Prepending a few self-generated random interaction clips as context lets VLA policies identify novel camera viewpoints and morphologies at test time and outperform multi-view baselines without parameter updates.
hub Mixed citations
Unified Video Action Model
Mixed citation behavior. Most common role is background (70%).
68
Pith papers citing it
Background
70% of classified citations
abstract
A unified video and action model holds significant promise for robotics, where videos provide rich scene information for action prediction, and actions provide dynamics information for video prediction. However, effectively combining video generation and action prediction remains challenging, and current video generation-based methods struggle to match the performance of direct policy learning in action accuracy and inference speed. To bridge this gap, we introduce the Unified Video Action model (UVA), which jointly optimizes video and action predictions to achieve both high accuracy and efficient action inference. The key lies in learning a joint video-action latent representation and decoupling video-action decoding. The joint latent representation bridges the visual and action domains, effectively modeling the relationship between video and action sequences. Meanwhile, the decoupled decoding, powered by two lightweight diffusion heads, enables high-speed action inference by bypassing video generation during inference. Such a unified framework further enables versatile functionality through masked input training. By selectively masking actions or videos, a single model can tackle diverse tasks beyond policy learning, such as forward and inverse dynamics modeling and video generation. Via an extensive set of experiments, we demonstrate that UVA can serve as a general-purpose solution for a wide range of robotics tasks, such as policy learning, forward/inverse dynamics and video observation prediction, without compromising performance compared to methods tailored for specific applications. Results are best viewed on https://unified-video-action-model.github.io/.
hub tools
citation-role summary
background 17
baseline 4
dataset 1
method 1
citation-polarity summary
representative citing papers
Introduces Colosseum V2 benchmark for evaluating VLA model generalization in robotic manipulation with 28 tasks, revealing limitations in current methods and sim-real correlations.
NoiseGate learns per-latent timestep schedules as an information-gating policy in diffusion-based world action models, yielding consistent gains on RoboTwin manipulation tasks.
EA-WM generates more accurate robot world rollouts by projecting actions as structured visual fields in camera space and using event-aware bidirectional fusion to better capture interaction dynamics.
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
VistaBot integrates 4D geometry estimation and spatiotemporal view synthesis into action policies to improve cross-view generalization by 2.6-2.8x on a new VGS metric in simulation and real tasks.
Action Images turn robot arm motions into interpretable multiview pixel videos, letting video backbones serve as zero-shot policies for end-to-end robot learning.
PhysGen uses video models to learn physics for robots, outperforming baselines by up to 13.8% on Libero and matching specialized models in real-world tasks.
A video foundation model trained on human demonstrations generates zero-shot plans that convert to executable robot actions on novel scenes and tasks.
Multimodal Diffusion Forcing trains a diffusion model on partially masked multimodal robot trajectories to learn temporal and cross-modal dependencies for forceful manipulation.
DreamGen trains robot policies on synthetic trajectories from adapted video world models, enabling a humanoid robot to perform 22 new behaviors in seen and unseen environments from a single pick-and-place teleoperation dataset.
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.
AutoSpeed learns annotation-free, stage-adaptive robot motion speeds by optimizing policies toward the minimum-cost DCT-retimed multi-speed demonstration target.
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.
VT-WAM jointly predicts visual futures, tactile deformation, and actions via flow matching with Asymmetric MoT attention and contact-gated AVTAG, reporting 71.67% success on six real-world contact-rich tasks.
MuSe adapts a vision-action policy to force-torque via multi-stage fusion, multisensory future prediction, and experience replay, improving both new contact-rich tasks and original vision tasks.
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.
T-Rex introduces a large tactile dataset and MoT architecture that achieves over 30% higher success rates than baselines on 12 tasks requiring force control and deformable object handling.
UMA treats object motion and robot actions as co-evolving variables under a masked generative objective with hindsight relabeling and contrastive disentanglement to support multi-task pretraining and deployment across heterogeneous robot data.
ω-EVA is a three-stage latent world model framework that trains action-conditioned dynamics, a language-conditioned flow policy, and a tri-branch refiner to improve embodied action generation in simulation.
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.
FAWAM integrates force signals into perception, prediction, and closed-loop correction, raising success rates 36% over vision baselines in contact-rich manipulation tasks.
WorldFly integrates a world model into a VLA framework via dual-branch coupled flow matching to jointly generate future videos and actions, outperforming baselines on an urban canyon traversal benchmark especially in unseen environments.
