"
      }
    },
    {
      "title": "What Matters in Learning from Offline Human Demonstrations for Robot Manipulation",
      "authors": "Ajay Mandlekar, Danfei Xu, Josiah Wong, Soroush Nasiriany, Chen Wang, Rohun Kulkarni, Li Fei-Fei, Silvio Savarese, Yuke Zhu, Roberto Martin-Martin",
      "venue": "CoRL 2021",
      "abstract": "A large-scale study on learning manipulation skills from human demonstrations.",
      "awards": [
        "Oral Presentation"
      ],
      "thumbnail": {
        "type": "image",
        "url": "mandlekar_mic2021.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2108.03298",
        "code": "https://github.com/ARISE-Initiative/robomimic",
        "website": "https://arise-initiative.github.io/robomimic-web/",
        "blog": "https://ai.stanford.edu/blog/robomimic/"
      }
    },
    {
      "title": "Human-in-the-Loop Imitation Learning using Remote Teleoperation",
      "authors": "Ajay Mandlekar, Danfei Xu, Roberto Martin-Martin, Yuke Zhu, Li Fei-Fei, Silvio Savarese",
      "venue": "Arxiv Preprint, 2021",
      "abstract": "Human-in-the-loop learning for complex manipulation tasks.",
      "thumbnail": {
        "type": "image",
        "url": "mandlekar_hil2020.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2012.06733"
      }
    },
    {
      "title": "Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration",
      "authors": "Chen Wang, Claudia D'Arpino, Danfei Xu, Li Fei-Fei, Karen Liu, Silvio Savarese",
      "venue": "CoRL 2021",
      "abstract": "Learning human-robot collaboration policies from human-human collaboration demonstrations.",
      "thumbnail": {
        "type": "image",
        "url": "wang_cg2021.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2108.06038"
      }
    },
    {
      "title": "Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control",
      "authors": "Chen Wang*, Rui Wang*, Ajay Mandlekar, Li Fei-Fei, Silvio Savarese, Danfei Xu",
      "venue": "IROS 2021",
      "abstract": "An learnable action space for recovering human's hand-eye coordination behaviors by learning from human demonstrations.",
      "thumbnail": {
        "type": "image",
        "url": "wang_han2020.png"
      },
      "links": {
        "paper": "https://arxiv.org/pdf/2103.00375.pdf"
      }
    },
    {
      "title": "Deep Affordance Foresight: Planning Through What Can Be Done in the Future",
      "authors": "Danfei Xu, Ajay Mandlekar, Roberto Martin-Martin, Yuke Zhu, Silvio Savarese, Li Fei-Fei",
      "venue": "ICRA 2021",
      "abstract": "We extend the classical definition of affordance to enable generalizable long-horizon planning.",
      "notes": [
        "Long version at ICRA 2021",
        "Short version - Oral Presentation at NeurIPS Workshop on Object Representations for Learning and Reasoning, 2020"
      ],
      "thumbnail": {
        "type": "image",
        "url": "xu_daf2020.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2011.08424"
      }
    },
    {
      "title": "Positive-Unlabeled Reward Learning",
      "authors": "Danfei Xu, Misha Denil",
      "venue": "CoRL 2020",
      "abstract": "An algorithm framework that simultaneously addresses the reward delusion problem in supervised reward learning and the overfitting discriminator problem in adversarial imitation learning.",
      "notes": [
        "Long version at CoRL 2020",
        "Short version at NeurIPS Deep Reinforcement Learning Workshop 2019"
      ],
      "thumbnail": {
        "type": "image",
        "url": "xu_purl2019.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/1911.00459",
        "video": "https://www.youtube.com/watch?v=eRVr5eyRCWc&feature=emb_title"
      }
    },
    {
      "title": "Procedure Planning in Instructional Videos",
      "authors": "Chien-Yi Chang, De-An Huang, Danfei Xu, Ehsan Adeli, Li Fei-Fei, Juan Carlos Niebles",
