Related papers: Self-Improving Embodied Foundation Models

We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across 17 embodied AI…

In recent years, Multi-modal Foundation Models (MFMs) and Embodied Artificial Intelligence (EAI) have been advancing side by side at an unprecedented pace. The integration of the two has garnered significant attention from the AI research…

The realization of Artificial General Intelligence (AGI) necessitates Embodied AI agents capable of robust spatial perception, effective task planning, and adaptive execution in physical environments. However, current large language models…

Humans can perceive and reason about spatial relationships from sequential visual observations, such as egocentric video streams. However, how pretrained models acquire such abilities, especially high-level reasoning, remains unclear. This…

Supervised fine-tuning (SFT) of foundation models often leads to poor generalization, where prior capabilities deteriorate after tuning on new tasks or domains. Inspired by trust-region policy optimization (TRPO) and proximal policy…

The performance of learned robot visuomotor policies is heavily dependent on the size and quality of the training dataset. Although large-scale robot and human datasets are increasingly available, embodiment gaps and mismatched action…

Supervised fine-tuning (SFT) is a critical step in aligning large language models (LLMs) with human instructions and values, yet many aspects of SFT remain poorly understood. We trained a wide range of base models on a variety of datasets…

Foundation models encode rich representations that can be adapted to downstream tasks by fine-tuning. However, fine-tuning a model on one data distribution often degrades performance under distribution shifts. Current approaches to robust…

Automatic code generation has been a longstanding research topic. With the advancement of general-purpose large language models (LLMs), the ability to code stands out as one important measure to the model's reasoning performance. Usually, a…

The power of foundation models (FMs) lies in their capacity to learn highly expressive representations that can be adapted to a broad spectrum of tasks. However, these pretrained models require additional training stages to become effective…

Following its success in natural language processing and computer vision, foundation models that are pre-trained on large-scale multi-task datasets have also shown great potential in robotics. However, most existing robot foundation models…

We propose a promising neural network model with which to acquire a grounded representation of robot actions and the linguistic descriptions thereof. Properly responding to various linguistic expressions, including polysemous words, is an…

Multi-stage training and knowledge transfer, from a large-scale pretraining task to various finetuning tasks, have revolutionized natural language processing and computer vision resulting in state-of-the-art performance improvements. In…

Imitation learning is a widely used approach for training agents to replicate expert behavior in complex decision-making tasks. However, existing methods often struggle with compounding errors and limited generalization, due to the inherent…

Pre-trained Large Language Model (LLM) exhibits broad capabilities, yet, for specific tasks or domains their attainment of higher accuracy and more reliable reasoning generally depends on post-training through Supervised Fine-Tuning (SFT)…

Reinforcement learning (RL) has proven effective in incentivizing the reasoning abilities of large language models (LLMs), but suffers from severe efficiency challenges due to its trial-and-error nature. While the common practice employs…

Self-alignment is an effective way to reduce the cost of human annotation while ensuring promising model capability. However, most current methods complete the data collection and training steps in a single round, which may overlook the…

Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we…

Improving Multi-modal Large Language Models (MLLMs) in the post-training stage typically relies on supervised fine-tuning (SFT) or reinforcement learning (RL), which require expensive and manually annotated multi-modal data--an ultimately…

This paper presents a modality-augmented fine-tuning framework designed to adapt foundation robot policies to diverse humanoid embodiments. We validate our approach across two distinct settings: (i) the GR1 embodiment, utilizing public…