Introduces Colosseum V2 benchmark for evaluating VLA model generalization in robotic manipulation with 28 tasks, revealing limitations in current methods and sim-real correlations.
hub
Dit4dit: Jointly modeling video dynamics and actions for generalizable robot control
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
years
2026 22roles
background 3polarities
background 3representative citing papers
CreFlow combines LTL compositional rewards with credit-aware NFT and corrective reflow losses in online RL to improve embodied video diffusion models, raising downstream task success by 23.8 percentage points on eight bimanual manipulation tasks.
MoLA infers a mixture of latent actions from generated future videos via modality-aware inverse dynamics models to improve robot manipulation policies.
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.
Temporal Ratio, the action head’s attention to future video latents versus the current frame, predicts and can be used to mitigate the compositional video–action generalization gap.
FORGE decouples robotic tool-use into keypoint trajectory prediction from action-free data and action grounding from limited demonstrations, achieving over 2X improvement in functional generalization to unseen tools.
ImageWAM shows image editing models can replace video generation in world action models, delivering better performance with 6x lower FLOPs and 4x lower latency by using edit-derived KV caches as compact context.
MaskWAM unifies mask prompting and prediction in world-action models via Mixture of Transformers to improve robotic policy generalization on language-ambiguous tasks.
MotionWAM conditions a policy on intermediate features from a video world model to predict unified whole-body motion tokens, enabling real-time humanoid loco-manipulation that outperforms VLA baselines by over 30% on nine Unitree G1 tasks.
A state-adaptive noise-trajectory scheduler selects intermediate video conditions for action generation, matching or beating full-denoising WAMs at far lower latency.
X-WAM unifies robotic action execution and 4D world synthesis by adapting video diffusion priors with a lightweight depth branch and asynchronous noise sampling, achieving 79-91% success on robot benchmarks.
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.
World Pilot augments VLA policies with world-action priors through latent and action steering pathways, reporting 84.7% success on LIBERO-Plus zero-shot OOD and top real-robot results across four tasks.
AGRA is an Action-Grounded Representation Alignment objective that aligns intermediate video diffusion features with semantic representations to make world action model hidden states more useful for low-level robot control, improving localization, affordance, and robustness.
WLA models use an autoregressive Transformer to jointly predict textual subtasks, subgoal images, and robot actions from instructions, images, and states, reporting SOTA success rates on RoboTwin2.0 and RMBench.
Discrete-WAM unifies world modeling and policy learning for autonomous driving by representing observations, states, decisions, and actions as tokens in one space and using hierarchical token editing for planning.
MemoryWAM is a world action model with a hybrid memory design using recent frames, anchor frames, and gist tokens for efficient long-horizon robotic manipulation.
Donk is a unified video-action denoising model that generates dexterous hand trajectories and videos under language, image, and state conditioning while also serving as a text-conditioned data engine.
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
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.
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.
citing papers explorer
-
Colosseum V2: Benchmarking Generalization for Vision Language Action Models
Introduces Colosseum V2 benchmark for evaluating VLA model generalization in robotic manipulation with 28 tasks, revealing limitations in current methods and sim-real correlations.
-
CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL
CreFlow combines LTL compositional rewards with credit-aware NFT and corrective reflow losses in online RL to improve embodied video diffusion models, raising downstream task success by 23.8 percentage points on eight bimanual manipulation tasks.
-
From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation
MoLA infers a mixture of latent actions from generated future videos via modality-aware inverse dynamics models to improve robot manipulation policies.
-
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.
-
Understanding and Mitigating the Video-Action Generalization Gap via Temporal Ratio
Temporal Ratio, the action head’s attention to future video latents versus the current frame, predicts and can be used to mitigate the compositional video–action generalization gap.
-
FORGE: Towards Functional Tool-Use Generalization via Keypoint Trajectory Reasoning
FORGE decouples robotic tool-use into keypoint trajectory prediction from action-free data and action grounding from limited demonstrations, achieving over 2X improvement in functional generalization to unseen tools.
-
ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?
ImageWAM shows image editing models can replace video generation in world action models, delivering better performance with 6x lower FLOPs and 4x lower latency by using edit-derived KV caches as compact context.
-
MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models
MaskWAM unifies mask prompting and prediction in world-action models via Mixture of Transformers to improve robotic policy generalization on language-ambiguous tasks.
-
MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation
MotionWAM conditions a policy on intermediate features from a video world model to predict unified whole-body motion tokens, enabling real-time humanoid loco-manipulation that outperforms VLA baselines by over 30% on nine Unitree G1 tasks.
-
SANTS: A State-Adaptive Scheduler for World Action Models
A state-adaptive noise-trajectory scheduler selects intermediate video conditions for action generation, matching or beating full-denoising WAMs at far lower latency.
-
Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
X-WAM unifies robotic action execution and 4D world synthesis by adapting video diffusion priors with a lightweight depth branch and asynchronous noise sampling, achieving 79-91% success on robot benchmarks.
-
World Value Models for Robotic Manipulation
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.
-
World Pilot: Steering Vision-Language-Action Models with World-Action Priors
World Pilot augments VLA policies with world-action priors through latent and action steering pathways, reporting 84.7% success on LIBERO-Plus zero-shot OOD and top real-robot results across four tasks.
-
Making Foresight Actionable: Repurposing Representation Alignment in World Action Models
AGRA is an Action-Grounded Representation Alignment objective that aligns intermediate video diffusion features with semantic representations to make world action model hidden states more useful for low-level robot control, improving localization, affordance, and robustness.
-
World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
WLA models use an autoregressive Transformer to jointly predict textual subtasks, subgoal images, and robot actions from instructions, images, and states, reporting SOTA success rates on RoboTwin2.0 and RMBench.
-
Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning
Discrete-WAM unifies world modeling and policy learning for autonomous driving by representing observations, states, decisions, and actions as tokens in one space and using hierarchical token editing for planning.
-
MemoryWAM: Efficient World Action Modeling with Persistent Memory
MemoryWAM is a world action model with a hybrid memory design using recent frames, anchor frames, and gist tokens for efficient long-horizon robotic manipulation.
-
Unified Video-Action Joint Denoising for Dexterous Action and Data Generation
Donk is a unified video-action denoising model that generates dexterous hand trajectories and videos under language, image, and state conditioning while also serving as a text-conditioned data engine.
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
-
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.
- GenHOI: Contact-Aware Humanoid-Object Interaction by Imitating Generated Videos without Task-Specific Training