When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task. Prior research into learning from demonstrations (LfD) has failed to capture this notion of the acceptability of an execution; meanwhile, temporal logics provide a flexible language for expressing task specifications. Inspired by this, we present Bayesian specification inference, a probabilistic model for inferring task specification as a temporal logic formula. We incorporate methods from probabilistic programming to define our priors, along with a domain-independent likelihood function to enable sampling-based inference. We demonstrate the efficacy of our model for inferring true specifications with over 90% similarity between the inferred specification and the ground truth, both within a synthetic domain and a real-world table setting task.

Furthermore, weprove information theoretic lower bounds which establish minimax optimality of the skillparameter estimation technique usedinouralgorithm. These bounds utilize a continuum version of Fano's method along with a careful covering argument.

'We Ain't Seen Nothing Yet'--Trump's Mass Deportations Will Only Grow From Here Militias and far-right extremists believed they would be central to Trump's mass deportation plans. When Donald Trump won a second term as US president a year ago, members of violent militias and far-right extremist groups who had spent years boosting the lie that the 2020 election was rigged were ready to assist the president with delivering on one of his main campaign promises: mass deportations. "I'm willing to help," Richard Mack, a former sheriff who founded the far-right Constitutional Sheriffs and Peace Officers Association, told WIRED at the time, claiming he was in touch with Tom Homan, the man Trump installed as his "border czar." Tim Foley, head of the Arizona Border Recon, which describes itself as a "non-government organization," also told WIRED he was in contact with administration officials. William Teer, then head of the far-right Texas Three Percenters militia, wrote a letter to Trump offering his help.

Learning from a few examples is a challenging computer vision task. Traditionally,meta-learning-based methods have shown promise towards solving this problem.Recent approaches show benefits by learning a feature extractor on the abundantbase examples and transferring these to the fewer novel examples. However, thefinetuning stage is often prone to overfitting due to the small size of the noveldataset. To this end, we propose Few shot Learning with hard Mixup (FeLMi)using manifold mixup to synthetically generate samples that helps in mitigatingthe data scarcity issue. Different from a naïve mixup, our approach selects the hardmixup samples using an uncertainty-based criteria. To the best of our knowledge,we are the first to use hard-mixup for the few-shot learning problem.

We consider the question of learning the natural parameters of a $k$ parameter \textit{minimal} exponential family from i.i.d.

We study core stability in non-centroid clustering under the max-loss objective, where each agent's loss is the maximum distance to other members of their cluster. We prove that for all $k\geq 3$ there exist metric instances with $n\ge 9$ agents, with $n$ divisible by $k$, for which no clustering lies in the $α$-core for any $α<2^{\frac{1}{5}}\sim 1.148$. The bound is tight for our construction. Using a computer-aided proof, we also identify a two-dimensional Euclidean point set whose associated lower bound is slightly smaller than that of our general construction. This is, to our knowledge, the first impossibility result showing that the core can be empty in non-centroid clustering under the max-loss objective.

When observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task. Prior research into learning from demonstrations (LfD) has failed to capture this notion of the acceptability of an execution; meanwhile, temporal logics provide a flexible language for expressing task specifications. Inspired by this, we present Bayesian specification inference, a probabilistic model for inferring task specification as a temporal logic formula. We incorporate methods from probabilistic programming to define our priors, along with a domain-independent likelihood function to enable sampling-based inference. We demonstrate the efficacy of our model for inferring true specifications with over 90% similarity between the inferred specification and the ground truth, both within a synthetic domain and a real-world table setting task.

With AI datacenters soaring power bills for households, a policy called'demand flexibility' could help ease grid strain A cheap, bipartisan tool could help the US meet increasing energy demand from AI datacenters while also easing soaring power bills for households, preventing deadly blackouts and helping the climate. The policy solution, called "demand flexibility", can be quickly deployed across the US. Demand flexibility essentially means rewarding customers for using less power during times of high demand, reducing strain on the grid or in some cases, selling energy they have captured by solar panels on their homes. Peak power demand is expected to grow by 20% over the next decade - driven by the dramatic rise of AI datacenters, onshoring of manufacturing, increasing use of EVs and growing need for air conditioning amid hotter summers. Increasing energy demand is putting states such as California and Texas at higher risk of life-threatening blackouts in extreme weather.

Meta Tells Its Metaverse Workers to Use AI to'Go 5X Faster' Mark Zuckerberg's metaverse chief is urging employees to adopt AI across every workflow as part of a broader shift inside the company. Meta CEO Mark Zuckerberg says most of the company's code will be written by AI in the next 18 months. A Meta executive in charge of building the company's metaverse products told employees that they should be using AI to "go 5X faster" according to an internal message obtained by 404 Media. "Metaverse AI4P: Think 5X, not 5%," the message, posted by Vishal Shah, Meta's VP of Metaverse, said (AI4P is AI for Productivity). The idea is that programmers should be using AI to work five times more efficiently than they are currently working--not just using it to go 5 more efficiently.