Pith. sign in

REVIEW 9 cited by

Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.14037 v1 pith:QX4PKZJ3 submitted 2024-08-26 cs.RO cs.LG

Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning

classification cs.RO cs.LG
keywords datasetsdatare-mixroboticsmodelsrobotweightsacross
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Increasingly large imitation learning datasets are being collected with the goal of training foundation models for robotics. However, despite the fact that data selection has been of utmost importance in vision and natural language processing, little work in robotics has questioned what data such models should actually be trained on. In this work we investigate how to weigh different subsets or ``domains'' of robotics datasets for robot foundation model pre-training. Concrete, we use distributionally robust optimization (DRO) to maximize worst-case performance across all possible downstream domains. Our method, Re-Mix, addresses the wide range of challenges that arise when applying DRO to robotics datasets including variability in action spaces and dynamics across different datasets. Re-Mix employs early stopping, action normalization, and discretization to counteract these issues. Through extensive experimentation on the largest open-source robot manipulation dataset, the Open X-Embodiment dataset, we demonstrate that data curation can have an outsized impact on downstream performance. Specifically, domain weights learned by Re-Mix outperform uniform weights by 38\% on average and outperform human-selected weights by 32\% on datasets used to train existing generalist robot policies, specifically the RT-X models.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics

    cs.RO 2026-06 unverdicted novelty 7.0

    Ambient Diffusion Policy enables better imitation learning from suboptimal robot data by leveraging spectral properties to restrict data usage to specific diffusion times.

  2. Distributionally Robust Multi-Task Reinforcement Learning via Adaptive Task Sampling

    cs.LG 2026-05 unverdicted novelty 7.0

    DRATS derives a minimax objective from a feasibility formulation of MTRL to adaptively sample tasks with the largest return gaps, leading to better worst-task performance on MetaWorld benchmarks.

  3. SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models

    cs.RO 2026-07 conditional novelty 6.0

    Selecting 50% of robot demonstrations by maximizing exposure to reusable primitive-transition patterns outperforms full-data training while halving training steps.

  4. VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment

    cs.CV 2026-07 unverdicted novelty 6.0

    VLAFlow shows that combining language-supervised co-training with future latent alignment produces the most stable transfer performance for vision-language-action models trained on mixed robot data.

  5. Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making

    cs.LG 2026-05 unverdicted novelty 6.0

    Ada-Diffuser is a causal diffusion model that jointly learns observed interaction structure and underlying latent dynamics from minimal observations for adaptive planning and policy learning.

  6. R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation

    cs.RO 2025-10 unverdicted novelty 6.0

    R2RGen introduces a simulator-free three-stage pipeline that parses, augments, and post-processes real pointcloud observation-action pairs to improve spatial generalization in robotic manipulation policies.

  7. Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering

    cs.RO 2026-06 unverdicted novelty 5.0

    MoRE improves robot policy success rates by 44 percentage points by distilling mode redirection into weights, matching filtered retraining performance without inference overhead.

  8. World Value Models for Robotic Manipulation

    cs.RO 2026-06 unverdicted novelty 5.0

    World Value Model (WVM) integrates world models with value estimation to achieve SOTA Value-Order Correlation on expert and suboptimal robotic data and improves downstream policy performance.

  9. General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling

    cs.CV 2026-05 unverdicted novelty 4.0

    GAM framework uses arc-length parameterization for temporal invariance and schema-affine factorization for geometric invariance to build a covariant action manifold integrated into VLA models for improved generalizati...