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.
hub
Being-H0.7: A Latent World-Action Model from Egocentric Videos
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
abstract
Visual-Language-Action models (VLAs) have advanced generalist robot control by mapping multimodal observations and language instructions directly to actions, but sparse action supervision often encourages shortcut mappings rather than representations of dynamics, contact, and task progress. Recent world-action models introduce future prediction through video rollouts, yet pixel-space prediction is a costly and indirect substrate for control, as it may model visual details irrelevant to action generation and introduces substantial training or inference overhead. We present Being-H0.7, a latent world-action model that brings future-aware reasoning into VLA-style policies without generating future frames. Being-H0.7 inserts learnable latent queries between perception and action as a compact reasoning interface, and trains them with a future-informed dual-branch design: a deployable prior branch infers latent states from the current context, while a training-only posterior branch replaces the queries with embeddings from future observations. Jointly aligning the two branches at the latent reasoning space leads the prior branch to reason future-aware, action-useful structure from current observations alone. At inference, Being-H0.7 discards the posterior branch and performs no visual rollout. Experiments across six simulation benchmarks and diverse real-world tasks show that Being-H0.7 achieves state-of-the-art or comparable performance, combining the predictive benefits of world models with the efficiency and deployability of direct VLA policies.
hub tools
citation-role summary
background 2
citation-polarity summary
years
2026 17roles
background 2polarities
background 2representative citing papers
VLAFlow shows that combining language-supervised co-training with future latent alignment produces the most stable transfer performance for vision-language-action models trained on mixed robot data.
Aligning temporal granularity, action subspaces, and train-test conditioning yields SOTA long-horizon mobile and fine-grained manipulation success for a unified world-action model.
Wh0 generates scalable egocentric human manipulation videos with world models and converts them to boost pretrained VLA models' zero-shot dexterous task success from 8.3% to 38.9% on 18 real-world tasks.
RepWAM introduces representation visual-action tokenizers to pretrain world action models that jointly model future visual states and latent actions under instructions for improved robot manipulation.
EmbodiSteer steers embodiment-agnostic Cartesian diffusion policies into joint space with Jacobian-based collision guidance after each denoising step for zero-shot cross-embodiment deployment.
Next Forcing augments video generation models with auxiliary multi-chunk prediction modules to achieve faster training convergence, higher accuracy at high frame rates, and 2x faster inference on world modeling benchmarks.
A state-adaptive noise-trajectory scheduler selects intermediate video conditions for action generation, matching or beating full-denoising WAMs at far lower latency.
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.
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.
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.
Kairos learns and maintains control-sufficient world states via a cross-embodiment curriculum, hybrid linear temporal attention, and deployment-aware co-design for Physical AI.
Efficient-WAM delivers 30x lower latency than prior WAMs at 100 ms per chunk while keeping competitive manipulation performance by treating coarse future video as guidance rather than high-fidelity output.
A unified embodied foundation model uses one VLM for understanding and reasoning plus a joint video-action future generator, reporting competitive scores on VLM, world modeling, and robot benchmarks without apparent compromise.
LingBot-VLA 2.0 combines 60k hours of multi-embodiment pretraining data, an expanded whole-body action space, and dual-query distillation from depth and video teachers to improve VLA performance on GM-100 and long-horizon mobile manipulation tasks.
Bridge-WA introduces a lightweight distillation-based world-action model that uses future-change priors to improve robotic task success and robustness without deployment-time dense rollouts.
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.
citing papers explorer
-
OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
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.
-
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
VLAFlow shows that combining language-supervised co-training with future latent alignment produces the most stable transfer performance for vision-language-action models trained on mixed robot data.
-
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model
Aligning temporal granularity, action subspaces, and train-test conditioning yields SOTA long-horizon mobile and fine-grained manipulation success for a unified world-action model.
-
Wh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data
Wh0 generates scalable egocentric human manipulation videos with world models and converts them to boost pretrained VLA models' zero-shot dexterous task success from 8.3% to 38.9% on 18 real-world tasks.
-
RepWAM: World Action Modeling with Representation Visual-Action Tokenizers
RepWAM introduces representation visual-action tokenizers to pretrain world action models that jointly model future visual states and latent actions under instructions for improved robot manipulation.
-
EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment
EmbodiSteer steers embodiment-agnostic Cartesian diffusion policies into joint space with Jacobian-based collision guidance after each denoising step for zero-shot cross-embodiment deployment.
-
Next Forcing: Causal World Modeling with Multi-Chunk Prediction
Next Forcing augments video generation models with auxiliary multi-chunk prediction modules to achieve faster training convergence, higher accuracy at high frame rates, and 2x faster inference on world modeling benchmarks.
-
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.
-
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.
-
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.
-
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.
-
Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI
Kairos learns and maintains control-sufficient world states via a cross-embodiment curriculum, hybrid linear temporal attention, and deployment-aware co-design for Physical AI.
-
Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination
Efficient-WAM delivers 30x lower latency than prior WAMs at 100 ms per chunk while keeping competitive manipulation performance by treating coarse future video as guidance rather than high-fidelity output.
-
Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action
A unified embodied foundation model uses one VLM for understanding and reasoning plus a joint video-action future generator, reporting competitive scores on VLM, world modeling, and robot benchmarks without apparent compromise.
-
From Foundation to Application: Improving VLA Models in Practice
LingBot-VLA 2.0 combines 60k hours of multi-embodiment pretraining data, an expanded whole-body action space, and dual-query distillation from depth and video teachers to improve VLA performance on GM-100 and long-horizon mobile manipulation tasks.
-
Bridge-WA: Predicting Where and How the World Changes for Robotic Action
Bridge-WA introduces a lightweight distillation-based world-action model that uses future-change priors to improve robotic task success and robustness without deployment-time dense rollouts.
-
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.