In Russia's'blitz' of Ukraine, the question of appeasement is back Following another week of intensive and lethal Russian bombardment of Ukraine's cities, a composite image has been doing the rounds on Ukrainian social media. Underneath an old, black-and-white photo of Londoners queuing at a fruit and vegetable stall surrounded by the bombed-out rubble of the Blitz, a second image - this time in colour - creates a striking juxtaposition. Taken on Saturday, it shows shoppers thronging to similar stalls in a northern suburb of the Ukrainian capital, Kyiv, while a column of black smoke rises ominously in the background. Bombs can't stop markets, reads the caption linking the two images. The night before, as the city's sleep was interrupted once again by the now all-too-familiar booms of missile and drone strikes, two people were killed and nine others injured.

Yoshihiro Murai, 65, celebrates his victory in the Miyagi gubernatorial election on Sunday night. SENDAI - Yoshihiro Murai held off four other candidates to clinch his sixth term as governor of Miyagi Prefecture in Sunday's gubernatorial election. Murai, an independent candidate who had support from prefectural assembly members of the Liberal Democratic Party, Japan Innovation Party and Komeito, highlighted his achievements as the prefecture's governor spanning five terms, or 20 years. The 65-year-old former chief of the National Governors' Association pledged to enhance productivity by promoting digital transformation using generative artificial intelligence, in anticipation of a further population decline. He successfully fended off Masamune Wada, 51, also an independent candidate, who had been closing in.

Is Trump losing patience with Putin? Will sanctions against Russian oil giants hurt Putin? How much of Europe's oil still comes from Russia? Russian drone attacks on the Ukrainian capital, Kyiv, early on Sunday killed at least three people and wounded 29 others, according to Ukrainian Minister of Internal Affairs Ihor Klymenko. The wounded included seven children, Klymenko said.

Reinforcement learning (RL) has become a predominant technique to align language models (LMs) with human preferences or promote outputs which are deemed to be desirable by a given reward function. Standard RL approaches optimize average reward, while methods explicitly focused on reducing the probability of undesired outputs typically come at a cost to average-case performance. To improve this tradeoff, we introduce RePULSe, a new training method that augments the standard RL loss with an additional loss that uses learned proposals to guide sampling low-reward outputs, and then reduces those outputs' probability. We run experiments demonstrating that RePULSe produces a better tradeoff of expected reward versus the probability of undesired outputs and is more adversarially robust, compared to standard RL alignment approaches and alternatives.

To understand feature learning dynamics in neural networks, recent theoretical works have focused on gradient-based learning of Gaussian single-index models, where the label is a nonlinear function of a latent one-dimensional projection of the input. While the sample complexity of online SGD is determined by the information exponent of the link function, recent works improved this by performing multiple gradient steps on the same sample with different learning rates -- yielding a non-correlational update rule -- and instead are limited by the (potentially much smaller) generative exponent. However, this picture is only valid when these learning rates are sufficiently large. In this paper, we characterize the relationship between learning rate(s) and sample complexity for a broad class of gradient-based algorithms that encapsulates both correlational and non-correlational updates. We demonstrate that, in certain cases, there is a phase transition from an "information exponent regime" with small learning rate to a "generative exponent regime" with large learning rate. Our framework covers prior analyses of one-pass SGD and SGD with batch reuse, while also introducing a new layer-wise training algorithm that leverages a two-timescales approach (via different learning rates for each layer) to go beyond correlational queries without reusing samples or modifying the loss from squared error. Our theoretical study demonstrates that the choice of learning rate is as important as the design of the algorithm in achieving statistical and computational efficiency.

Space-air-ground integrated multi-access edge computing (SAGIN-MEC) provides a promising solution for the rapidly developing low-altitude economy (LAE) to deliver flexible and wide-area computing services. However, fully realizing the potential of SAGIN-MEC in the LAE presents significant challenges, including coordinating decisions across heterogeneous nodes with different roles, modeling complex factors such as mobility and network variability, and handling real-time decision-making under partially observable environment with hybrid variables. To address these challenges, we first present a hierarchical SAGIN-MEC architecture that enables the coordination between user devices (UDs), uncrewed aerial vehicles (UAVs), and satellites. Then, we formulate a UD cost minimization optimization problem (UCMOP) to minimize the UD cost by jointly optimizing the task offloading ratio, UAV trajectory planning, computing resource allocation, and UD association. We show that the UCMOP is an NP-hard problem. To overcome this challenge, we propose a multi-agent deep deterministic policy gradient (MADDPG)-convex optimization and coalitional game (MADDPG-COCG) algorithm. Specifically, we employ the MADDPG algorithm to optimize the continuous temporal decisions for heterogeneous nodes in the partially observable SAGIN-MEC system. Moreover, we propose a convex optimization and coalitional game (COCG) method to enhance the conventional MADDPG by deterministically handling the hybrid and varying-dimensional decisions. Simulation results demonstrate that the proposed MADDPG-COCG algorithm significantly enhances the user-centric performances in terms of the aggregated UD cost, task completion delay, and UD energy consumption, with a slight increase in UAV energy consumption, compared to the benchmark algorithms. Moreover, the MADDPG-COCG algorithm shows superior convergence stability and scalability.

