JD
Jiafei Duan
cs.ROcs.CVcs.AIcs.LGcs.HCcs.CLcs.GR
On Valency
published · living versionsW_n6r59p5c·v1 · currentpublished
Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models
with Jianman Lin, Shailesh Shailesh, Zhongyi Luo
1 version
Preprints & journals
41 papers in the corpus · 2020–2026Reflex: Visually Grounded Reactive Humanoid Control2610.12772v1 · Taoyang Jia, Weikai Huang, Linxin Song et al.2026 · 0 citationsarXiv
Grounded Action Model: 3D Grounding as a Foundation for Robotics2609.23863v2 · Gehao Zhang, Weikai Huang, Shailesh Shailesh et al.2026 · 0 citationsarXiv
Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models2609.12641v1 · Jianman Lin, Shailesh Shailesh, Zhongyi Luo et al.2026 · 0 citationsarXivon Valency
MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction2606.18558v2 · Jianing Zhang, Chenhao Zheng, Yajun Yang et al.2026 · 0 citationsarXiv
MolmoAct2: Action Reasoning Models for Real-world Deployment2605.02881v2 · Haoquan Fang, Jiafei Duan, Donovan Clay et al.2026 · 0 citationsarXiv
WildDet3D: Scaling Promptable 3D Detection in the Wild2604.08626v2 · Weikai Huang, Jieyu Zhang, Sijun Li et al.2026 · 0 citationsarXiv
MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation2603.16861v2 · Abhay Deshpande, Maya Guru, Rose Hendrix et al.2026 · 0 citationsarXiv
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics2602.19313v2 · Shirui Chen, Cole Harrison, Ying-Chun Lee et al.2026 · 0 citationsarXiv
MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation2602.11337v2 · Yejin Kim, Wilbert Pumacay, Omar Rayyan et al.2026 · 0 citationsarXiv
Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning2602.07845v1 · Yalcin Tur, Jalal Naghiyev, Haoquan Fang et al.2026 · 0 citationsarXiv
VLS: Steering Pretrained Robot Policies via Vision-Language Models2602.03973v1 · Shuo Liu, Ishneet Sukhvinder Singh, Yiqing Xu et al.2026 · 0 citationsarXiv
RoboCade: Gamifying Robot Data Collection2512.21235v3 · Suvir Mirchandani, Mia Tang, Jiafei Duan et al.2025 · 0 citationsarXiv
FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models2510.01642v4 · Zijun Lin, Jiafei Duan, Haoquan Fang et al.2025 · 0 citationsarXiv
MolmoAct: Action Reasoning Models that can Reason in Space2508.07917v4 · Jason Lee, Jiafei Duan, Haoquan Fang et al.2025 · 2 citationsarXiv
RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation2507.00435v2 · Yi Ru Wang, Carter Ung, Christopher Tan et al.2025 · 1 citationarXiv
GraspMolmo: Generalizable Task-Oriented Grasping via Large-Scale Synthetic Data Generation2505.13441v3 · Abhay Deshpande, Yuquan Deng, Arijit Ray et al.2025 · 0 citationsarXiv
PointArena: Probing Multimodal Grounding Through Language-Guided Pointing2505.09990v2 · Long Cheng, Jiafei Duan, Yi Ru Wang et al.2025 · 0 citationsarXiv
SAM2Act: Integrating Visual Foundation Model with A Memory Architecture for Robotic Manipulation2501.18564v4 · Haoquan Fang, Markus Grotz, Wilbert Pumacay et al.2025 · 0 citationsarXiv
SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models2412.07755v3 · Arijit Ray, Jiafei Duan, Ellis Brown et al.2024 · 0 citationsarXiv
AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation2410.00371v1 · Jiafei Duan, Wilbert Pumacay, Nishanth Kumar et al.2024 · 5 citationsarXiv
