English
Related papers

Related papers: Self-Improving Embodied Foundation Models

200 papers

Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs), notably enhancing their capacity to acquire domain-specific knowledge while preserving or potentially augmenting their general-purpose…

Machine Learning · Computer Science 2026-03-31 Ali Taheri , Alireza Taban , Qizhou Wang , Shanshan Ye , Abdolreza Mirzaei , Tongliang Liu , Bo Han

Large Language Models (LLMs) are pretrained on massive datasets and later instruction-tuned via supervised fine-tuning (SFT) or reinforcement learning (RL). Best practices emphasize large, diverse pretraining data, whereas post-training…

Machine Learning · Computer Science 2026-03-03 Adel Javanmard , Baharan Mirzasoleiman , Vahab Mirrokni

Fine-tuning (FT) pre-trained sentence embedding models on small datasets has been shown to have limitations. In this paper we show that concatenating the embeddings from the pre-trained model with those from a simple sentence embedding…

Computation and Language · Computer Science 2020-10-06 Siddhant Garg , Rohit Kumar Sharma , Yingyu Liang

Foundation models have demonstrated a great ability to achieve general human-level intelligence far beyond traditional approaches. As the technique keeps attracting attention from the AI community, an increasing number of foundation models…

Computation and Language · Computer Science 2024-05-07 Shizhe Diao , Rui Pan , Hanze Dong , Ka Shun Shum , Jipeng Zhang , Wei Xiong , Tong Zhang

Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy fine-tuning data at the expense of the high-entropy pretraining distribution.…

Machine learning models underpin many modern financial systems for use cases such as fraud detection and churn prediction. Most are based on supervised learning with hand-engineered features, which relies heavily on the availability of…

Machine Learning · Computer Science 2024-01-05 Piotr Skalski , David Sutton , Stuart Burrell , Iker Perez , Jason Wong

Background and objective: Employing deep learning models in critical domains such as medical imaging poses challenges associated with the limited availability of training data. We present a strategy for improving the performance and…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Eva Pachetti , Sotirios A. Tsaftaris , Sara Colantonio

Imitation learning for robotic manipulation faces a fundamental challenge: the scarcity of large-scale, high-quality robot demonstration data. Recent robotic foundation models often pre-train on cross-embodiment robot datasets to increase…

Robotics · Computer Science 2025-08-04 Hongzhe Bi , Lingxuan Wu , Tianwei Lin , Hengkai Tan , Zhizhong Su , Hang Su , Jun Zhu

Humanoid robots are envisioned as embodied intelligent agents capable of performing a wide range of human-level loco-manipulation tasks, particularly in scenarios requiring strenuous and repetitive labor. However, learning these skills is…

Robotics · Computer Science 2024-12-20 Junjia Liu , Zhuo Li , Minghao Yu , Zhipeng Dong , Sylvain Calinon , Darwin Caldwell , Fei Chen

There are several challenges in developing a model for multi-tasking humanoid control. Reinforcement learning and imitation learning approaches are quite popular in this domain. However, there is a trade-off between the two. Reinforcement…

Robotics · Computer Science 2024-06-18 Siddharth Padmanabhan , Kazuki Miyazawa , Takato Horii , Takayuki Nagai

Many healthcare applications are inherently multimodal, involving several physiological signals. As sensors for these signals become more common, improving machine learning methods for multimodal healthcare data is crucial. Pretraining…

Machine Learning · Computer Science 2024-10-23 Ching Fang , Christopher Sandino , Behrooz Mahasseni , Juri Minxha , Hadi Pouransari , Erdrin Azemi , Ali Moin , Ellen Zippi

The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…

Computation and Language · Computer Science 2025-12-24 Xiang Chen , Yixin Ou , Quan Feng , Lei Li , Piji Li , Haibo Ye , Sheng-Jun Huang , Shuofei Qiao , Shumin Deng , Huajun Chen , Ningyu Zhang

Federated Learning (FL) enables decentralized, privacy-preserving model training but struggles to balance global generalization and local personalization due to non-identical data distributions across clients. Personalized Fine-Tuning…

Machine Learning · Computer Science 2025-12-30 Minghui Chen , Hrad Ghoukasian , Ruinan Jin , Zehua Wang , Sai Praneeth Karimireddy , Xiaoxiao Li

Multimodal learning, especially large-scale multimodal pre-training, has developed rapidly over the past few years and led to the greatest advances in artificial intelligence (AI). Despite its effectiveness, understanding the underlying…

Neural and Evolutionary Computing · Computer Science 2022-08-18 Haoyu Lu , Qiongyi Zhou , Nanyi Fei , Zhiwu Lu , Mingyu Ding , Jingyuan Wen , Changde Du , Xin Zhao , Hao Sun , Huiguang He , Ji-Rong Wen

The evolution of machine learning has increasingly prioritized the development of powerful models and more scalable supervision signals. However, the emergence of foundation models presents significant challenges in providing effective…

Artificial Intelligence · Computer Science 2024-11-19 Xinyan Guan , Yanjiang Liu , Xinyu Lu , Boxi Cao , Ben He , Xianpei Han , Le Sun , Jie Lou , Bowen Yu , Yaojie Lu , Hongyu Lin

Imitation learning has emerged as an effective approach for bootstrapping sequential decision-making in robotics, achieving strong performance even in high-dimensional dexterous manipulation tasks. Recent behavior cloning methods further…

Robotics · Computer Science 2026-02-06 Entong Su , Tyler Westenbroek , Anusha Nagabandi , Abhishek Gupta

Humanoid locomotion is a challenging task due to its inherent complexity and high-dimensional dynamics, as well as the need to adapt to diverse and unpredictable environments. In this work, we introduce a novel learning framework for…

Robotics · Computer Science 2025-10-16 Hyunyoung Jung , Zhaoyuan Gu , Ye Zhao , Hae-Won Park , Sehoon Ha

Reinforcement fine-tuning (RFT) has become a core paradigm for post-training large language models, yet its training process remains highly fragile. Existing efforts mainly improve reliability at the system level or address specific issues…

Software Engineering · Computer Science 2026-05-07 Lingzhe Zhang , Tong Jia , Yunpeng Zhai , Liancheng Fang , Kening Zheng , Hongyi Liu , Xiaosong Huang , Philip S. Yu , Ying Li

We present EmbodiedMAE, a unified 3D multi-modal representation for robot manipulation. Current approaches suffer from significant domain gaps between training datasets and robot manipulation tasks, while also lacking model architectures…

Robotics · Computer Science 2025-05-16 Zibin Dong , Fei Ni , Yifu Yuan , Yinchuan Li , Jianye Hao

We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form…