World models introduce a stealthy poisoning vector into robot learning pipelines where malicious prompts or dynamics in teleoperated data activate only during synthetic trajectory generation, enabling backdoors in downstream policies.
super hub Mixed citations
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
Mixed citation behavior. Most common role is background (55%).
112
Pith papers citing it
Background
55% of classified citations
abstract
Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train generalist X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. More details can be found on the project website https://robotics-transformer-x.github.io.
hub tools
citation-role summary
background 23
dataset 18
baseline 2
method 1
citation-polarity summary
claims ledger
- abstract Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train generalist X-robot policy that can be adapted efficiently to new robots, tasks, and enviro
authors
co-cited works
representative citing papers
BOKBO is the first conformal abstention method for K-sample VLA policies that supplies finite-sample distribution-free guarantees on executed violation rates, with global and Mondrian per-task variants.
SkiP introduces action relabeling and Motion Spectrum Keying to skip redundant steps in robot trajectories, cutting executed steps by 15-40% while maintaining success rates across 72 simulated and 3 real tasks.
Flow map policies enable fast one-step inference for flow-based RL policies, and FMQ provides an optimal closed-form Q-guided target for offline-to-online adaptation under trust-region constraints, achieving SOTA performance.
SABER provides 44.8K multi-representation action samples from unscripted retail environments that raise a VLA model's mean success rate on ten manipulation tasks from 13.4% to 29.3%.
OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.
Action Agent pairs LLM-driven video generation with a flow-constrained diffusion transformer to produce velocity commands, raising video success to 86% and delivering 64.7% real-world navigation on a Unitree G1 humanoid.
A 48-camera residential platform delivers real-time occlusion-robust 3D perception and coordinated actuation for multi-human multi-robot interaction in a shared home workspace.
A cross-version swap protocol reveals dominant skills that swing composition success by up to 50 percentage points, and an atomic probe with selective revalidation governs updates at lower cost than always re-testing full compositions.
π₀.₇ is a steerable generalist robotic model that uses rich multimodal prompts including language, subgoal images, and performance metadata to achieve out-of-the-box generalization across tasks and robot bodies.
PhysMem enables VLM-based robot planners to learn and verify physical properties through test-time interaction and hypothesis testing, raising success on a brick insertion task from 23% to 76%.
UniLACT improves VLA models by adding depth-aware unified latent action pretraining that outperforms RGB-only baselines on seen and unseen manipulation tasks.
A video foundation model trained on human demonstrations generates zero-shot plans that convert to executable robot actions on novel scenes and tasks.
Averaging and temporally interpolating text latents in VLAs enables 83% success on novel task combinations in the libero-ood benchmark where SOTA models achieve under 15%.
Introduces the Kaiwu multimodal dataset and framework with 11,664 synchronized assembling demonstrations including hand motions, pressures, sounds, multi-view videos, motion capture, eye gaze, and EMG signals with timestamp-based and semantic annotations.
RoboDreamer factorizes video generation using language primitives to achieve compositional generalization in robot world models, outperforming monolithic baselines on unseen goals in RT-X.
3D-VLA is a new embodied foundation model that uses a 3D LLM plus aligned diffusion models to generate future images and point clouds for improved reasoning and action planning in 3D environments.
RT-H learns robot policies by first predicting language motions as an intermediate representation and then mapping those plus the high-level task to actions, yielding more robust multi-task performance and the ability to learn from language interventions.
ATM pre-trains models to predict trajectories of any points in videos, then uses those predictions to learn strong visuomotor policies from minimal action labels, beating baselines by 80% on 130+ tasks.
PACE dynamically selects execution horizons for action chunks in robot policies by detecting low-speed transition points in predicted speed profiles, raising success rates from 57.8% to 64.2% on 50 simulation tasks and from 50.7% to 70.4% in real-robot tests.
VISUALTHINK-VLA uses visual evidence tokens and selective routing to reach top success rates on VLA benchmarks while cutting reasoning latency from multi-second to sub-second levels.
Instrumented objects boost diffusion policy success in robotic hanger insertion by 14-25 percentage points over vision-only baselines, and augmenting datasets with instrumented expert rollouts lets a vision-only student match the instrumented expert.
A compositional flow-matching model learns a dictionary of motion primitives with length masks and assembles them via sparse binary placement with geometric continuity losses, reporting SOTA results on two embodied trajectory datasets.
AVP architecture has VLM emit visual-primitive tokens to condition flow-matching action expert, yielding 27.61% higher success rate than pi_0.5 on real-robot pick-and-place tasks.
citing papers explorer
-
3D-VLA: A 3D Vision-Language-Action Generative World Model
3D-VLA is a new embodied foundation model that uses a 3D LLM plus aligned diffusion models to generate future images and point clouds for improved reasoning and action planning in 3D environments.
-
VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
VISUALTHINK-VLA uses visual evidence tokens and selective routing to reach top success rates on VLA benchmarks while cutting reasoning latency from multi-second to sub-second levels.
-
EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices
EgoKit is a new toolkit and accessory set that unifies egocentric video collection with wrist views across heterogeneous consumer devices using a consistent interface and log format.
-
Why Latent Actions Fail, and How to Prevent It
Extending linear LAMs to model exogenous state shows standard reconstruction encodes future exogenous info in latent actions, while endogenous-focused spaces and auxiliary objectives like action-supervision enforce consistency across noise.
-
HumanNet: Scaling Human-centric Video Learning to One Million Hours
HumanNet is a 1M-hour human-centric video dataset with interaction annotations that enables better vision-language-action model performance than equivalent robot data in a controlled test.
-
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
DreamVLA uses dynamic-region-guided world knowledge prediction, block-wise attention to disentangle information types, and a diffusion transformer for actions, reaching 76.7% success on real robot tasks and 4.44 average length on CALVIN ABC-D.
-
CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
CoT-VLA is a 7B VLA that generates future visual frames autoregressively as planning goals before actions, outperforming prior VLAs by 17% on real-world tasks and 6% in simulation.
-
HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model
HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.
-
Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations
Video Prediction Policy conditions robot action learning on future-frame predictions inside fine-tuned video diffusion models, yielding 18.6% relative gains on Calvin ABC-D and 31.6% higher real-world success rates.
-
Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces
MLLMs achieve competitive but subhuman performance on the new VSI-Bench for visual-spatial intelligence from videos, with spatial reasoning as the main bottleneck and explicit cognitive map generation improving distance estimation.
-
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
LongVILA scales visual-language models from 8 to 2048 video frames with 99.8% needle-in-a-haystack accuracy using long-context extension, supervised fine-tuning, and multi-modal sequence parallelism on up to 256 GPUs.
-
DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
DriveVLM adds vision-language models with scene description, analysis, and hierarchical planning modules to autonomous driving, paired with a hybrid DriveVLM-Dual system tested on nuScenes and SUP-AD datasets and deployed on a production vehicle.
-
Physical Object Understanding with a Physically Controllable World Model
Autoregressive probabilistic world models trained on raw videos yield emergent object segmentation, 3D controllability, and physical relationship inference via multi-future motion correlation analysis.
-
SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution
SWEET is a one-shot sparse visual planning framework that progressively generates manipulation keyframes via image editing conditioned on language and spatial guidance, then converts them to actions with a diffusion predictor, showing better fidelity and lower cost than video models on DROID and Rob
- Dynamic Execution Commitment of Vision-Language-Action Models