      "venue": "ECCV 2020",
      "abstract": "Learning to plan from instructional videos.",
      "thumbnail": {
        "type": "image",
        "url": "cy_eccv20.png"
      },
      "links": {
        "paper": "https://arxiv.org/pdf/1907.01172.pdf"
      }
    },
    {
      "title": "Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations",
      "authors": "Ajay Mandlekar*, Danfei Xu*, Roberto Martin-Martin, Silvio Savarese, Li Fei-Fei",
      "venue": "RSS 2020",
      "abstract": "Learning visuomotor policies that can generalize across long-horizon tasks by modeling latent compositional structures.",
      "thumbnail": {
        "type": "image",
        "url": "gti2020.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/2003.06085",
        "website": "https://sites.google.com/view/gti2020",
        "video": "https://youtu.be/_adwEw1rmxA",
        "blog": "http://ai.stanford.edu/blog/gti/"
      }
    },
    {
      "title": "6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints",
      "authors": "Chen Wang, Roberto Martin-Martin, Danfei Xu, Jun Lv, Cewu Lu, Li Fei-Fei, Silvio Savarese, Yuke Zhu",
      "venue": "ICRA 2020",
      "abstract": "Real-time category-level 6D object tracking from RGB-D data.",
      "thumbnail": {
        "type": "image",
        "url": "wang_pack2019.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/1910.10750",
        "website": "https://sites.google.com/view/6packtracking",
        "video": "https://www.youtube.com/watch?v=INBjNZsnfy4",
        "code": "https://github.com/j96w/6-PACK"
      }
    },
    {
      "title": "Regression Planning Networks",
      "authors": "Danfei Xu, Roberto Martin-Martin, De-An Huang, Yuke Zhu, Silvio Savarese, Li Fei-Fei",
      "venue": "NeurIPS 2019",
      "abstract": "A flexible neural network architecture for learning to plan from video demonstrations.",
      "thumbnail": {
        "type": "image",
        "url": "xu_rpn_neurips2019.png"
      },
      "links": {
        "paper": "rpn_neurips19_final.pdf",
        "code": "https://github.com/danfeiX/RPN",
        "poster": "xu_rpn_neurips2019_poster.pdf"
      }
    },
    {
      "title": "Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning",
      "authors": "De-An Huang, Danfei Xu, Yuke Zhu, Silvio Savarese, Li Fei-Fei, Juan Carlos Niebles",
      "venue": "IROS 2019",
      "abstract": "One-shot imitation learning via hybrid neural-symbolic planning.",
      "thumbnail": {
        "type": "image",
        "url": "huang_iros19.jpg"
      },
      "links": {
        "paper": "https://arxiv.org/abs/1908.06769",
        "blog": "http://ai.stanford.edu/blog/ntp-ntg/"
      }
    },
    {
      "title": "DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion",
      "authors": "Chen Wang, Danfei Xu, Yuke Zhu, Roberto Martin-Martin, Cewu Lu, Li Fei-Fei, Silvio Savarese",
      "venue": "CVPR 2019",
      "abstract": "Dense RGB-depth sensor fusion for 6D object pose estimation.",
      "thumbnail": {
        "type": "image",
        "url": "df2019.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/1901.04780",
        "website": "https://sites.google.com/view/densefusion/",
        "video": "https://www.youtube.com/watch?v=SsE5-FuK5jo",
        "code": "https://github.com/j96w/DenseFusion"
      }
    },
    {
      "title": "Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration",
      "authors": "De-An Huang*, Suraj Nair*, Danfei Xu*, Yuke Zhu, Animesh Garg, Li Fei-Fei, Silvio Savarese, Juan Carlos Niebles",
      "venue": "CVPR 2019",
      "abstract": "Generate executable task graphs from video demonstrations.",
      "awards": [
        "Oral Presentation"
      ],
      "thumbnail": {
        "type": "image",
        "url": "eccv18_ntg.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/1807.03480",
        "blog": "http://ai.stanford.edu/blog/ntp-ntg/"
      }
