Jun Jin — accepted AI-conference papers

2026

CAPE: Context-Aware Diffusion Policy Via Proximal Mode Expansion for Collision Avoidance

Rui Heng Yang, Xuan Zhao, Léo Maxime Brunswic, Montgomery Tucker Alban, Matéo Clémente, Tongtong Cao +2

ICRA 2026poster

In robotics, diffusion models can capture multi-modal trajectories from demonstrations, making them a transformative approach in imitation learning. However, achieving optimal performance following this regiment requires a large-scale dataset, which is costly to obtain, especially for challenging ta…

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning

Ke Sun, Hongming Zhang, Jun Jin, Chao Gao, Xi Chen, Wulong Liu +1

ICLR 2026poster

Inspired by the human learning and memory system, particularly the interplay between the hippocampus and cerebral cortex, this study proposes a dual-learner framework comprising a fast learner and a meta learner to address continual Reinforcement Learning~(RL) problems. These two learners are couple…

Cited by 0 Source ↗Scholar ↗

2025

RA-DP: Rapid Adaptive Diffusion Policy for Training-Free High-frequency Robotics Replanning

Xi Ye, Rui Heng Yang, Jun Jin, Yinchuan Li, Amir Rasouli

IROS 2025

Diffusion models exhibit impressive scalability in robotic task learning, yet they struggle to adapt to novel, highly dynamic environments. This limitation primarily stems from their constrained replanning ability: they either operate at a low frequency due to a time-consuming iterative sampling pro

Cited by 5 Source ↗Scholar ↗

2025

Towards the Efficient Inference by Incorporating Automated Computational Phenotypes under Covariate Shift

chao ying, Jun Jin, Yi Guo, Xiudi Li, Muxuan Liang, Jiwei Zhao

ICML 2025poster

Collecting gold-standard phenotype data via manual extraction is typically labor-intensive and slow, whereas automated computational phenotypes (ACPs) offer a systematic and much faster alternative. However, simply replacing the gold-standard with ACPs, without acknowledging their differences, could…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

Dynamic Decision Frequency with Continuous Options

Amirmohammad Karimi, Jun Jin, Jun Luo, A. Rupam Mahmood, Martin Jagersand, Samuele Tosatto

IROS 2023poster

In classic reinforcement learning algorithms, agents make decisions at discrete and fixed time intervals. The duration between decisions becomes a crucial hyperparameter, as setting it too short may increase the problem's difficulty by requiring the agent to make numerous decisions to achieve its go…

Cited by 9 Source ↗code ↗Scholar ↗

2023

EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought

Yao Mu, Qinglong Zhang, Mengkang Hu, Wenhai Wang, Mingyu Ding, Jun Jin +4

NeurIPS 2023spotlight

Embodied AI is a crucial frontier in robotics, capable of planning and executing action sequences for robots to accomplish long-horizon tasks in physical environments. In this work, we introduce EmbodiedGPT, an end-to-end multi-modal foundation model for embodied AI, empowering embodied agents with…

Cited by 246 Source ↗PDF ↗Scholar ↗

2023

Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay

Hongming Zhang, Chenjun Xiao, Han Wang, Jun Jin, bo xu, Martin Müller

ICLR 2023poster

Experience replay, which stores transitions in a replay memory for repeated use, plays an important role of improving sample efficiency in reinforcement learning. Existing techniques such as reweighted sampling, episodic learning and reverse sweep update further process the information in the replay…

Cited by 11 Source ↗PDF ↗Scholar ↗

2022

A Quantitative Analysis of Activities of Daily Living: Insights into Improving Functional Independence with Assistive Robotics

Laura Petrich, Jun Jin, Masood Dehghan, Martin Jagersand

ICRA 2022poster

Wheelchair-mounted robotic manipulators have the potential to help the elderly and individuals living with disabilities carry out their activities of daily living (ADLs) independently. Robotics researchers focus on assistive tasks from the perspective of various control schemes and motion types, whe…

Cited by 24 Source ↗Scholar ↗

2022

A Simple Decentralized Cross-Entropy Method

Zichen Zhang, Jun Jin, Martin Jagersand, Jun Luo, Dale Schuurmans

NeurIPS 2022accept

Cross-Entropy Method (CEM) is commonly used for planning in model-based reinforcement learning (MBRL) where a centralized approach is typically utilized to update the sampling distribution based on only the top-$k$ operation's results on samples. In this paper, we show that such a centralized approa…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2022

Generalizable task representation learning from human demonstration videos: a geometric approach

