ICL for Robotics

ICL: In-Context Learning

In-context learning for robotics studies how robots can acquire or adapt behaviors from examples, observations, and feedback supplied during use rather than by retraining their models. Common approaches condition vision-language-action policies on demonstrations, retrieve relevant episodes from memory, or use action effects and world models to infer how the robot and environment behave. These methods are tested on simulated and real manipulation, including long-horizon tasks, novel objects, contact-rich actions, and changing viewpoints, with some also addressing bimanual control and deformable objects. A central challenge is making context useful and compact enough for reliable adaptation while ensuring gains transfer across tasks, robots, and real-world conditions.

Latest papers

40 papers14 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

In-Context Learning World Models for Robot Dual-Arm Manipulation of Soft Garment with Partial Observations
Oct 22, 2026Hengyi Sim, Quentin Rouxel, Dennis Hong +2World Models for Robotics Robotic Manipulation
Collaborative and Versatile Robots (CLOVER) Laboratory, Department of Mechanical and Automation Engineering, T-Stone Robotics Institute, The Chinese University of Hong Kong, Hong Kong. · Department of Mechanical and Aerospace Engineering, University of California, Los Angeles, USA · Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy +1
Adaptive Aerial Loco-Manipulation Policy Learning via LLM-Assisted Proactive Task Generation
Oct 22, 2026Jingyu Ru, Xiangyuan Xie, Lixuan Jin +8Aerial Robotics Aerial Manipulation
Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China · National Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China · School of Artiﬁcial Intelligence, Nanjing University, Nanjing, China +1
PhysiCalWorld: In-Context Physics Calibration for World Models
Oct 21, 2026Yunhao Luo, Wentao He, Yinpei Dai +5World Models Action-Conditioned World Models
University of Michigan
Embodied Task Agents Can Perform Fine Manipulation through Tactile In-Context Learning
Oct 20, 2026Yubang Wang, Zezheng Huai, Yifei Zhang +8Robotic Manipulation ICL for Robotics
Fudan University · Shanghai Innovation Institute · Tencent +3
Has GPT-6-Astra Achieved Embodied Intelligence?
Oct 15, 2026SenseNova, Joint Research Team, Zhongang Cai +59Embodied AI Agentic AI for Robotics
LTM: Latent Transition Based In-Context Memory for Vision-Language-Action Models
Oct 15, 2026Qixin Sun, WenLong Gao, Xiansheng Chen +3Memory-Augmented VLMs ICL for Robotics
Beihang University · BAAI
Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution
Oct 14, 2026Yunze Liu, Jing Wang, Shenrui Wu +16Vision-Language-Action Models ICL for Robotics
NVIDIA · UCB · MIT +2
Contact Trajectory Prompting: In-Context Transfer of Contact-Rich Behaviors from a Single Demonstration
Oct 13, 2026Xian Nie, Yujie Zang, Yuhang Zheng +8Contact-Rich Robotic Manipulation Robot Imitation Learning
Shanghai Jiao Tong University · TARS Robotics · National University of Singapore +2
Can a Frontier VLM Serve as a Robot Policy for Memory-Dependent Manipulation?
Oct 12, 2026Jack B. Jedlicki, Amish Sethi, Heng YangRobotic Manipulation Long-Horizon Robotic Manipulation
Harvard University
Recursive Video In-Context Learning for Agentic Robot
Oct 5, 2026Wenrui Bao, Xinxin Liu, Bingxin Xu +1ICL for Robotics Robotic Manipulation
University of Central Florida · University of Southern California
Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation
Oct 1, 2026Shukai Gong, Xuanran Zhai, Yintianrun Zhang +16Long-Horizon Robotic Manipulation Robotic Manipulation
Peking University
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks
Sep 29, 2026Minxing Li, Minghao Han, Weizhi Zhao +10ICL for Robotics Robotic Manipulation
NLPR, Institute of Automation, Chinese Academy of Sciences (CASIA) · Amap, Alibaba Group
In-Context Learning for Robots: Methods and Applications
Sep 28, 2026Haojian Huang, Zexi Li, Junhao Guo +36ICL for Robotics Generalization in Robotic Manipulation
Knowin AI · HKUST(GZ) · The Chinese University of Hong Kong +5
RoboICL: Embodied In-Context Learning with GPT-6 Astra
Sep 28, 2026Fangcheng Liu, Yeqing Shen, Anda Cheng +7Robotic Control ICL for Robotics
Samsung Research, Beijing, China · Samsung Robotics eXperience · Shanghai Jiao Tong University
Robot Manipulation with GPT-6-Astra: Body Knowledge, Experience Reuse, Emergent Skills, and Sim2Real Transfer
Sep 24, 2026Sida He, Lingxi Xie, Yunning Cao +6Robotic Manipulation Robot Skill Learning
Huawei Inc., China
Zeva-Ego: Egocentric Mid-Training with In-Context Causal Learning for Robot Manipulation
Sep 21, 2026Bingjia Huang, Xin Ding, Fu Chen +5ICL for Robotics Robot Policy Adaptation
Institute for AI Industry Research (AIR), Tsinghua University; Z-Trans AI
RopeFormer: Cross-Trial Adaptation from Interaction History for Dynamic Rope Manipulation
Sep 20, 2026Menglin Wu, Kaixiang Yao, Shangbo Luan +2ICL for Robotics Deformable Object Manipulation
University of California, Berkeley · Xi’an Jiaotong University · Southern University of Science and Technology +1
Transferring the Intelligence of VLMs to Robotic Control
Sep 19, 2026Meng-Hao Guo, Zhe-Han Mo, Jia-Jun Wang +6VLMs for Robotics Zero-Shot Robotic Manipulation
Tsinghua University · Tencent Hunyuan
In-Context Robot Learning with VLM Agents
Sep 16, 2026Dongzhou Cheng, Taoran Yi, Ye Fang +12Robot Policy Learning ICL for Robotics
Morphi Robot · Shanghai Innovation Institute · Huazhong University of Science and Technology +7
ContextFlow: In-Context Flow Matching for Robot Manipulation
Sep 6, 2026Jian Ding, Xianjie Dai, Roei Herzig +5ICL for Robotics Robot Imitation Learning
KAUST, Thuwal, Saudi Arabia · University of California, Berkeley, USA · Zurich, Switzerland
Zeva: In-Context Causal Learning for Generalizable Embodied Manipulation
Aug 31, 2026Fu Chen, Xin Ding, Bingjia Huang +8Robot Policy Learning ICL for Robotics
Institute for AI Industry Research (AIR), Tsinghua University
Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization
Aug 26, 2026Jiaming Zhou, Qihang Zhang, Gangwei Xu +9Zero-Shot Robotic Manipulation Generalization in Robotic Manipulation
Robbyant · HKUST (GZ) · HKUST
RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
Aug 26, 2026Sanghwan Jang, Minjin Jeon, Minsoo Kim +3Test-Time Adaptation of VLA Models Vision-Language-Action Models
Department of Computer Science and Engineering, POSTECH, Pohang, South Korea · Graduate School of Artificial Intelligence, POSTECH, Pohang, South Korea
MatchingPolicy: Correspondence-Aware Policy Enables Cross-Object In-Context Learning
Aug 17, 2026Qijin She, Hanyang Yu, Zeming Li +1Robot Imitation Learning ICL for Robotics
Hong Kong University of Science and Technology Hong Kong SAR, China
In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use
Aug 6, 2026Jiarui Yang, Wen Huang, Jiale Zhang +2Reasoning for VLA Models ICL for Robotics
Nankai University · Tsinghua University · Swiss Federal Institute of Technology in Lausanne (EPFL)
WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory and In-Context Learning
Jul 21, 2026Haisheng Su, Zongdai Liu, Xin Jin +13ICL for Robotics World Model Learning
Manifold AI · Tsinghua University · Shanghai Jiao Tong University
In-Context World Modeling for Robotic Control
Jun 24, 2026Siyin Wang, Junhao Shi, Senyu Fei +4ICL for Robotics World Model Learning
1Fudan University · 2Shanghai Innovation Institute · 3Tongji University
Reflective VLA: In-Context Action Consequences Make VLAs Generalize
Jun 23, 2026Qing Lian, Kent Yu, Lei ZhangICL for Robotics Generalization in Robotic Manipulation
Futian Laboratory · International Digital Economy Academy (IDEA) · Visincept
VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network
Jun 10, 2026Song Chen, Linyan Xiang, Ying Zhou +1ICL for Robotics Language-Conditioned Robot Manipulation
National University of Singapore
SynthICL: Scalable In-context Imitation Learning with Synthetic Data
Jun 6, 2026Cheng Qian, Ruomeng Fan, Yifei Ren +2ICL for Robotics Robot Skill Learning
The Robot Learning Lab Imperial College London

