JOPAT jointly models pixels, point tracks, and actions in a diffusion transformer and reports gains over pixel-only baselines on long-horizon robot tasks with occlusion and off-screen motion.
hub Canonical reference
World Action Models are Zero-shot Policies
Canonical reference. 90% of citing Pith papers cite this work as background.
56
Pith papers citing it
Background
90% of classified citations
abstract
State-of-the-art Vision-Language-Action (VLA) models excel at semantic generalization but struggle to generalize to unseen physical motions in novel environments. We introduce DreamZero, a World Action Model (WAM) built upon a pretrained video diffusion backbone. Unlike VLAs, WAMs learn physical dynamics by predicting future world states and actions, using video as a dense representation of how the world evolves. By jointly modeling video and action, DreamZero learns diverse skills effectively from heterogeneous robot data without relying on repetitive demonstrations. This results in over 2x improvement in generalization to new tasks and environments compared to state-of-the-art VLAs in real robot experiments. Crucially, through model and system optimizations, we enable a 14B autoregressive video diffusion model to perform real-time closed-loop control at 7Hz. Finally, we demonstrate two forms of cross-embodiment transfer: video-only demonstrations from other robots or humans yield a relative improvement of over 42% on unseen task performance with just 10-20 minutes of data. More surprisingly, DreamZero enables few-shot embodiment adaptation, transferring to a new embodiment with only 30 minutes of play data while retaining zero-shot generalization.
hub tools
citation-role summary
background 28
baseline 1
citation-polarity summary
claims ledger
- abstract State-of-the-art Vision-Language-Action (VLA) models excel at semantic generalization but struggle to generalize to unseen physical motions in novel environments. We introduce DreamZero, a World Action Model (WAM) built upon a pretrained video diffusion backbone. Unlike VLAs, WAMs learn physical dynamics by predicting future world states and actions, using video as a dense representation of how the world evolves. By jointly modeling video and action, DreamZero learns diverse skills effectively from heterogeneous robot data without relying on repetitive demonstrations. This results in over 2x i
co-cited works
years
2026 56representative citing papers
WorldVLN proposes the first autoregressive world action model for aerial vision-language navigation that predicts short-horizon latent world states, decodes them to waypoints in closed loop, and uses two-stage training with Action-aware GRPO to achieve over 12% success-rate gains on benchmarks plus零
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.
ACWM-Phys is a controllable simulator benchmark with in- and out-of-distribution protocols for evaluating action-conditioned world models across rigid, kinematic, deformable, and particle dynamics.
NoiseGate learns per-latent timestep schedules as an information-gating policy in diffusion-based world action models, yielding consistent gains on RoboTwin manipulation tasks.
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.
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.
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.
ViVa turns a video generator into a value model for robot RL that jointly forecasts future states and task value, yielding better performance on real-world box assembly when integrated with RECAP.
MoRight disentangles object and camera motion via canonical-view specification and temporal cross-view attention, while decomposing motion into active user-driven and passive consequence components to learn and apply causality in 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.
A curiosity-based 3D exploration policy that pairs persistent online 3D reconstruction with episodic sequence modeling over RGB to outperform active-mapping baselines on HM3D and transfer zero-shot to Gibson and synthetic worlds.
WorldKV enables persistent world memory in autoregressive video diffusion models by selectively retrieving and compressing KV-cache chunks, matching full-cache fidelity at roughly twice the throughput without training.
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
Proposes World-Ego Modeling with WEM using CP-MoE diffusion and a new HTEWorld benchmark, claiming SOTA on hybrid navigation-manipulation tasks.
DeMiAn re-annotates robot and egocentric videos with VLM-generated dense labels across motion, scene, pose, and reasoning aspects, then uses a learned instructor to boost policy success by 5 points on RoboCasa over task-only baselines.
UAM adds a Dorsal Expert initialized from a generative model and trained on visual dynamics prediction to preserve over 95% of VLM multimodal ability in VLA training while achieving top success rates on manipulation tasks including OOD cases.
Feedback world model closes the prediction-observation loop at inference time to correct errors and improve diffusion policy performance under distribution shift in robotics.
A co-evolutionary VLM-VGM loop on 500 unlabeled images raises planner success by 30 points and simulator success by 48 percent while beating fully supervised baselines.
Pyramid Forcing classifies attention heads into Anchor, Wave, and Veil types and applies type-specific KV cache policies to improve long-horizon autoregressive video generation quality.
DAWN couples a world predictor with a world-conditioned action denoiser in latent space so that each refines the other recursively, yielding strong planning and safety results on autonomous driving benchmarks.
ALAM introduces algebraic consistency regularization on latent action transitions from videos, raising VLA success rates from 47.9% to 85.0% on MetaWorld MT50 and 94.1% to 98.1% on LIBERO.
citing papers explorer
-
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.