Manipulate-Anything: Automating Real-World Robots using Vision-Language Models2406.18915v3 · Jiafei Duan, Wentao Yuan, Wilbert Pumacay et al.2024 · 6 citationsarXiv
RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics2406.10721v1 · Wentao Yuan, Jiafei Duan, Valts Blukis et al.2024 · 7 citationsarXiv
Octopi: Object Property Reasoning with Large Tactile-Language Models2405.02794v2 · Samson Yu, Kelvin Lin, Anxing Xiao et al.2024 · 35 citationsarXiv
EVE: Enabling Anyone to Train Robots using Augmented Reality2404.06089v3 · Jun Wang, Chun-Cheng Chang, Jiafei Duan et al.2024 · 5 citationsarXiv
THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation2402.08191v2 · Wilbert Pumacay, Ishika Singh, Jiafei Duan et al.2024 · 29 citationsarXiv
Selective Visual Representations Improve Convergence and Generalization for Embodied AI2311.04193v2 · Ainaz Eftekhar, Kuo-Hao Zeng, Jiafei Duan et al.2023 · 4 citationsarXiv
NEWTON: Are Large Language Models Capable of Physical Reasoning?2310.07018v1 · Yi Ru Wang, Jiafei Duan, Dieter Fox et al.2023 · 14 citationsarXiv
AR2-D2:Training a Robot Without a Robot2306.13818v1 · Jiafei Duan, Yi Ru Wang, Mohit Shridhar et al.2023 · 1 citationarXiv
Read My Mind: A Multi-Modal Dataset for Human Belief Prediction2304.14501v1 · Jiafei Duan, Samson Yu, Nicholas Tan et al.2023 · 0 citationsarXiv
Robustness of Utilizing Feedback in Embodied Visual Navigation2303.15453v1 · Jenny Zhang, Samson Yu, Jiafei Duan et al.2023 · 1 citationarXiv
A Study of Comfortability between Interactive AI and Human2302.14360v1 · Yi Ru Wang, Jiafei Duan, Sidharth Talia et al.2023 · 3 citationsarXiv
BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios2206.10665v1 · Jiafei Duan, Samson Yu, Nicholas Tan et al.2022 · 2 citationsarXiv
Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation2206.10606v2 · Jenny Zhang, Samson Yu, Jiafei Duan et al.2022 · 3 citationsarXiv
ABCDE: An Agent-Based Cognitive Development Environment2206.04909v1 · Jieyi Ye, Jiafei Duan, Samson Yu et al.2022 · 0 citationsarXiv
A Survey on Machine Learning Approaches for Modelling Intuitive Physics2202.06481v3 · Jiafei Duan, Arijit Dasgupta, Jason Fischer et al.2022 · 15 citationsarXiv
A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories2111.08826v1 · Arijit Dasgupta, Jiafei Duan, Marcelo H. Ang Jr et al.2021 · 4 citationsarXiv
AVoE: A Synthetic 3D Dataset on Understanding Violation of Expectation for Artificial Cognition2110.05836v2 · Arijit Dasgupta, Jiafei Duan, Marcelo H. Ang Jr et al.2021 · 2 citationsarXiv
PIP: Physical Interaction Prediction via Mental Simulation with Span Selection2109.04683v3 · Jiafei Duan, Samson Yu, Soujanya Poria et al.2021 · 7 citationsarXiv
SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments2108.06180v1 · Jiafei Duan, Samson Yu Bai Jian, Cheston Tan2021 · 2 citationsarXiv
A Survey of Embodied AI: From Simulators to Research Tasks2103.04918v8 · Jiafei Duan, Samson Yu, Hui Li Tan et al.2021 · 400 citationsarXiv
Actionet: An Interactive End-To-End Platform For Task-Based Data Collection And Augmentation In 3D Environment2010.01357v1 · Jiafei Duan, Samson Yu, Hui Li Tan et al.2020 · 8 citationsarXiv
Career total: 47 works. 41 are in this corpus.
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.