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.
hub Canonical reference
Evaluating Gemini Robotics Policies in a Veo World Simulator
Canonical reference. 86% of citing Pith papers cite this work as background.
26
Pith papers citing it
Background
86% of classified citations
hub tools
citation-role summary
background 6
other 1
citation-polarity summary
representative citing papers
RoboWM-Bench evaluates video world models by converting their manipulation video predictions into executable actions validated in simulation, showing that visual plausibility does not guarantee physical executability.
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
Step Forcing lets a 4-step video world model generate 30-second closed-loop rollouts, and a VLM judge scores them to reproduce the real RoboArena policy ranking at r=0.989.
SC3-Eval enforces three consistencies on a video model to produce policy rollouts that correlate 0.929 with real-world performance across seven vision-language-action policies and reproduce observed failure modes.
WEAVER is a multi-view world model using flow-matching that jointly satisfies fidelity, consistency, and efficiency for robotic manipulation, yielding 0.87 correlation with real success and policy gains on hardware.
TacForeSight trains a force-conditioned tactile world model to predict latent dynamics and uses those predictions as anticipatory priors inside a visuo-tactile policy for real-time contact-rich manipulation.
iMaC introduces image-based action tokens in a dual-branch architecture to improve future state prediction and control in embodied world models over vector-based baselines.
StressDream optimizes initial noise in diffusion video world models using VLM semantic and plausibility objectives to steer generations toward specified high-impact outcomes for improved policy evaluation.
RAW-Dream disentangles world-model learning from task data by using a pre-trained task-agnostic world model and VLM rewards, with dual-noise filtering, to enable zero-shot VLA adaptation in simulation and real settings.
A discrete diffusion model tokenizes multimodal robotic data and uses a progress token to predict future states and task completion for scalable policy evaluation.
Hi-WM uses human interventions inside an action-conditioned world model with rollback and branching to generate dense corrective data, raising real-world success by 37.9 points on average across three manipulation tasks.
Temporal difference calibration aligns uncertainty estimates in vision-language-action models with their value functions for better sequential performance.
SafetyALFRED shows multimodal LLMs recognize kitchen hazards accurately in QA tests but achieve low success rates when required to mitigate those hazards through embodied planning.
VAG is a synchronized dual-stream flow-matching framework that generates aligned video-action pairs for synthetic embodied data synthesis and policy pretraining.
mimic-video combines internet video pretraining with a flow-matching decoder to achieve state-of-the-art robotic manipulation performance with 10x better sample efficiency than vision-language-action models.
A video-action foundation model pretrained natively with a causal diffusion transformer and semantic visual-action tokenizer reports improved few-shot robot manipulation and 225 Hz asynchronous closed-loop control.
LingBot-Video is an open-source MoE video foundation model for embodied intelligence that scales to 120B parameters, integrates robot data, and uses multi-dimensional RL to improve physical plausibility.
DVG-WM disentangles dynamics learning from visual synthesis via flow matching and latent degradation to deliver faster, higher-quality video predictions for robotic manipulation.
Action-conditioned pretraining of a multi-view diffusion world model on robot data produces transferable dynamics priors that support both simulator rollouts and policy prediction.
The paper proposes an L0-L7 evidential ladder for evaluating world models in embodied decision-making, prioritizing interventional action fidelity and policy optimization utility over visual plausibility.
OptiWorld inserts a classical optimal-control layer that extracts a world state, plans an optimal trajectory on a geometric manifold under physical constraints, and renders the video conditioned on that trajectory.
LingBot-VA combines video world modeling with policy learning via Mixture-of-Transformers, closed-loop rollouts, and asynchronous inference to improve robot manipulation in simulation and real settings.
Human-video dynamics models enable cross-embodiment robot self-improvement via training-free Dynamics-Guided Action Correction, raising success rates from 40% to 81% on seven real-world tasks.
citing papers explorer
-
Targeting World Models to Compromise Robot Learning Pipelines
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.
-
RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation
RoboWM-Bench evaluates video world models by converting their manipulation video predictions into executable actions validated in simulation, showing that visual plausibility does not guarantee physical executability.
-
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
DreamDojo is a foundation world model pretrained on the largest human video dataset to date that uses continuous latent actions to transfer interaction knowledge and achieves controllable physics simulation after robot post-training.
-
RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation
Step Forcing lets a 4-step video world model generate 30-second closed-loop rollouts, and a VLM judge scores them to reproduce the real RoboArena policy ranking at r=0.989.
