EgoEngine transforms egocentric human videos into high-fidelity robot data enabling zero-shot visuomotor dexterous policy learning without real-robot demonstrations.
HPT: Scaling proprioceptive-visual learning with heterogeneous pre-trained transformers
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
abstract
One of the roadblocks for training generalist robotic models today is heterogeneity. Previous robot learning methods often collect data to train with one specific embodiment for one task, which is expensive and prone to overfitting. This work studies the problem of learning policy representations through heterogeneous pre-training on robot data across different embodiments and tasks at scale. We propose Heterogeneous Pre-trained Transformers (HPT), which pre-train a large, shareable trunk of a policy neural network to learn a task and embodiment agnostic shared representation. This general architecture aligns the specific proprioception and vision inputs from distinct embodiments to a short sequence of tokens and then processes such tokens to map to control robots for different tasks. Leveraging the recent large-scale multi-embodiment real-world robotic datasets as well as simulation, deployed robots, and human video datasets, we investigate pre-training policies across heterogeneity. We conduct experiments to investigate the scaling behaviors of training objectives, to the extent of 52 datasets. HPTs outperform several baselines and enhance the fine-tuned policy performance by over 20% on unseen tasks in multiple simulator benchmarks and real-world settings. See the project website (https://liruiw.github.io/hpt/) for code and videos.
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Latent Bridge predicts VLM feature deltas to reduce VLM calls by 50-75% in dual-system VLA models while retaining 95-100% performance and achieving 1.65-1.73x speedup across LIBERO, RoboCasa, and ALOHA benchmarks.
World Action Model co-training with DINO or 3D-flow targets scales human-to-robot transfer on bimanual tasks far better than behavior cloning, while pixel prediction transfers weakly.
A 1,362-hour multi-source egocentric human dataset and multi-lab study show co-training improves robot manipulation, but only when aligned human–robot data anchors transfer from diverse human data.
GraspVLA shows that pretraining a grasping model on a billion synthetic action frames enables zero-shot open-vocabulary performance and sim-to-real transfer.
DexVLA combines a scaled diffusion action expert with embodiment curriculum learning to achieve better generalization and performance than prior VLA models on diverse robot hardware and long-horizon tasks.
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 generalization from sparse data.
citing papers explorer
-
EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations
EgoEngine transforms egocentric human videos into high-fidelity robot data enabling zero-shot visuomotor dexterous policy learning without real-robot demonstrations.
-
Latent Bridge: Feature Delta Prediction for Efficient Dual-System Vision-Language-Action Model Inference
Latent Bridge predicts VLM feature deltas to reduce VLM calls by 50-75% in dual-system VLA models while retaining 95-100% performance and achieving 1.65-1.73x speedup across LIBERO, RoboCasa, and ALOHA benchmarks.
-
EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data
World Action Model co-training with DINO or 3D-flow targets scales human-to-robot transfer on bimanual tasks far better than behavior cloning, while pixel prediction transfers weakly.
-
EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World
A 1,362-hour multi-source egocentric human dataset and multi-lab study show co-training improves robot manipulation, but only when aligned human–robot data anchors transfer from diverse human data.
-
GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data
GraspVLA shows that pretraining a grasping model on a billion synthetic action frames enables zero-shot open-vocabulary performance and sim-to-real transfer.
-
DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control
DexVLA combines a scaled diffusion action expert with embodiment curriculum learning to achieve better generalization and performance than prior VLA models on diverse robot hardware and long-horizon tasks.
-
General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling
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 generalization from sparse data.
- EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control