Oct 22, 2026J/K move · Enter open · S save

In-Context Learning World Models for Robot Dual-Arm Manipulation of Soft Garment with Partial Observations

Hengyi Sim, Quentin Rouxel, Dennis Hong, Darwin Caldwell+1

Collaborative and Versatile Robots (CLOVER) Laboratory, Department of Mechanical and Automation Engineering, T-Stone Robotics Institute, The Chinese University of Hong Kong, Hong Kong. · Department of Mechanical and Aerospace Engineering, University of California, Los Angeles, USA · Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy+1

World Models for Robotics Robotic Manipulation Robot State Estimation ICL for Robotics Cross-Embodiment Robot Learning

Open paper AskPDF arXiv

Robust manipulation of soft objects, such as garments, is a critical skill for service and household robots to adopt, but remains challenging due to its high-dimensional state space, and material-dependent deformations. Humans address this challenge by using mental world models that "imagine" the shape and material properties from partial observations, which enables them to predict how actions affect future states. As such, embedding such world models in robots allows for better generalization in manipulating a wide variety of garments in the real world. However, learned world models typically require large amounts of real world data that is strenuous to collect, and a mechanism to infer latent properties that govern dynamics. We present a Soft-Object World Model that performs generative full-state estimation and action-conditioned dynamics prediction using a transformer backbone trained on large-scale simulated soft object interactions, with measures to mitigate the sim-to-real gap. By learning to infer latent shape and material cues through in-context learning over a variable-length partial point-cloud history, the model generalizes across robot embodiments, material parameters, garment types and shapes, and manipulation coordination modes without weight updates. The world model is then integrated with a Goal-Conditioned action planner for motion synthesis. We validate the approach in simulation and real world for bimanual garment folding, reporting improvements in reconstruction fidelity, prediction accuracy, and task success.