-
SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation
SC3-Eval enforces three consistencies on a video model to produce policy rollouts that correlate 0.929 with real-world performance across seven vision-language-action policies and reproduce observed failure modes.
-
WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation
WEAVER is a multi-view world model using flow-matching that jointly satisfies fidelity, consistency, and efficiency for robotic manipulation, yielding 0.87 correlation with real success and policy gains on hardware.
-
TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation
TacForeSight trains a force-conditioned tactile world model to predict latent dynamics and uses those predictions as anticipatory priors inside a visuo-tactile policy for real-time contact-rich manipulation.
-
iMaC: Translating Actions into Motion and Contact Images for Embodied World Models
iMaC introduces image-based action tokens in a dual-branch architecture to improve future state prediction and control in embodied world models over vector-based baselines.
-
StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement
StressDream optimizes initial noise in diffusion video world models using VLM semantic and plausibility objectives to steer generations toward specified high-impact outcomes for improved policy evaluation.
-
Reinforcing VLAs in Task-Agnostic World Models
RAW-Dream disentangles world-model learning from task data by using a pre-trained task-agnostic world model and VLM rewards, with dual-noise filtering, to enable zero-shot VLA adaptation in simulation and real settings.
-
dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model
A discrete diffusion model tokenizes multimodal robotic data and uses a progress token to predict future states and task completion for scalable policy evaluation.
-
Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training
Hi-WM uses human interventions inside an action-conditioned world model with rollback and branching to generate dense corrective data, raising real-world success by 37.9 points on average across three manipulation tasks.
-
Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models
Temporal difference calibration aligns uncertainty estimates in vision-language-action models with their value functions for better sequential performance.
-
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
SafetyALFRED shows multimodal LLMs recognize kitchen hazards accurately in QA tests but achieve low success rates when required to mitigate those hazards through embodied planning.
-
VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis
VAG is a synchronized dual-stream flow-matching framework that generates aligned video-action pairs for synthetic embodied data synthesis and policy pretraining.
-
mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
mimic-video combines internet video pretraining with a flow-matching decoder to achieve state-of-the-art robotic manipulation performance with 10x better sample efficiency than vision-language-action models.
-
Native Video-Action Pretraining for Generalizable Robot Control
A video-action foundation model pretrained natively with a causal diffusion transformer and semantic visual-action tokenizer reports improved few-shot robot manipulation and 225 Hz asynchronous closed-loop control.
-
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
LingBot-Video is an open-source MoE video foundation model for embodied intelligence that scales to 120B parameters, integrates robot data, and uses multi-dimensional RL to improve physical plausibility.
-
DVG-WM: Disentangled Video Generation Enables Efficient Embodied World Model for Robotic Manipulation
DVG-WM disentangles dynamics learning from visual synthesis via flow matching and latent degradation to deliver faster, higher-quality video predictions for robotic manipulation.
-
Learning Transferable Dynamics Priors from Action to World Modeling
Action-conditioned pretraining of a multi-view diffusion world model on robot data produces transferable dynamics priors that support both simulator rollouts and policy prediction.
-
How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position
The paper proposes an L0-L7 evidential ladder for evaluating world models in embodied decision-making, prioritizing interventional action fidelity and policy optimization utility over visual plausibility.
-
OptiWorld: Optimal Control for Video World Generation under Physical Constraints
OptiWorld inserts a classical optimal-control layer that extracts a world state, plans an optimal trajectory on a geometric manifold under physical constraints, and renders the video conditioned on that trajectory.
-
Causal World Modeling for Robot Control
LingBot-VA combines video world modeling with policy learning via Mixture-of-Transformers, closed-loop rollouts, and asynchronous inference to improve robot manipulation in simulation and real settings.
-
Robot Self-Improvement via Human-Video Dynamics Models
Human-video dynamics models enable cross-embodiment robot self-improvement via training-free Dynamics-Guided Action Correction, raising success rates from 40% to 81% on seven real-world tasks.
-
World Action Models: A Survey
A survey that clarifies boundaries and organizes World Action Models by generation requirements and predictive substrates, identifying a trend toward generating less of the future.
-
World Model for Robot Learning: A Comprehensive Survey
A comprehensive survey that organizes the literature on world models in robot learning, their roles in policy learning, planning, simulation, and video-based generation, with connections to navigation, driving, datasets, and benchmarks.