PointAction uses predicted dynamic 3D pointmaps from fine-tuned video models as an embodiment-agnostic action representation to map video predictions to executable robot actions.
citing papers explorer
-
In-Context World Modeling for Robotic Control
Prepending a few self-generated random interaction clips as context lets VLA policies identify novel camera viewpoints and morphologies at test time and outperform multi-view baselines without parameter updates.
-
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.
-
NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models
NoiseGate learns per-latent timestep schedules as an information-gating policy in diffusion-based world action models, yielding consistent gains on RoboTwin manipulation tasks.
-
EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields
EA-WM generates more accurate robot world rollouts by projecting actions as structured visual fields in camera space and using event-aware bidirectional fusion to better capture interaction dynamics.
-
Being-H0.7: A Latent World-Action Model from Egocentric Videos
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
-
VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis
VistaBot integrates 4D geometry estimation and spatiotemporal view synthesis into action policies to improve cross-view generalization by 2.6-2.8x on a new VGS metric in simulation and real tasks.
-
Action Images: End-to-End Policy Learning via Multiview Video Generation
Action Images turn robot arm motions into interpretable multiview pixel videos, letting video backbones serve as zero-shot policies for end-to-end robot learning.
-
Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation
PhysGen uses video models to learn physics for robots, outperforming baselines by up to 13.8% on Libero and matching specialized models in real-world tasks.
-
Large Video Planner Enables Generalizable Robot Control
A video foundation model trained on human demonstrations generates zero-shot plans that convert to executable robot actions on novel scenes and tasks.
-
Multimodal Diffusion Forcing for Forceful Manipulation
Multimodal Diffusion Forcing trains a diffusion model on partially masked multimodal robot trajectories to learn temporal and cross-modal dependencies for forceful manipulation.
-
DreamGen: Unlocking Generalization in Robot Learning through Video World Models
DreamGen trains robot policies on synthetic trajectories from adapted video world models, enabling a humanoid robot to perform 22 new behaviors in seen and unseen environments from a single pick-and-place teleoperation dataset.
-
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.
-
AutoSpeed: Annotation-Free Stage-Adaptive Motion Speed Learning for Robot Manipulation
AutoSpeed learns annotation-free, stage-adaptive robot motion speeds by optimizing policies toward the minimum-cost DCT-retimed multi-speed demonstration target.
-
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.
-
VT-WAM: Visual-Tactile World Action Model for Contact-Rich Manipulation
VT-WAM jointly predicts visual futures, tactile deformation, and actions via flow matching with Asymmetric MoT attention and contact-gated AVTAG, reporting 71.67% success on six real-world contact-rich tasks.
-
Multisensory Continual Learning: Adapting Pretrained Visuomotor Policies to Force
MuSe adapts a vision-action policy to force-torque via multi-stage fusion, multisensory future prediction, and experience replay, improving both new contact-rich tasks and original vision tasks.
-
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.
-
T-Rex: Tactile-Reactive Dexterous Manipulation
T-Rex introduces a large tactile dataset and MoT architecture that achieves over 30% higher success rates than baselines on 12 tasks requiring force control and deformable object handling.
-
Unified Motion-Action Modeling for Heterogeneous Robot Learning
UMA treats object motion and robot actions as co-evolving variables under a masked generative objective with hindsight relabeling and contrastive disentanglement to support multi-task pretraining and deployment across heterogeneous robot data.
-
$\omega$-EVA: Envision, Verify, and Act with Latent Interactive World Models
ω-EVA is a three-stage latent world model framework that trains action-conditioned dynamics, a language-conditioned flow policy, and a tri-branch refiner to improve embodied action generation in simulation.
-
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.
-
FAWAM: Force-Aware World Action Models for Closed-Loop Contact-Rich Manipulation
FAWAM integrates force signals into perception, prediction, and closed-loop correction, raising success rates 36% over vision baselines in contact-rich manipulation tasks.
-
WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation
WorldFly integrates a world model into a VLA framework via dual-branch coupled flow matching to jointly generate future videos and actions, outperforming baselines on an urban canyon traversal benchmark especially in unseen environments.
-
PointAction: 3D Points as Universal Action Representations for Robot Control
PointAction uses predicted dynamic 3D pointmaps from fine-tuned video models as an embodiment-agnostic action representation to map video predictions to executable robot actions.
-
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
A multi-agent video world model using simplex rotary agent encoding and sparse hub attention achieves better fidelity, controllability, and consistency than baselines while generalizing from 2 to 4 players.
-
Turning Video Models into Generalist Robot Policies
Decouples action-free video world models from embodiment-specific IDMs using Jacobian-based translation to achieve zero-shot cross-embodiment robot policies.
-
Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
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.
