--This paper investigates the application of Neuroevo-lution of Augmenting T opologies (NEA T) to automate gameplay in Dark Souls, a notoriously challenging action role-playing game characterized by complex combat mechanics, dynamic environments, and high-dimensional visual inputs. T o facilitate this approach, we introduce the Dark Souls API (DSAPI), a novel Python framework leveraging real-time computer vision techniques for extracting critical game metrics, including player and enemy health states. Using NEA T, agents evolve effective combat strategies for defeating the Asylum Demon, the game's initial boss, without predefined behaviors or domain-specific heuristics. Experimental results demonstrate that evolved agents achieve up to a 35% success rate, indicating the viability of neuroevolution in addressing complex, visually intricate gameplay scenarios. This work represents an interesting application of vision-based neuroevolution, highlighting its potential use in a wide range of challenging game environments lacking direct API support or well-defined state representations. The development of artificial intelligence (AI) capable of playing video games at a human or superhuman level has long been an important benchmark in AI research [1], [2].

Many existing approaches to generalizing statistical inference amidst distribution shift operate under the covariate shift assumption, which posits that the conditional distribution of unobserved variables given observable ones is invariant across populations. However, recent empirical investigations have demonstrated that adjusting for shift in observed variables (covariate shift) is often insufficient for generalization. In other words, covariate shift does not typically ``explain away'' the distribution shift between settings. As such, addressing the unknown yet non-negligible shift in the unobserved variables given observed ones (conditional shift) is crucial for generalizable inference. In this paper, we present a series of empirical evidence from two large-scale multi-site replication studies to support a new role of covariate shift in ``predicting'' the strength of the unknown conditional shift. Analyzing 680 studies across 65 sites, we find that even though the conditional shift is non-negligible, its strength can often be bounded by that of the observable covariate shift. However, this pattern only emerges when the two sources of shifts are quantified by our proposed standardized, ``pivotal'' measures. We then interpret this phenomenon by connecting it to similar patterns that can be theoretically derived from a random distribution shift model. Finally, we demonstrate that exploiting the predictive role of covariate shift leads to reliable and efficient uncertainty quantification for target estimates in generalization tasks with partially observed data. Overall, our empirical and theoretical analyses suggest a new way to approach the problem of distributional shift, generalizability, and external validity.

Propaganda plays a critical role in shaping public opinion and fueling disinformation. While existing research primarily focuses on identifying propaganda techniques, it lacks the ability to capture the broader motives and the impacts of such content. To address these challenges, we introduce propainsight, a conceptual framework grounded in foundational social science research, which systematically dissects propaganda into techniques, arousal appeals, and underlying intent. propainsight offers a more granular understanding of how propaganda operates across different contexts. Additionally, we present propagaze, a novel dataset that combines human-annotated data with high-quality synthetic data generated through a meticulously designed pipeline. Our experiments show that off-the-shelf LLMs struggle with propaganda analysis, but training with propagaze significantly improves performance. Fine-tuned Llama-7B-Chat achieves 203.4% higher text span IoU in technique identification and 66.2% higher BertScore in appeal analysis compared to 1-shot GPT-4-Turbo. Moreover, propagaze complements limited human-annotated data in data-sparse and cross-domain scenarios, showing its potential for comprehensive and generalizable propaganda analysis.

Tables play a crucial role in conveying information in various domains. We propose a Plan-then-Reason framework to answer different types of user queries over tables with sentence context. The framework first plans the reasoning paths over the context, then assigns each step to program-based or textual reasoning to reach the final answer. This framework enhances the table reasoning abilities for both in-context learning and fine-tuning methods. GPT-3.5-Turbo following Plan-then-Reason framework surpasses other prompting baselines without self-consistency while using less API calls and in-context demonstrations. We also construct an instruction tuning set TrixInstruct to evaluate the effectiveness of fine-tuning with this framework. We present ProTrix model family by finetuning models on TrixInstruct. Our experiments show that ProTrix family generalizes to diverse unseen tabular tasks with only 6k training instances. We further demonstrate that ProTrix can generate accurate and faithful explanations to answer complex free-form questions. Our work underscores the importance of the planning and reasoning abilities towards a model over tabular tasks with generalizability and interpretability. We open-source our dataset and models at https://github.com/WilliamZR/ProTrix.

