Image caption, Will Pep Guardiola or Mikel Arteta be lifting the Premier League trophy next month? With five games to go, Manchester City and Arsenal are only separated on goals scored at the top of the Premier League table. It's a new league now, says Gunners boss Mikel Arteta, whose side had been top of the table for 209 days until Wednesday. Manchester City's 2-1 win over Arsenal on Sunday boosted their hopes - and a 1-0 victory at Burnley on Wednesday sent them top. Who is going to win the title now?

Andon Market in San Francisco represents a vision, however flawed, of a future when more sophisticated AI agents take over work traditionally done by humans. In San Francisco's upscale Cow Hollow district, the introduction of a boutique selling coffee table games, tote bags and other household items would be pretty unremarkable. However, Andon Market has one key differentiator: It's run by AI. At this store, an artificial intelligence agent named Luna effectively acts as the chief executive officer of the operation. It decides what products to offer and how much to charge for them.

We present a novel actor-critic algorithm for an environment with delayed feedback, which addresses the state-space explosion problem of conventional approaches. Conventional approaches use an augmented state constructed from the last observed state and actions executed since visiting the last observed state Using the augmented state space, the correct Markov decision process for delayed environments can be constructed; however, this causes the state space to explode as the number of delayed timesteps increases, leading to slow convergence. Our proposed algorithm, called Belief-Projection-Based Q-learning (BPQL), addresses the state-space explosion problem by evaluating the values of the critic for which the input state size is equal to the original state-space size rather than that of the augmented one. We compare BPQL to traditional approaches in continuous control tasks and demonstrate that it significantly outperforms other algorithms in terms of asymptotic performance and sample efficiency. We also show that BPQL solves long-delayed environments, which conventional approaches are unable to do.

Modern language models excel at integrating across long temporal scales needed to encode linguistic meaning and show non-trivial similarities to biological neural systems. Prior work suggests that human brain responses to language exhibit hierarchically organized "integration windows" that substantially constrain the overall influence of an input token (e.g., a word) on the neural response. However, little prior work has attempted to use integration windows to characterize computations in large language models (LLMs). We developed a simple word-swap procedure for estimating integration windows from black-box language models that does not depend on access to gradients or knowledge of the model architecture (e.g., attention weights). Using this method, we show that trained LLMs exhibit stereotyped integration windows that are well-fit by a convex combination of an exponential and a power-law function, with a partial transition from exponential to power-law dynamics across network layers. We then introduce a metric for quantifying the extent to which these integration windows vary with structural boundaries (e.g., sentence boundaries), and using this metric, we show that integration windows become increasingly yoked to structure at later network layers. None of these findings were observed in an untrained model, which as expected integrated uniformly across its input. These results suggest that LLMs learn to integrate information in natural language using a stereotyped pattern: integrating across position-yoked, exponential windows at early layers, followed by structure-yoked, power-law windows at later layers. The methods we describe in this paper provide a general-purpose toolkit for understanding temporal integration in language models, facilitating cross-disciplinary research at the intersection of biological and artificial intelligence.

China's DeepSeek unveils latest models a year after upending global tech China's DeepSeek has unveiled the latest versions of its signature artificial intelligence-powered chatbot, a year after its flagship model sent shockwaves through the global tech scene. The Chinese start-up launched preview versions of DeepSeek-V4-Pro and DeepSeek-V4-Flash on Friday as it touted its ability to go toe-to-toe with US rivals such as OpenAI and Google. The "flash" model has similar reasoning abilities to the "pro" version, while offering faster response times and more cost-effective pricing, the Hangzhou-based startup said. Like DeepSeek's previous chatbots, V4-Pro and V4-Flash follow an open-source model, meaning developers are free to use and modify them at will. The release comes after DeepSeek-R1 stunned the tech sector upon its launch in January last year with capabilities broadly comparable with those of ChatGPT and Gemini.

Causal identification is at the core of the causal inference literature, where complete algorithms have been proposed to identify causal queries of interest. The validity of these algorithms hinges on the restrictive assumption of having access to a correctly specified causal structure. In this work, we study the setting where a probabilistic model of the causal structure is available. Specifically, the edges in a causal graph exist with uncertainties which may, for example, represent degree of belief from domain experts. Alternatively, the uncertainty about an edge may reflect the confidence of a particular statistical test. The question that naturally arises in this setting is: Given such a probabilistic graph and a specific causal effect of interest, what is the subgraph which has the highest plausibility and for which the causal effect is identifiable? We show that answering this question reduces to solving an NP-complete combinatorial optimization problem which we call the edge ID problem. We propose efficient algorithms to approximate this problem and evaluate them against both real-world networks and randomly generated graphs.

Near the Kremlin several dozen people are queuing outside the presidential administration office. They've come to submit petitions calling on President Vladimir Putin to end a crackdown on the internet. Russian authorities have been tightening control of the country's cyber space. Access to global messaging apps has been restricted and there are widespread disruptions to, even shutdowns of, mobile internet. Petitioning the president is legal.

This paper presents a simple, self-supervised method for magnifying subtle motions in video: given an input video and a magnification factor, we manipulate the video such that its new optical flow is scaled by the desired amount. To train our model, we propose a loss function that estimates the optical flow of the generated video and penalizes how far if deviates from the given magnification factor. Thus, training involves differentiating through a pretrained optical flow network. Since our model is self-supervised, we can further improve its performance through test-time adaptation, by finetuning it on the input video. It can also be easily extended to magnify the motions of only user-selected objects. Our approach avoids the need for synthetic magnification datasets that have been used to train prior learning-based approaches.

We consider online prediction of a binary sequence with expert advice. For this setting, we devise label-efficient forecasting algorithms, which use a selective sampling scheme that enables collecting much fewer labels than standard procedures. For the general case without a perfect expert, we prove best-of-both-worlds guarantees, demonstrating that the proposed forecasting algorithm always queries sufficiently many labels in the worst case to obtain optimal regret guarantees, while simultaneously querying much fewer labels in more benign settings. Specifically, for a scenario where one expert is strictly better than the others in expectation, we show that the label complexity of the label-efficient forecaster is roughly upperbounded by the square root of the number of rounds. Finally, we present numerical experiments empirically showing that the normalized regret of the label-efficient forecaster can asymptotically match known minimax rates for pool-based active learning, suggesting it can optimally adapt to benign settings.