Skand

I am a postdoc at UT Austin 🤘 working with Roberto Martín-Martín in the RobIN lab. Previously, I was visiting the WEIRD lab at the University of Washington 🐺, collaborating with Abhishek Gupta and Jesse Zhang on fast real-world adaptation of policies using world models.

I received my Ph.D. from Oregon State University 🦫, where I was advised by Fuxin Li and Stefan Lee. My dissertation, Efficient and Robust Robot Learning, proposed methods to build robots that keep working – making them (a) more energy-efficient, (b) resilient to sensory failures, (c) robust to viewpoint and lighting changes, and (d) adaptable to new tasks via 3D point dynamics models.

I am interested in developing systems and algorithms that enable robots to learn and continuously adapt to complex tasks in the real world.

Previous Research Life

Previously, I worked with Sungjin Ahn on object-centric world models and RL. Before that, I was worked with Venkatesh Babu at the Indian Institute of Science. I graduated with Bachelors of Technology (B.Tech) degree in Computer Science and Engineering from Indian Institute of Technology, Ropar where I was advised by Narayanan Krishnan for my Bachelor’s Thesis. During my undergrad, I also worked with Deepti Bathula and Abhinav Dhall.

publications

PrePrint

VETO: Reward-Supervised World Models as Action Verifiers for Sample-Efficient RL

Skand Peri*, Matthew Hong*, Chaoxiang Zhang, Ross Worobel, Suraj Shivakumar, Dieter Fox, Jesse Zhang†, and Abhishek Gupta†

preprint, 2026

R2RL Workshop (Oral), Learn@Deploy Workshop (Spotlight), CSIR Workshop @ CoRL 2026

Bib

@article{VETO,
  author = {Peri*, Skand and Hong*, Matthew and Zhang, Chaoxiang and Worobel, Ross and Shivakumar, Suraj and Fox, Dieter and Zhang†, Jesse and Gupta†, Abhishek},
  title = {VETO: Reward-Supervised World Models as Action Verifiers for Sample-Efficient RL},
  journal = {preprint},
  year = {2026},
}

PrePrint

OopsieRecover: Learning Transferable VLA Corrections from Semantic Interventions

Arpit Bahety*, Skand Peri*, Sriniket Ambatipudi, Chen Xu, Haruki Nishimura, Masha Itkina, and Roberto Martín-Martín

arXiv preprint, 2026

Learning from Corrections and Interventions (LfC) Workshop @ CoRL 2026

arXiv Bib Website

@article{OopsieRecover,
  author = {Bahety*, Arpit and Peri*, Skand and Ambatipudi, Sriniket and Xu, Chen and Nishimura, Haruki and Itkina, Masha and Martín-Martín, Roberto},
  title = {OopsieRecover: Learning Transferable VLA Corrections from Semantic Interventions
  },
  journal = {arXiv preprint},
  year = {2026},
}

CoRLOral

Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control

Skand Peri, Akhil Perincherry*, Bikram Pandit*, and Stefan Lee

Conference on Robot Learning, 2025

arXiv Bib Code Website Talk

@article{PEGRAD,
  abbr2 = {Oral},
  author = {Peri, Skand and Perincherry*, Akhil and Pandit*, Bikram and Lee, Stefan},
  title = {Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control},
  journal = {Conference on Robot Learning},
  year = {2025},
  talk = {https://youtu.be/9lzFVQoc4Do?t=4470}
}

CoRL

Simple Masked Training Strategies Yield Control Policies That Are Robust to Sensor Failure

Skand Peri, Bikram Pandit, Chanho Kim, Li Fuxin, and Stefan Lee

Conference on Robot Learning, 2024

Bib PDF Website

@article{RME,
  author = {Peri, Skand and Pandit, Bikram and Kim, Chanho and Fuxin, Li and Lee, Stefan},
  title = {Simple Masked Training Strategies Yield Control Policies That Are Robust to Sensor Failure},
  journal = {Conference on Robot Learning},
  year = {2024},
}

ICRA

Point Cloud Models Improve Visual Robustness in Robotic Learners

Skand Peri, Iain Lee, Chanho Kim, Li Fuxin, Tucker Hermans, and Stefan Lee

International Conference on Robotics and Automation, 2024

arXiv Bib PDF Website

@article{PCWM,
  author = {Peri, Skand and Lee, Iain and Kim, Chanho and Fuxin, Li and Hermans, Tucker and Lee, Stefan},
  title = {Point Cloud Models Improve Visual Robustness in Robotic Learners},
  journal = {International Conference on Robotics and Automation},
  year = {2024},
}

ICLR

SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition

Zhixuan Lin*, Yi-Fu Wu*, Skand Peri*, Weihao Sun, Gautam Singh, Fei Deng, Jindong Jiang, and Sungjin Ahn