    },
    {
      "title": "Neural Task Programming: Learning to Generalize Across Hierarchical Tasks",
      "authors": "Danfei Xu*, Suraj Nair*, Yuke Zhu, Julian Gao, Animesh Garg, Li Fei-Fei, Silvio Savarese",
      "venue": "ICRA 2018",
      "abstract": "Neural Task Programming (NTP) is a meta-learning framework that learns to generate robot-executable neural programs from task demonstration video.",
      "thumbnail": {
        "type": "image",
        "url": "ntp2017.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/1710.01813",
        "website": "https://stanfordvl.github.io/ntp/",
        "video": "https://www.youtube.com/watch?v=THq7I7C5rkk",
        "blog": "http://ai.stanford.edu/blog/ntp-ntg/"
      }
    },
    {
      "title": "PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation",
      "authors": "Danfei Xu, Ashesh Jain, Dragomir Anguelov",
      "venue": "CVPR 2018",
      "abstract": "End-to-end 3D Bounding Box Estimation via sensor fusion.",
      "thumbnail": {
        "type": "image",
        "url": "ptf2018.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/1711.10871"
      }
    },
    {
      "title": "Scene Graph Generation by Iterative Message Passing",
      "authors": "Danfei Xu, Yuke Zhu, Christopher B. Choy, Li Fei-Fei",
      "venue": "CVPR 2017",
      "abstract": "We propose an end-to-end model that jointly infers object category, location, and relationships. The model learns to iteratively improve its prediction by passing messages on a scene graph.",
      "thumbnail": {
        "type": "image",
        "url": "imp2017.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/1701.02426",
        "website": "https://cs.stanford.edu/~danfei/scene-graph/",
        "code": "https://github.com/danfeiX/scene-graph-TF-release"
      }
    },
    {
      "title": "3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction",
      "authors": "Christopher B. Choy, Danfei Xu*, JunYoung Gwak*, Silvio Savarese",
      "venue": "ECCV 2016",
      "abstract": "We propose an end-to-end 3D reconstruction model that unifies single- and multi-view reconstruction.",
      "thumbnail": {
        "type": "image",
        "url": "r2n22016.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/1604.00449",
        "website": "http://3d-r2n2.stanford.edu/",
        "code": "https://github.com/chrischoy/3D-R2N2/"
      }
    },
    {
      "title": "Model-Driven Feed-Forward Prediction for Manipulation of Deformable Objects",
      "authors": "Yinxiao Li, Yan Wang, Yonghao Yue, Danfei Xu, Michael Case, Shih-Fu Chang, Eitan Grinspun, Peter K. Allen",
      "venue": "IEEE TASE 2016",
      "abstract": "Deformable object manipulation with an application of personal assitive robot.",
      "thumbnail": {
        "type": "image",
        "url": "unfolding.png"
      },
      "links": {
        "paper": "https://arxiv.org/abs/1607.04411",
        "website": "http://www.cs.columbia.edu/~yli/laundry_robot/"
      }
    },
    {
      "title": "Topometric localization on a road network",
      "authors": "Danfei Xu, Hernan Badino, Daniel Huber",
      "venue": "IROS 2015",
      "abstract": "Vision-based localization on a probabilistic road network.",
      "thumbnail": {
        "type": "image",
        "url": "localization.jpg"
      },
      "links": {
        "paper": "http://ieeexplore.ieee.org/abstract/document/6943043/"
      }
    },
    {
      "title": "Tactile identification of objects using Bayesian exploration",
      "authors": "Danfei Xu, Gerald E. Loeb, Jeremy Fishel",
      "venue": "ICRA 2013",
      "abstract": "Object classification using multi-modal tactile sensing.",
      "thumbnail": {
        "type": "image",
        "url": "tactile.png"
      },
      "links": {
        "paper": "https://pdfs.semanticscholar.org/2127/2c9877e4159f83546eac3a352ba47f3d858d.pdf"
      }
    }
  ]
}