Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization

• URL: http://arxiv.org/abs/2511.16602v1
• Date: Thu, 20 Nov 2025 17:58:04 GMT
• Title: Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization
• Authors: Yi Zhang, Che Liu, Xiancong Ren, Hanchu Ni, Yingji Zhang, Shuai Zhang, Zeyuan Ding, Jiayu Hu, Haozhe Shan, Junbo Qi, Yan Bai, Dengjie Li, Jiachen Luo, Yidong Wang, Yong Dai, Zenglin Xu, Bin Shen, Qifan Wang, Jian Tang, Xiaozhu Ju,
• Abstract summary: Deliberate Practice Policy Optimization (DPPO) is a metacognitive Metaloop'' training framework.<n>DPPO alternates between supervised fine-tuning (competence expansion) and reinforcement learning (skill refinement)<n> Empirically, training a vision-language embodied model with DPPO, referred to as Pelican-VL 1.0, yields a 20.3% performance improvement over the base model.<n>We are open-sourcing both the models and code, providing the first systematic framework that alleviates the data and resource bottleneck.
• Score: 72.20212909644017
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Developing a universal and versatile embodied intelligence system presents two primary challenges: the critical embodied data bottleneck, where real-world data is scarce and expensive, and the algorithmic inefficiency of existing methods, which are resource-prohibitive. To address these limitations, we introduce Deliberate Practice Policy Optimization (DPPO), a metacognitive ``Metaloop'' training framework that dynamically alternates between supervised fine-tuning (competence expansion) and reinforcement learning (skill refinement). This enables automatic weakness identification and targeted resource allocation, specifically designed to maximize learning efficiency from sparse, finite data. Theoretically, DPPO can be formalised as a unified preference-learning framework. Empirically, training a vision-language embodied model with DPPO, referred to as Pelican-VL 1.0, yields a 20.3% performance improvement over the base model and surpasses open-source models at the 100B-parameter scale by 10.6%. We are open-sourcing both the models and code, providing the first systematic framework that alleviates the data and resource bottleneck and enables the community to build versatile embodied agents efficiently.

Related papers

• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• PCMind-2.1-Kaiyuan-2B Technical Report [31.709484756045587]
  We introduce PCMind-2.1-Kaiyuan-2B, a fully open-source 2-billion- parameter model focused on improving training efficiency and effectiveness under resource constraints.<n>Our methodology includes three key innovations: a Quantile Data Benchmarking method for systematically comparing heterogeneous open-source datasets.<n>We release all assets (including model weights, data, and code) under Apache 2.0 license at https://huggingface.co/thu-pacman/PCMind-2.1-Kaiyuan-2B.
  arXiv  Detail & Related papers  (2025-12-08T15:00:10Z)
• EmbodiedBrain: Expanding Performance Boundaries of Task Planning for Embodied Intelligence [17.644658293987955]
  Embodied AI agents are capable of robust spatial perception, effective task planning, and adaptive execution in physical environments.<n>Current large language models (LLMs) and multimodal LLMs (MLLMs) for embodied tasks suffer from key limitations.<n>We propose EmbodiedBrain, a novel vision-language foundation model available in both 7B and 32B parameter sizes.
  arXiv  Detail & Related papers  (2025-10-23T14:05:55Z)
• RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 [20.92548890511589]
  This paper introduces RecLLM-R1, a novel recommendation framework leveraging Large Language Models (LLMs)<n> RecLLM-R1 significantly surpasses existing baseline methods across a spectrum of evaluation metrics, including accuracy, diversity, and novelty.
  arXiv  Detail & Related papers  (2025-06-24T01:39:34Z)
• Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs [51.21041884010009]
  Ring-lite is a Mixture-of-Experts (MoE)-based large language model optimized via reinforcement learning (RL)<n>Our approach matches the performance of state-of-the-art (SOTA) small-scale reasoning models on challenging benchmarks.
  arXiv  Detail & Related papers  (2025-06-17T17:12:34Z)
• Memory-Enhanced Neural Solvers for Routing Problems [8.255381359612885]
  We present MEMENTO, an approach that leverages memory to improve the search of neural solvers at inference.<n>We validate its effectiveness on the Traveling Salesman and Capacitated Vehicle Routing problems, demonstrating its superiority over tree-search and policy-gradient fine-tuning.<n>We successfully train all RL auto-regressive solvers on large instances, and verify MEMENTO's scalability and data-efficiency.
  arXiv  Detail & Related papers  (2024-06-24T08:18:19Z)
• Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training [23.56208527227504]
  Source-free domain adaptation (SFDA) aims to adapt a source model trained on a fully-labeled source domain to a related but unlabeled target domain. In the conventional SFDA pipeline, a large data (e.g. ImageNet) pre-trained feature extractor is used to initialize the source model. We introduce an integrated framework to incorporate pre-trained networks into the target adaptation process.
  arXiv  Detail & Related papers  (2024-05-05T14:48:13Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• Fully Decentralized Model-based Policy Optimization for Networked Systems [23.46407780093797]
  This work aims to improve data efficiency of multi-agent control by model-based learning. We consider networked systems where agents are cooperative and communicate only locally with their neighbors. In our method, each agent learns a dynamic model to predict future states and broadcast their predictions by communication, and then the policies are trained under the model rollouts.
  arXiv  Detail & Related papers  (2022-07-13T23:52:14Z)
• Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality [141.89413461337324]
  Deployment efficiency is an important criterion for many real-world applications of reinforcement learning (RL) We propose a theoretical formulation for deployment-efficient RL (DE-RL) from an "optimization with constraints" perspective.
  arXiv  Detail & Related papers  (2022-02-14T01:31:46Z)
• Edge-assisted Democratized Learning Towards Federated Analytics [67.44078999945722]
  We show the hierarchical learning structure of the proposed edge-assisted democratized learning mechanism, namely Edge-DemLearn. We also validate Edge-DemLearn as a flexible model training mechanism to build a distributed control and aggregation methodology in regions.
  arXiv  Detail & Related papers  (2020-12-01T11:46:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.