International Conference on Learning Representations, 2020

Bib PDF Code Website

@article{SPACE20,
  author = {Lin*, Zhixuan and Wu*, Yi-Fu and Peri*, Skand and Sun, Weihao and Singh, Gautam and Deng, Fei and Jiang, Jindong and Ahn, Sungjin},
  title = {SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition},
  journal = {International Conference on Learning Representations},
  year = {2020},
}

PrePrint

VETO: Reward-Supervised World Models as Action Verifiers for Sample-Efficient RL

Skand Peri*, Matthew Hong*, Chaoxiang Zhang, Ross Worobel, Suraj Shivakumar, Dieter Fox, Jesse Zhang†, and Abhishek Gupta†

preprint, 2026

R2RL Workshop (Oral), Learn@Deploy Workshop (Spotlight), CSIR Workshop @ CoRL 2026

Bib

@article{VETO,
  author = {Peri*, Skand and Hong*, Matthew and Zhang, Chaoxiang and Worobel, Ross and Shivakumar, Suraj and Fox, Dieter and Zhang†, Jesse and Gupta†, Abhishek},
  title = {VETO: Reward-Supervised World Models as Action Verifiers for Sample-Efficient RL},
  journal = {preprint},
  year = {2026},
}

PrePrint

OopsieRecover: Learning Transferable VLA Corrections from Semantic Interventions

Arpit Bahety*, Skand Peri*, Sriniket Ambatipudi, Chen Xu, Haruki Nishimura, Masha Itkina, and Roberto Martín-Martín

arXiv preprint, 2026

Learning from Corrections and Interventions (LfC) Workshop @ CoRL 2026

arXiv Bib Website

@article{OopsieRecover,
  author = {Bahety*, Arpit and Peri*, Skand and Ambatipudi, Sriniket and Xu, Chen and Nishimura, Haruki and Itkina, Masha and Martín-Martín, Roberto},
  title = {OopsieRecover: Learning Transferable VLA Corrections from Semantic Interventions
  },
  journal = {arXiv preprint},
  year = {2026},
}

PrePrint

MoMaSplat: Dynamic Novel-View Demonstration Augmentation for Mobile Manipulation

Sateesh Kumar*, Arnav Balaji*, Arpit Bahety, Skand Peri, Georgios Pavlakos†, and Roberto Martín-Martín†

arXiv preprint, 2026

The Action Gap (TAG) Workshop @ CoRL 2026

arXiv Bib Website

@article{MoMaSplat,
  author = {Kumar*, Sateesh and Balaji*, Arnav and Bahety, Arpit and Peri, Skand and Pavlakos†, Georgios and Martín-Martín†, Roberto},
  title = {MoMaSplat: Dynamic Novel-View Demonstration Augmentation for Mobile Manipulation
  },
  journal = {arXiv preprint},
  year = {2026},
}

PrePrint

3D Point World Models Point Completion Enables More Accurate Dynamics Learning

Skand Peri, Hung Nguyen, Chanho Kim, Li Fuxin, and Stefan Lee

arXiv preprint, 2026

E2E3D Workshop @ CVPR 2026

arXiv Bib Code Website

@article{3DPWM,
  author = {Peri, Skand and Nguyen, Hung and Kim, Chanho and Fuxin, Li and Lee, Stefan},
  title = {3D Point World Models Point Completion Enables More Accurate Dynamics Learning},
  journal = {arXiv preprint},
  year = {2026},
}

CoRLOral

Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control

Skand Peri, Akhil Perincherry*, Bikram Pandit*, and Stefan Lee

Conference on Robot Learning, 2025

arXiv Bib Code Website Talk

@article{PEGRAD,
  abbr2 = {Oral},
  author = {Peri, Skand and Perincherry*, Akhil and Pandit*, Bikram and Lee, Stefan},
  title = {Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control},
  journal = {Conference on Robot Learning},
  year = {2025},
  talk = {https://youtu.be/9lzFVQoc4Do?t=4470}
}

CoRL

Simple Masked Training Strategies Yield Control Policies That Are Robust to Sensor Failure

Skand Peri, Bikram Pandit, Chanho Kim, Li Fuxin, and Stefan Lee

Conference on Robot Learning, 2024

Bib PDF Website

@article{RME,
  author = {Peri, Skand and Pandit, Bikram and Kim, Chanho and Fuxin, Li and Lee, Stefan},
  title = {Simple Masked Training Strategies Yield Control Policies That Are Robust to Sensor Failure},
  journal = {Conference on Robot Learning},
  year = {2024},
}

ICRA

Point Cloud Models Improve Visual Robustness in Robotic Learners

Skand Peri, Iain Lee, Chanho Kim, Li Fuxin, Tucker Hermans, and Stefan Lee

International Conference on Robotics and Automation, 2024

arXiv Bib PDF Website

@article{PCWM,
  author = {Peri, Skand and Lee, Iain and Kim, Chanho and Fuxin, Li and Hermans, Tucker and Lee, Stefan},
  title = {Point Cloud Models Improve Visual Robustness in Robotic Learners},
  journal = {International Conference on Robotics and Automation},
  year = {2024},
}

