WAM
A robot control paradigm that performs planning and decision-making by learning an internal world model of how the environment changes in response to actions. It emphasizes modeling the causal relationships of the physical world to achieve stronger generalization capabilities and few-shot learning.
Core Facts
Timeline (last 90 days)
Jia Xiaosong observed that models such as VLA and WAM that introduce stronger vision-language capabilities are not necessarily better than well-optimized end-to-end models on some autonomous driving benchmarks; what truly limits the model is whether it can make the right decision, not whether it recognizes a certain object.
WAM proponents argue that once predictive models are sufficiently accurate, agents can achieve few-shot or even zero-shot motion planning through model predictive control (MPC) or latent-space tree search, bypassing the reliance on large volumes of real demonstration data.
VLA leans toward end-to-end imitation and builds capability through data scale, while WAM leans toward explicit world modeling and improves generalization through structured reasoning.
LIBERO simulation successfully runs long-horizon tasks on Mac for the first time, with GR00T achieving a 100% success rate, WAM achieving 98%, and a 2.8-billion-parameter VLA small model achieving 96%.
World Action Models (WAMs) couple predictive world modeling with action generation, enabling the model not only to predict the next state of the environment but also to guide agents in taking their next actions accordingly.
All Facts (5)
World Action Models (WAMs) couple predictive world modeling with action generation, enabling the model not only to predict the next state of the environment but also to guide agents in taking their next actions accordingly.
75%UnverifiedJia Xiaosong observed that models such as VLA and WAM that introduce stronger vision-language capabilities are not necessarily better than well-optimized end-to-end models on some autonomous driving benchmarks; what truly limits the model is whether it can make the right decision, not whether it recognizes a certain object.
50%UnverifiedWAM proponents argue that once predictive models are sufficiently accurate, agents can achieve few-shot or even zero-shot motion planning through model predictive control (MPC) or latent-space tree search, bypassing the reliance on large volumes of real demonstration data.
50%UnverifiedVLA leans toward end-to-end imitation and builds capability through data scale, while WAM leans toward explicit world modeling and improves generalization through structured reasoning.
50%UnverifiedLIBERO simulation successfully runs long-horizon tasks on Mac for the first time, with GR00T achieving a 100% success rate, WAM achieving 98%, and a 2.8-billion-parameter VLA small model achieving 96%.
50%