Fidelity-Aware Data Composition for Robust Robot Generalization

• URL: http://arxiv.org/abs/2509.24797v1
• Date: Mon, 29 Sep 2025 13:48:36 GMT
• Title: Fidelity-Aware Data Composition for Robust Robot Generalization
• Abstract summary: Generalist robot policies trained on large-scale, visually homogeneous datasets can be susceptible to shortcut learning.<n>This paper suggests that robust generalization depends on principled, fidelity-aware data composition.<n>We introduce Coherent Information Fidelity Tuning (CIFT), a framework that treats data composition as an optimization problem.
• Score: 39.69070982795268
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generalist robot policies trained on large-scale, visually homogeneous datasets can be susceptible to shortcut learning, which impairs their out-of-distribution (OOD) generalization. While generative data augmentation is a common approach to introduce diversity, it presents a subtle challenge: data composition. Naively mixing real and synthetic data can corrupt the learning signal, as this process often prioritizes visual diversity at the expense of information fidelity. This paper suggests that robust generalization depends on principled, fidelity-aware data composition. We introduce Coherent Information Fidelity Tuning (CIFT), a framework that treats data composition as an optimization problem. CIFT uses a practical proxy for Information Fidelity based on the feature-space geometry of a dataset. This enables the identification of a phase transition, termed the Decoherence Point, where training stability degrades. The framework includes a generative engine, Multi-View Video Augmentation (MVAug), to synthesize a causally disentangled data spectrum for this tuning process. Applying CIFT to policy architectures such as $\pi_0$ and Diffusion Policy improves OOD success rates by over 54\%. These results indicate that fidelity-aware composition, beyond data synthesis alone, is an important component for developing robust, general-purpose robots.

Related papers

• Towards Generalizable Robotic Data Flywheel: High-Dimensional Factorization and Composition [15.755384541529098]
  The lack of sufficiently diverse data is a major bottleneck for generalist robotic models.<n>We propose F-ACIL, a factor-aware iterative learning framework that enables structured data factorization.<n>With extensive real-world experiments, we show that F-ACIL can achieve more than 45% performance gains.
  arXiv  Detail & Related papers  (2026-03-26T16:00:39Z)
• GO-GenZip: Goal-Oriented Generative Sampling and Hybrid Compression [50.76941829813458]
  Current network data telemetry pipelines consist of massive streams of fine-grained Key Performance Indicators (KPIs) from multiple distributed sources towards central aggregators.<n>This work presents a generative AI (GenAI)-driven sampling and hybrid compression framework that redesigns network telemetry from a goal-oriented perspective.
  arXiv  Detail & Related papers  (2026-03-20T16:33:15Z)
• EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning [63.03672166010434]
  We introduce an evolutionary, task-agnostic, strategy-guided, executably-checkable data synthesis framework.<n>It jointly synthesizes problems, diverse candidate solutions, and verification artifacts.<n>It iteratively discovers strategies via a consistency-based evaluator that enforces agreement between human-annotated and strategy-induced checks.
  arXiv  Detail & Related papers  (2025-10-20T11:56:35Z)
• CausalDiffTab: Mixed-Type Causal-Aware Diffusion for Tabular Data Generation [6.449839514410505]
  We introduce CausalDiffTab, a diffusion model-based generative model specifically designed to handle mixed data.<n>We propose a hybrid adaptive causal regularization method based on the principle of Hierarchical Prior Fusion.<n>Experiments conducted on seven datasets demonstrate that CausalDiffTab outperforms baseline methods across all metrics.
  arXiv  Detail & Related papers  (2025-06-17T05:48:44Z)
• AIGC-assisted Federated Learning for Edge Intelligence: Architecture Design, Research Challenges and Future Directions [41.88981742448266]
  Federated learning (FL) can leverage large-scale terminal data while ensuring privacy and security.<n>To address this challenge, artificial intelligence-generated content (AIGC) which is an innovative data synthesis technique emerges as one potential solution.
  arXiv  Detail & Related papers  (2025-03-26T02:45:19Z)
• FLIGAN: Enhancing Federated Learning with Incomplete Data using GAN [1.5749416770494706]
  Federated Learning (FL) provides a privacy-preserving mechanism for distributed training of machine learning models on networked devices. We propose FLIGAN, a novel approach to address the issue of data incompleteness in FL. Our methodology adheres to FL's privacy requirements by generating synthetic data in a federated manner without sharing the actual data in the process.
  arXiv  Detail & Related papers  (2024-03-25T16:49:38Z)
• HeteroSwitch: Characterizing and Taming System-Induced Data Heterogeneity in Federated Learning [36.00729012296371]
  Federated Learning (FL) is a practical approach to train deep learning models collaboratively across user-end devices. In FL, participating user-end devices are highly fragmented in terms of hardware and software configurations. We propose HeteroSwitch, which adaptively adopts generalization techniques depending on the level of bias caused by varying HW and SW configurations.
  arXiv  Detail & Related papers  (2024-03-07T04:23:07Z)
• FLASH: Federated Learning Across Simultaneous Heterogeneities [55.0981921695672]
  FLASH(Federated Learning Across Simultaneous Heterogeneities) is a lightweight and flexible client selection algorithm.<n>It outperforms state-of-the-art FL frameworks under extensive sources of Heterogeneities.<n>It achieves substantial and consistent improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2024-02-13T20:04:39Z)
• Fake It Till Make It: Federated Learning with Consensus-Oriented Generation [52.82176415223988]
  We propose federated learning with consensus-oriented generation (FedCOG) FedCOG consists of two key components at the client side: complementary data generation and knowledge-distillation-based model training. Experiments on classical and real-world FL datasets show that FedCOG consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-12-10T18:49:59Z)
• Feature Matching Data Synthesis for Non-IID Federated Learning [7.740333805796447]
  Federated learning (FL) trains neural networks on edge devices without collecting data at a central server. This paper proposes a hard feature matching data synthesis (HFMDS) method to share auxiliary data besides local models. For better privacy preservation, we propose a hard feature augmentation method to transfer real features towards the decision boundary.
  arXiv  Detail & Related papers  (2023-08-09T07:49:39Z)
• CAFE: Learning to Condense Dataset by Aligning Features [72.99394941348757]
  We propose a novel scheme to Condense dataset by Aligning FEatures (CAFE) At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art.
  arXiv  Detail & Related papers  (2022-03-03T05:58:49Z)
• Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning [53.73083199055093]
  We show that attention-based architectures (e.g., Transformers) are fairly robust to distribution shifts. Our experiments show that replacing convolutional networks with Transformers can greatly reduce catastrophic forgetting of previous devices.
  arXiv  Detail & Related papers  (2021-06-10T21:04:18Z)

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.