-
OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation
OmniHumanoid factorizes transferable motion learning from embodiment-specific adaptation to enable scalable cross-embodiment video generation without paired data for new humanoids.
-
When to Trust Imagination: Adaptive Action Execution for World Action Models
A verifier called Future Forward Dynamics Causal Attention enables adaptive action execution in World Action Models, reducing model inferences by 69% and improving success rates in robotic tasks.
-
Bridging the Embodiment Gap: Disentangled Cross-Embodiment Video Editing
A dual-contrastive disentanglement method factorizes videos into independent task and embodiment latents, then uses a parameter-efficient adapter on a frozen video diffusion model to synthesize robot executions from single human demonstrations without paired data.
-
UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
UniT creates a unified physical language via visual anchoring and tri-branch reconstruction to enable scalable human-to-humanoid transfer for policy learning and world modeling.
-
DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks
CLWM with DINOv3 targets, O(1) TTT memory, SAI latency masking, and EmbodiChain training achieves SOTA dual-arm simulation performance and zero-shot sim-to-real transfer that beats real-data finetuned baselines.
-
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.
-
From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data
Video-to-robot control methods cluster into three interface families, and the field’s main bottleneck is grounding video-derived predictions into dependable closed-loop robot behavior.
-
DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLA
DIAL decouples intent from action in end-to-end VLAs using a latent visual foresight bottleneck and two-stage training, reaching SOTA on RoboCasa with 10x fewer demonstrations and zero-shot real-world transfer.
-
Fast-WAM: Do World Action Models Need Test-time Future Imagination?
Fast-WAM shows that explicit future imagination at test time is not required for strong WAM performance; video modeling during training provides the main benefit.
-
Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
SimDist pretrains world models in simulation and adapts them to real-world robots by updating only the latent dynamics model, enabling rapid improvement on contact-rich tasks where prior methods fail.
-
World Action Models are Zero-shot Policies
DreamZero uses a 14B video diffusion model as a World Action Model to achieve over 2x better zero-shot generalization on real robots than state-of-the-art VLAs, real-time 7Hz closed-loop control, and cross-embodiment transfer with 10-30 minutes of data.
-
Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning
Single-stage fine-tuning of a video model to generate actions as latent frames plus future states and values yields state-of-the-art robot policy performance on LIBERO, RoboCasa, and bimanual tasks.
-
HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models
HiF-VLA improves long-horizon robotic manipulation by encoding past motion as hindsight priors and anticipating future motion through foresight reasoning inside a VLA framework.
-
Ctrl-World: A Controllable Generative World Model for Robot Manipulation
A controllable world model trained on the DROID dataset generates consistent multi-view robot trajectories for over 20 seconds and improves generalist policy success rates by 44.7% via imagined trajectory fine-tuning.
-
F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions
F1 integrates next-scale visual foresight prediction into a Mixture-of-Transformer VLA architecture to reformulate action generation as foresight-guided inverse dynamics, achieving higher success rates on 136 tasks.
-
Vidar: Embodied Video Diffusion Model for Generalist Manipulation
Vidar shows that a video diffusion prior continuously pre-trained on 750K multi-view robot trajectories plus a label-free masked inverse dynamics adapter can generalize manipulation to new robot embodiments with 1% of typical demonstration data.
-
AnyPos: Automated Task-Agnostic Actions for Bimanual Manipulation
AnyPos automates task-agnostic action collection and inverse-dynamics modeling with arm/end-effector decoupling plus a direction-aware decoder, delivering 51% higher test accuracy and 30-40% better success rates on bimanual tasks.
-
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.
-
Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
Self Forcing trains autoregressive video diffusion models by performing autoregressive rollout with KV caching during training to close the exposure bias gap, using a holistic video-level loss and few-step diffusion for efficiency.
-
FLARE: Robot Learning with Implicit World Modeling
FLARE integrates predictive latent world modeling into diffusion transformer policies for robots, delivering up to 26% gains on multitask manipulation benchmarks and enabling co-training with action-free human videos.
-
Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots
A five-layer C++ runtime deploys VLA and WAM models for closed-loop robot control, reporting 100% and 91% task success plus large memory savings on one Transformer block.
-
RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures
RoboTALES uses hierarchical LLM subgoals and VLM reward feedback to keep video-model futures task-aligned, then trains robot policies that beat baselines on RoboCasa and LIBERO10 long-horizon tasks.
-
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
PhysisForcing applies trajectory and relational alignment losses to DiT features in video models, improving physical plausibility on R-Bench, PAI-Bench, and EZS-Bench while raising closed-loop robotic success rates from 16% to 24%.