The Met said corruption was the most consistent offence detected, with misconduct related to'abuse of the IT system that rosters shifts by police officers for personal or financial gain'. The Met said corruption was the most consistent offence detected, with misconduct related to'abuse of the IT system that rosters shifts by police officers for personal or financial gain'. Sat 25 Apr 2026 11.34 EDTFirst published on Sat 25 Apr 2026 11.31 EDT The Metropolitan police have launched investigations into hundreds of officers after using an AI tool built by the controversial tech company Palantir to root out rogue cops. The software was deployed by the Met over the course of a week, surveilling staff members using data the force has ready access to, unearthing rule-breaking ranging from work-from-home violations to suspected corruption and even criminal allegations such as rape. The Met said as a result of the software, evidence had been found tying a small number of officers to serious cases of misconduct and criminality, resulting in the arrest of three officers for offences including abuse of authority for sexual purposes, fraud, sexual assault, misconduct in public office and misuse of police systems.

Natural language-conditioned reinforcement learning (RL) enables agents to follow human instructions. Previous approaches generally implemented languageconditioned RL by providing the policy with human instructions in natural language (NL) and training the policy to follow instructions. In this is outside-in approach, the policy must comprehend the NL and manage the task simultaneously. However, the unbounded NL examples often bring much extra complexity for solving concrete RL tasks, which can distract policy learning from completing the task. To ease the learning burden of the policy, we investigate an inside-out scheme for natural language-conditioned RL by developing a task language (TL) that is task-related and easily understood by the policy, thus reducing the policy learning burden. Besides, we employ a translator to translate natural language into the TL, which is used in RL to achieve efficient policy training. We implement this scheme as TALAR (TAsk Language with predicAte Representation) that learns multiple predicates to model object relationships as the TL. Experiments indicate that TALAR not only better comprehends NL instructions but also leads to a better instruction-following policy that significantly improves the success rate over baselines and adapts to unseen expressions of NL instruction. Besides, the TL is also an effective sub-task abstraction compatible with hierarchical RL.

This is the supplementary material of paper "Towards Enabling Meta-Learning from Target Models". We give implementation details, more discussions, and more experiment results in this material.

We use TSN-ResNet [11] as our backbone (see Table 1) and initialize it with ImageNet-pretrained weights [4]. We replace its 7 spatial convolutional layers with the RSA layers; for every two ResNet blocks from the third block in res2 to the second block in res5, each spatial convolutional layer is replaced with the RSA layer. For the bottlenecks including RSA layers, we randomly initialize weights using MSRA initialization [3] and set the gamma parameter of the last batch normalization layer to zero. We resize the resolution of each frame to 240 320, and apply random cropping as 224 224, scale jittering, and random horizontal flipping for data augmentation. Note that we do not flip videos of which action labels include'left' or'right' words, e.g., 'pulling something from left to right'.

Given a point set P M from a metric space (M,d)and numbers k,z N, the metric k-center problem with z outliers is to find a set C P of k points such that the maximum distance of all but at most z outlier points of P to their nearest center in C is minimized. We consider this problem in the fully dynamic model, i.e., under insertions and deletions of points, for the case that the metric space has a bounded doubling dimension dim. We utilize a hierarchical data structure to maintain the points and their neighborhoods, which enables us to efficiently find the clusters. In particular, our data structure can be queried at any time to generate a (3 + ε)-approximate solution for input values of k and z in worst-case query time ε O(dim)klognloglog, where is the ratio between the maximum and minimum distance between two points in P. Moreover, it allows insertion/deletion of a point in worst-case update time ε O(dim) lognlog . Our result achieves a significantly faster query time with respect to k and z than the current state-of-theart by Pellizzoni, Pietracaprina, and Pucci [18], which uses ε O(dim)(k+z)2 log query time to obtain a (3+ε)-approximate solution.