The link between in vitro hERG ion channel inhibition and subsequent in vivo QT interval prolongation, a critical risk factor for the development of arrythmias such as Torsade de Pointes, is so well established that in vitro hERG activity alone is often sufficient to end the development of an otherwise promising drug candidate. It is therefore of tremendous interest to develop advanced methods for identifying hERG-active compounds in the early stages of drug development, as well as for proposing redesigned compounds with reduced hERG liability and preserved on-target potency. In this work, we present CardioGenAI, a machine learning-based framework for re-engineering both developmental and commercially available drugs for reduced hERG activity while preserving their pharmacological activity. The framework incorporates novel state-of-the-art discriminative models for predicting hERG channel activity, as well as activity against the voltage-gated NaV1.5 and CaV1.2 channels due to their potential implications in modulating the arrhythmogenic potential induced by hERG channel blockade. We applied the complete framework to pimozide, an FDA-approved antipsychotic agent that demonstrates high affinity to the hERG channel, and generated 100 refined candidates. Remarkably, among the candidates is fluspirilene, a compound which is of the same class of drugs (diphenylmethanes) as pimozide and therefore has similar pharmacological activity, yet exhibits over 700-fold weaker binding to hERG. We envision that this method can effectively be applied to developmental compounds exhibiting hERG liabilities to provide a means of rescuing drug development programs that have stalled due to hERG-related safety concerns. Additionally, the discriminative models can also serve independently as effective components of a virtual screening pipeline. We have made all of our software open-source.

Geocoding is the task of converting location mentions in text into structured data that encodes the geospatial semantics. We propose a new architecture for geocoding, GeoNorm. GeoNorm first uses information retrieval techniques to generate a list of candidate entries from the geospatial ontology. Then it reranks the candidate entries using a transformer-based neural network that incorporates information from the ontology such as the entry's population. This generate-and-rerank process is applied twice: first to resolve the less ambiguous countries, states, and counties, and second to resolve the remaining location mentions, using the identified countries, states, and counties as context. Our proposed toponym resolution framework achieves state-of-the-art performance on multiple datasets. Code and models are available at \url{https://github.com/clulab/geonorm}.

This report presents Waymo's proposal for a systematic fatigue risk management framework that addresses prevention, monitoring, and mitigation of fatigue-induced risks during on-road testing of ADS technology. The proposed framework remains flexible to incorporate continuous improvements, and was informed by state of the art practices, research, learnings, and experience (both internal and external to Waymo). Fatigue is a recognized contributory factor in a substantial fraction of on-road crashes involving human drivers, and mitigation of fatigue-induced risks is still an open concern researched world-wide. While the proposed framework was specifically designed in relation to on-road testing of SAE Level 4 ADS technology, it has implications and applicability to lower levels of automation as well.

When Kroger customers in Cincinnati shop online these days, their groceries may be picked out not by a worker in their local supermarket but by a robot in a nearby warehouse. Gamers at Dave & Buster's in Dallas who want pretzel dogs can order and pay from their phones -- no need to flag down a waiter. And in the drive-through lane at Checkers near Atlanta, requests for Big Buford burgers and Mother Cruncher chicken sandwiches may be fielded not by a cashier in a headset, but by a voice-recognition algorithm. An increase in automation, especially in service industries, may prove to be an economic legacy of the pandemic. Businesses from factories to fast-food outlets to hotels turned to technology last year to keep operations running amid social distancing requirements and contagion fears.

The Virginia-class, nuclear-powered, fast-attack submarine, USS North Dakota (SSN 784), transits the Thames River as it pulls into its homeport on Naval Submarine Base New London in Groton, Conn - file photo. Bringing massive amounts of firepower closer to enemy targets, conducting clandestine "intel" missions in high threat waters and launching undersea attack and surveillance drones are all anticipated missions for the Navy's emerging Block V Virginia-class attack submarines. The boats, nine of which are now surging ahead through a new developmental deal between the Navy and General Dynamics Electric Boat, are reshaping submarine attack strategies and concepts of operations -- as rivals make gains challenging U.S. undersea dominance. Eight of the new 22-billion Block V deal are being engineered with a new 80-foot weapons sections in the boat, enabling the submarine to increase its attack missile capacity from 12 to 40 on-board Tomahawks. "Block V Virginias and Virginia Payload Module are a generational leap in submarine capability for the Navy," Program Executive Officer for Submarines Rear Adm. David Goggins, said in a Navy report.

Purpose: Variability in patient treatment responses can be a barrier to effective care. Utilization of available patient databases may improve the prediction of treatment responses. We evaluated machine learning methods to predict novel, individual patient responses to pregabalin for painful diabetic peripheral neuropathy, utilizing an agent-based modeling and simulation platform that integrates real-world observational study (OS) data and randomized clinical trial (RCT) data. Patients and methods: The best supervised machine learning methods were selected (through literature review) and combined in a novel way for aligning patients with relevant subgroups that best enable prediction of pregabalin responses. Data were derived from a German OS of pregabalin (N 2642) and nine international RCTs (N 1320).