English
Related papers

Related papers: Self-Improving Embodied Foundation Models

200 papers

Recent progress in (multimodal) large language models ((M)LLMs) has shifted focus from pre-training to inference-time computation and post-training optimization, largely due to concerns over the availability of high-quality human data.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Xiaoying Zhang , Da Peng , Yipeng Zhang , Zonghao Guo , Chengyue Wu , Jen-Tse Huang , Chi Chen , Wei Ke , Helen Meng , Maosong Sun

The proliferation of Large Language Models (LLMs) has s fueled a shift in robot learning from automation towards general embodied Artificial Intelligence (AI). Adopting foundation models together with traditional learning methods to robot…

Robotics · Computer Science 2023-11-27 Xuan Xiao , Jiahang Liu , Zhipeng Wang , Yanmin Zhou , Yong Qi , Qian Cheng , Bin He , Shuo Jiang

Recent robot foundation models largely rely on large-scale behavior cloning, which imitates expert actions but discards transferable dynamics knowledge embedded in heterogeneous embodied data. While the Unified World Model (UWM) formulation…

Pretrained foundation models learn embeddings that can be used for a wide range of downstream tasks. These embeddings optimise general performance, and if insufficiently accurate at a specific task the model can be fine-tuned to improve…

Machine Learning · Computer Science 2025-02-20 Matthew P. Wilson , Edward O. Pyzer-Knapp , Nicolas Galichet , Luke Dicks

While large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content, a significant gap remains between their pretraining performance and real-world deployment…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Zeyue Xue , Siming Fu , Jie Huang , Shuai Lu , Haoran Li , Yijun Liu , Yuming Li , Xiaoxuan He , Mengzhao Chen , Haoyang Huang , Nan Duan , Ping Luo

Improving data utilization, especially for imperfect data from task failures, is crucial for robotic manipulation due to the challenging, time-consuming, and expensive data collection process in the real world. Current imitation learning…

Robotics · Computer Science 2026-02-24 Kun Wu , Ning Liu , Zhen Zhao , Di Qiu , Jinming Li , Zhengping Che , Zhiyuan Xu , Jian Tang

The rapid advancement of autonomous systems, including self-driving vehicles and drones, has intensified the need to forge true Spatial Intelligence from multi-modal onboard sensor data. While foundation models excel in single-modal…

Computer Vision and Pattern Recognition · Computer Science 2026-01-09 Song Wang , Lingdong Kong , Xiaolu Liu , Hao Shi , Wentong Li , Jianke Zhu , Steven C. H. Hoi

Behavior Cloning (BC) on curated (or filtered) data is the predominant paradigm for supervised fine-tuning (SFT) of large language models; as well as for imitation learning of control policies. Here, we draw on a connection between this…

Machine Learning · Computer Science 2025-09-09 Chongli Qin , Jost Tobias Springenberg

Autonomous self-improving robots that interact and improve with experience are key to the real-world deployment of robotic systems. In this paper, we propose an online learning method, SELFI, that leverages online robot experience to…

Robotics · Computer Science 2024-10-08 Noriaki Hirose , Dhruv Shah , Kyle Stachowicz , Ajay Sridhar , Sergey Levine

Pretrained foundation models offer substantial benefits for a wide range of downstream tasks, which can be one of the most potential techniques to access artificial general intelligence. However, scaling up foundation transformers for…

Machine Learning · Computer Science 2024-06-21 Xingrun Xing , Li Du , Xinyuan Wang , Xianlin Zeng , Yequan Wang , Zheng Zhang , Jiajun Zhang

Recent years in robotics and imitation learning have shown remarkable progress in training large-scale foundation models by leveraging data across a multitude of embodiments. The success of such policies might lead us to wonder: just how…

Multi-Modal Self-Supervised Learning from videos has been shown to improve model's performance on various downstream tasks. However, such Self-Supervised pre-training requires large batch sizes and a large amount of computation resources…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Duo Wang , Salah Karout

Supervised fine-tuning (SFT) on domain-specific data is the dominant approach for adapting foundation models to specialized tasks. However, it has been observed that SFT models tend to forget knowledge acquired during pretraining. In vision…

Artificial Intelligence · Computer Science 2025-06-03 Yifan Hao , Xingyuan Pan , Hanning Zhang , Chenlu Ye , Rui Pan , Tong Zhang

As embodied AI systems become increasingly multi-modal, personalized, and interactive, they must learn effectively from diverse sensory inputs, adapt continually to user preferences, and operate safely under resource and privacy…

Federated fine-tuning enables Large Language Models (LLMs) to adapt to downstream tasks while preserving data privacy, but its resource-intensive nature limits deployment on edge devices. In this paper, we introduce Developmental Federated…

Machine Learning · Computer Science 2025-08-04 Yebo Wu , Jingguang Li , Zhijiang Guo , Li Li

It has always been expected that a robot can be easily deployed to unknown scenarios, accomplishing robotic grasping tasks without human intervention. Nevertheless, existing grasp detection approaches are typically off-body techniques and…

Robotics · Computer Science 2025-04-08 Jin Liu , Jialong Xie , Leibing Xiao , Chaoqun Wang , Fengyu Zhou

Foundation models have shown great success in natural language processing, computer vision, and multimodal tasks. FMs have a large number of model parameters, thus requiring a substantial amount of data to help optimize the model during the…

Machine Learning · Computer Science 2023-12-27 Panlong Wu , Kangshuo Li , Ting Wang , Fangxin Wang

If a model has some behavioral tendency, such as sycophancy or misalignment, and it is trained on its own outputs, will the tendency be amplified in the next generation of models? We study this question by training a series of models where…

Artificial Intelligence · Computer Science 2026-05-05 Zephaniah Roe , Jack Sanderson , Dang Nguyen , Julian Huang , Todd Nief , Aryan Shrivastava , Chenhao Tan , Ari Holtzman

Embodied AI represents a paradigm in AI research where artificial agents are situated within and interact with physical or virtual environments. Despite the recent progress in Embodied AI, it is still very challenging to learn the…

Robotics · Computer Science 2024-10-10 Xuetao Li , Fang Gao , Jun Yu , Shaodong Li , Feng Shuang

Embodied intelligence seamlessly integrates vision, language, and action.~However, most multimodal robotic models rely on massive fine-tuning, incurring high time and hardware costs.~To address this, we introduce RoboBERT, an end-to-end…

Robotics · Computer Science 2025-05-02 Sicheng Wang , Sheng Liu , Weiheng Wang , Jianhua Shan , Bin Fang