A fundamental challenge in embodied intelligence is developing expressive and compact state representations for efficient world modeling and decision making. However, existing methods often fail to achieve this balance of compactness and expressivity, yielding representations that are either overly redundant or lacking in task-critical information. We propose an unsupervised approach that learns a highly compressed two-token state representation using a lightweight encoder and a pre-trained Diffusion Transformer (DiT) decoder, capitalizing on its strong generative prior. Our representation is efficient, interpretable, and integrates seam-lessly into existing VLA-based models, improving performance by 14.3% on LIBERO and 30% in real-world task success rate with minimal inference overhead. More importantly, we find that the difference between these tokens, obtained via latent interpolation, naturally represents the motion, which can be further decoded into executable robot actions. This emergent capability reveals that our representation captures dynamics without explicit motion supervision. We name our method StaMo for its ability to learn generalizable robotic Motion from compact State representation, which is encoded from static images, challenging the prevalent dependence to learning robotic motions with complex temporal modeling and video data. Our learned representations also enhance policy co-training, outperforming prior methods by 10.4% with improved interpretability. "What we observe as static is merely dynamic equilibrium. " -- Richard Feynman, The Feynman Lectures on Physics Learning reusable and generalizable representations is a cornerstone of intelligent robotics systems.

Entity linking (EL) is the process of linking entity mentions appearing in text with their corresponding entities in a knowledge base. EL features of entities (e.g., prior probability, relatedness score, and entity embedding) are usually estimated based on Wikipedia. However, for newly emerging entities (EEs) which have just been discovered in news, they may still not be included in Wikipedia yet. As a consequence, it is unable to obtain required EL features for those EEs from Wikipedia and EL models will always fail to link ambiguous mentions with those EEs correctly as the absence of their EL features. To deal with this problem, in this paper we focus on a new task of learning EL features for emerging entities in a general way. We propose a novel approach called STAMO to learn high-quality EL features for EEs automatically, which needs just a small number of labeled documents for each EE collected from the Web, as it could further leverage the knowledge hidden in the unlabeled data. STAMO is mainly based on self-training, which makes it flexibly integrated with any EL feature or EL model, but also makes it easily suffer from the error reinforcement problem caused by the mislabeled data. Instead of some common self-training strategies that try to throw the mislabeled data away explicitly, we regard self-training as a multiple optimization process with respect to the EL features of EEs, and propose both intra-slot and inter-slot optimizations to alleviate the error reinforcement problem implicitly. We construct two EL datasets involving selected EEs to evaluate the quality of obtained EL features for EEs, and the experimental results show that our approach significantly outperforms other baseline methods of learning EL features.

Similar protections don't exist for the two billion-plus Facebook users who don't work for the company, the people said. The dual standard for employees versus regular users is a window on Facebook's struggle over how much to disclose to users about how their data is handled--an issue Facebook has recently tried to address with a raft of changes to the platform. A Facebook spokesman said the company has had discussions about issuing these types of alerts to all users. "In thinking about how we could do something similar for everyone, there are a number of important considerations that come into play--for example, how we can avoid tipping off bad actors or hindering our work to prevent real world harm in cases of abuse or other sensitive situations," the spokesman added. The system can be abused: Earlier this week, Facebook fired a security engineer who had bragged to a woman he met on a dating app about his access to private user information, according to a person familiar with the matter.