Jun Jin, Martin Jagersand

ICRA 2022poster

We study the problem of generalizable task learning from human demonstration videos without extra training on the robot or pre-recorded robot motions. Given a set of human demonstration videos showing a task with different objects/tools (categorical objects), we aim to learn a representation of visu…

Cited by 5 Source ↗Scholar ↗

2022

Offline Learning of Counterfactual Predictions for Real-World Robotic Reinforcement Learning

Jun Jin, Daniel Graves, Cameron Haigh, Jun Luo, Martin Jagersand

ICRA 2022poster

We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills. We aim to train a policy that maps multimodal sensory observations (vision and force) to a manipulator's joint velocities under practical considerations. We p…

Cited by 7 Source ↗Scholar ↗

2021

A Generative Model-Based Predictive Display for Robotic Teleoperation

Bowen Xie, Mingjie Han, Jun Jin, Martin Barczyk, Martin Jägersand

ICRA 2021poster

We propose a new generative model-based predictive display for robotic teleoperation over high-latency communication links. Our method is capable of rendering photo-realistic images of the scene to the human operator in real time from RGB-D images acquired by the remote robot. A preliminary explorat…

Cited by 4 Source ↗Scholar ↗

2021

Learning robust driving policies without online exploration

Daniel Graves, Nhat M. Nguyen, Kimia Hassanzadeh, Jun Jin, Jun Luo

ICRA 2021poster

We propose a multi-time-scale predictive representation learning method to efficiently learn robust driving policies in an offline manner that generalize well to novel road geometries, and damaged and distracting lane conditions which are not covered in the offline training data. We show that our pr…

Cited by 2 Source ↗Scholar ↗

2020

A Geometric Perspective on Visual Imitation Learning

Jun Jin, Laura Petrich, Masood Dehghan, Martin Jagersand

IROS 2020poster

We consider the problem of visual imitation learning without human kinesthetic teaching or teleoperation, nor access to an interactive reinforcement learning training environment. We present a geometric perspective to this problem where geometric feature correspondences are learned from one training…

Cited by 22 Source ↗Scholar ↗

2020

Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans

Jun Jin, Nhat M. Nguyen, Nazmus Sakib, Daniel Graves, Hengshuai Yao, Martin Jagersand

ICRA 2020poster

We consider the problem of mapless collision-avoidance navigation where humans are present using 2D laser scans. Our proposed method uses ego-safety to measure collision from the robot's perspective and social-safety to measure the impact of robot's actions on surrounding pedestrians. Specifically,…

Cited by 81 Source ↗Scholar ↗

2020

Visual Geometric Skill Inference by Watching Human Demonstration

Jun Jin, Laura Petrich, Zichen Zhang, Masood Dehghan, Martin Jagersand

ICRA 2020poster

We study the problem of learning manipulation skills from human demonstration video by inferring the association relationships between geometric features. Motivation for this work stems from the observation that humans perform eye-hand coordination tasks by using geometric primitives to define a tas…

Cited by 12 Source ↗Scholar ↗

2019

Online Object and Task Learning via Human Robot Interaction

Masood Dehghan, Zichen Zhang, Mennatullah Siam, Jun Jin, Laura Petrich, Martin Jagersand

ICRA 2019poster

This work describes the development of a robotic system that acquires knowledge incrementally through human interaction where new objects and motions are taught on the fly. The robotic system developed was one of the five finalists in the KUKA Innovation Award competition and demonstrated during the…

Cited by 32 Source ↗Scholar ↗

2019

Robot eye-hand coordination learning by watching human demonstrations: a task function approximation approach

Jun Jin, Laura Petrich, Masood Dehghan, Zichen Zhang, Martin Jagersand

ICRA 2019poster

We present a robot eye-hand coordination learning method that can directly learn visual task specification by watching human demonstrations. Task specification is represented as a task function, which is learned using inverse reinforcement learning(IRL [1]) by inferring a reward model from state tra…

Cited by 19 Source ↗Scholar ↗

2018

Real-Time Edge Template Tracking via Homography Estimation

Xuebin Qin, Shida He, Zichen Zhang, Masood Dehghan, Jun Jin, Martin Jagersand

IROS 2018poster

In this paper, we propose a novel real-time method for tracking planar edge templates. This method tracks an edge template by estimating its homography transformations with respect to the sampled edge pixels detected from the incoming frames. Particularly, we define a cost function based on a new fe…

Cited by 1 Source ↗Scholar ↗