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between desired attributes (e.g., helpfulness vs. verbosity). Yet, because the training data often reflects dominant, average preferences, LLMs tend to perform well on common requests but fall short in specific, individual needs. This mismatch creates a preference coverage gap. Existing methods often address this through costly retraining, which may not be generalized to the full spectrum of diverse preferences. This brittleness means that when a user's request reflects a nuanced preference deviating from the training data's central tendency, model performance can degrade unpredictably. To address this challenge, we introduce Robust Preference Selection (RPS), a post-hoc, training-free method by leveraging directional neighborhood consensus. Instead of forcing a model to generate a response from a single, highly specific preference, RPS samples multiple responses from a local neighborhood of related preferences to create a superior candidate pool. It then selects the response that best aligns with the user's original intent. We provide a theoretical framework showing our neighborhood generation strategy is provably superior to a strong baseline that also samples multiple candidates. Comprehensive experiments across three distinct alignment paradigms (DPA, DPO, and SFT) demonstrate that RPS consistently improves robustness against this baseline, achieving win rates of up to 69% on challenging preferences from under-represented regions of the space without any model retraining. Our work presents a practical, theoretically-grounded solution for enhancing the reliability of preference-aligned models.

Graph domain adaptation (GDA) is a fundamental task in graph machine learning, with techniques like shift-robust graph neural networks (GNNs) and specialized training procedures to tackle the distribution shift problem. Although these model-centric approaches show promising results, they often struggle with severe shifts and constrained computational resources. To address these challenges, we propose a novel model-free framework, GRADATE (GRAph DATa sElector), that selects the best training data from the source domain for the classification task on the target domain. GRADATE picks training samples without relying on any GNN model's predictions or training recipes, leveraging optimal transport theory to capture and adapt to distribution changes. GRADATE is data-efficient, scalable and meanwhile complements existing model-centric GDA approaches. Through comprehensive empirical studies on several real-world graph-level datasets and multiple covariate shift types, we demonstrate that GRADATE outperforms existing selection methods and enhances off-the-shelf GDA methods with much fewer training data.

We study Transformers through the perspective of optimal control theory, using tools from continuous-time formulations to derive actionable insights into training and architecture design. This framework improves the performance of existing Transformer models while providing desirable theoretical guarantees, including generalization and robustness. Our framework is designed to be plug-and-play, enabling seamless integration with established Transformer models and requiring only slight changes to the implementation. We conduct seven extensive experiments on tasks motivated by text generation, sentiment analysis, image classification, and point cloud classification. Experimental results show that the framework improves the test performance of the baselines, while being more parameter-efficient. On character-level text generation with nanoGPT, our framework achieves a 46% reduction in final test loss while using 42% fewer parameters. On GPT-2, our framework achieves a 9.3% reduction in final test loss, demonstrating scalability to larger models. To the best of our knowledge, this is the first work that applies optimal control theory to both the training and architecture of Transformers. It offers a new foundation for systematic, theory-driven improvements and moves beyond costly trial-and-error approaches.

Reward models are central to aligning LLMs with human preferences, but they are costly to train, requiring large-scale human-labeled preference data and powerful pretrained LLM backbones. Meanwhile, the increasing availability of high-quality synthetic instruction-following datasets raises the question: can simpler, reference-based metrics serve as viable alternatives to reward models during RL-based alignment? In this paper, we show first that BLEU, a basic string-matching metric, surprisingly matches strong reward models in agreement with human preferences on general instruction-following datasets. Based on this insight, we develop BLEUBERI, a method that first identifies challenging instructions and then applies Group Relative Policy Optimization (GRPO) using BLEU directly as the reward function. We demonstrate that BLEUBERI-trained models are competitive with models trained via reward model-guided RL across four challenging instruction-following benchmarks and three different base language models. A human evaluation further supports that the quality of BLEUBERI model outputs is on par with those from reward model-aligned models. Moreover, BLEUBERI models generate outputs that are more factually grounded than competing methods. Overall, we show that given access to high-quality reference outputs (easily obtained via existing instruction-following datasets or synthetic data generation), string matching-based metrics are cheap yet effective proxies for reward models during alignment. We release our code and data at https://github.com/lilakk/BLEUBERI.