ICML

Structured World Belief for Reinforcement Learning in POMDP

Gautam Singh, Skand Peri, Junghyun Kim, Hyunseok Kim, and Sungjin Ahn

International Conference on Machine Learning, 2021

Bib PDF

@article{SWB21,
  author = {Singh, Gautam and Peri, Skand and Kim, Junghyun and Kim, Hyunseok and Ahn, Sungjin},
  title = {Structured World Belief for Reinforcement Learning in POMDP},
  journal = {International Conference on Machine Learning},
  year = {2021},
}

ICML

Improving Generative Imagination in Object-Centric World Models

Zhixuan Lin, Yi-Fu Wu, Skand Peri, Bofeng Fu, Jindong Jiang, and Sungjin Ahn

International Conference on Machine Learning, 2020

Bib PDF Code Website

@article{GSWM20,
  author = {Lin, Zhixuan and Wu, Yi-Fu and Peri, Skand and Fu, Bofeng and Jiang, Jindong and Ahn, Sungjin},
  title = {Improving Generative Imagination in Object-Centric World Models},
  journal = {International Conference on Machine Learning},
  year = {2020},
}

ICLR

SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition

Zhixuan Lin*, Yi-Fu Wu*, Skand Peri*, Weihao Sun, Gautam Singh, Fei Deng, Jindong Jiang, and Sungjin Ahn

International Conference on Learning Representations, 2020

Bib PDF Code Website

@article{SPACE20,
  author = {Lin*, Zhixuan and Wu*, Yi-Fu and Peri*, Skand and Sun, Weihao and Singh, Gautam and Deng, Fei and Jiang, Jindong and Ahn, Sungjin},
  title = {SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition},
  journal = {International Conference on Learning Representations},
  year = {2020},
}

T-PAMI

Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection

Deepak Babu Sam*, Skand Peri*, M. N. Sundararaman, Amogh Kamath, and R. Venkatesh Babu

IEEE Transaction on Pattern Analysis and Machine Intelligence, 2020

Bib PDF Code

@article{LSCCNN,
  author = {Sam*, Deepak Babu and Peri*, Skand and Sundararaman, M. N. and Kamath, Amogh and Babu, R. Venkatesh},
  title = {Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection},
  journal = {IEEE Transaction on Pattern Analysis and Machine Intelligence},
  year = {2020},
}

WACV

Going Beyond the Regression Paradigm with Accurate Dot Prediction for Dense Crowds

Deepak Babu Sam*, Skand Peri*, M. N. Sundararaman, and R. Venkatesh Babu

Winter Conference on Applications of Computer Vision, 2020

Bib PDF

@article{DDCNN20,
  author = {Sam*, Deepak Babu and Peri*, Skand and Sundararaman, M. N. and Babu, R. Venkatesh},
  title = {Going Beyond the Regression Paradigm with Accurate Dot Prediction for Dense Crowds},
  journal = {Winter Conference on Applications of Computer Vision},
  year = {2020},
}

ACMMM

Deep Cross modal learning for Caricature Verification and Identification (CaVINet)

Jatin Garg, Skand Peri*, Himanshu Tolani, and Narayana.C Krishnan

ACM Multimedia, 2018

Bib PDF Code

@article{CaVINet_ACMMM18,
  author = {Garg, Jatin and Peri*, Skand and Tolani, Himanshu and Krishnan, Narayana.C},
  title = {Deep Cross modal learning for Caricature Verification and Identification (CaVINet)},
  journal = {ACM Multimedia},
  year = {2018},
}

MICCAI-W

MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net For Multi-Modal Alzheimer’s Classification

Apoorva Sikka, Skand Peri, and Deepti.R Bathula

MICCAI Workshop on Simulation and Synthesis in Medical Imaging, 2018

Bib PDF

@article{MRI2PET_MICCAI,
  author = {Sikka, Apoorva and Peri, Skand and Bathula, Deepti.R},
  title = { MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net For Multi-Modal Alzheimer's Classification},
  journal = {MICCAI Workshop on Simulation and Synthesis in Medical Imaging},
  year = {2018},
}

CVPR-W

DisguiseNet : A Contrastive Approach for Disguised Face Verification in the Wild

Skand Peri, and Abhinav Dhall

Computer Vision and Pattern Recognition Workshops (CVPRW), 2018

Bib PDF

@article{DisguiseNetCVPRW,
  author = {Peri, Skand and Dhall, Abhinav},
  title = {DisguiseNet : A Contrastive Approach for Disguised Face Verification in the Wild},
  journal = {Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year = {2018},
}