Large vision-language models have recently achieved remarkable progress, exhibiting great perception and reasoning abilities concerning visual information. However, how to effectively evaluate these large vision-language models remains a major obstacle, hindering future model development. Traditional benchmarks like VQAv2 or COCO Caption provide quantitative performance measurements but suffer from a lack of fine-grained ability assessment and non-robust evaluation metrics. Recent subjective benchmarks, such as OwlEval, offer comprehensive evaluations of a model's abilities by incorporating human labor, but they are not scalable and display significant bias. In response to these challenges, we propose MMBench, a novel multi-modality benchmark. MMBench methodically develops a comprehensive evaluation pipeline, primarily comprised of two elements. The first element is a meticulously curated dataset that surpasses existing similar benchmarks in terms of the number and variety of evaluation questions and abilities. The second element introduces a novel CircularEval strategy and incorporates the use of ChatGPT. This implementation is designed to convert free-form predictions into pre-defined choices, thereby facilitating a more robust evaluation of the model's predictions. MMBench is a systematically-designed objective benchmark for robustly evaluating the various abilities of vision-language models. We hope MMBench will assist the research community in better evaluating their models and encourage future advancements in this domain. Project page: https://opencompass.org.cn/mmbench.

Russia's defence ministry said its forces destroyed a wave of 20 Ukrainian drones over the Russian-annexed Crimean Peninsula. There were no casualties and no damage as a result of the attempted attack early on Saturday morning, the defence ministry said on the Telegram messaging app. Fourteen drones were destroyed by air defence systems and six were suppressed by electronic warfare, the ministry said. It was not immediately clear what was the target of the reported attacks on the peninsula. Sergei Kryuchkov, an adviser to the Russia-installed governor of Crimea, said earlier that air defence systems were engaged in repelling air attacks in different parts of the peninsula.

A millennium of endeavors to fully recognize and foresee the evolution of dynamic environments has produced many mathematical models for forecasting, and information-gathering techniques, but also exceptionally complicated computational systems. Predefined complicated realities called hyperchaotic frameworks [1] demonstrate unpredictable sequences of behavior over time and sometimes defy standards. These events' temporal and spatial relationships can be compared to physiological kinetics [2]. Several complicated frameworks are currently developed to comprehend spontaneous incidents, their erratic conduct, and how changing the circumstances of actual events may result in an unanticipated shift in the result. Over the duration of the past couple of eons, the objective of being able to understand and anticipate unpredictable actions has been accomplished with the aid of innovations in technology [3] and fundamental principles [4].

Bucharest, Romania – Last Wednesday, a Russian drone attack on Ukraine's grain port infrastructure shook Romania, a NATO member. The force of the attack on the Izmail port, across the Danube River from the Eastern European nation, was so intense that the windows of some village homes in southeastern Romania shattered. Even though she lives far from the county of Tulcea, where the impact was felt, 28-year-old Alexandra, a paralegal from the capital Bucharest, is concerned. "We share a border with Ukraine and the conflict could expand at any moment," she told Al Jazeera. Russia has launched several attacks on Danube ports since pulling out of the wartime Black Sea grain deal.

Timely, accurate, and reliable information is essential for decision-makers, emergency managers, and infrastructure operators during flood events. This study demonstrates a proposed machine learning model, MaxFloodCast, trained on physics-based hydrodynamic simulations in Harris County, offers efficient and interpretable flood inundation depth predictions. Achieving an average R-squared of 0.949 and a Root Mean Square Error of 0.61 ft on unseen data, it proves reliable in forecasting peak flood inundation depths. Validated against Hurricane Harvey and Storm Imelda, MaxFloodCast shows the potential in supporting near-time floodplain management and emergency operations. The model's interpretability aids decision-makers in offering critical information to inform flood mitigation strategies, to prioritize areas with critical facilities and to examine how rainfall in other watersheds influences flood exposure in one area. The MaxFloodCast model enables accurate and interpretable inundation depth predictions while significantly reducing computational time, thereby supporting emergency response efforts and flood risk management more effectively.

Latest methods for visual counterfactual explanations (VCE) harness the power of deep generative models to synthesize new examples of high-dimensional images of impressive quality. However, it is currently difficult to compare the performance of these VCE methods as the evaluation procedures largely vary and often boil down to visual inspection of individual examples and small scale user studies. In this work, we propose a framework for systematic, quantitative evaluation of the VCE methods and a minimal set of metrics to be used. We use this framework to explore the effects of certain crucial design choices in the latest diffusion-based generative models for VCEs of natural image classification (ImageNet). We conduct a battery of ablation-like experiments, generating thousands of VCEs for a suite of classifiers of various complexity, accuracy and robustness. Our findings suggest multiple directions for future advancements and improvements of VCE methods. By sharing our methodology and our approach to tackle the computational challenges of such a study on a limited hardware setup (including the complete code base), we offer a valuable guidance for researchers in the field fostering consistency and transparency in the assessment of counterfactual explanations.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Ukrainian authorities ordered a mandatory evacuation Thursday of nearly 12,000 civilians from 37 towns and villages in the eastern Kharkiv region, where Russian forces reportedly are making a concerted effort to punch through the front line. The local military administration in Kharkiv's Kupiansk district said residents must comply with the evacuation order or sign a document saying they would stay at their own risk. Ukrainian Deputy Defense Minister Hanna Maliar had said the previous day that "the intensity of combat and enemy shelling is high" in the area.

Bogged down in small-scale infantry attacks and incremental advances, Ukraine sought to gain an advantage in the 76th week of the war by attacking Russian shipping at range and was accused of drone strikes targeting Moscow. Drone footage Ukraine released on August 4 showed the prow of a surface drone approaching the Olenegorsky Gornyak, a Ropucha-class Russian landing ship, before going blank at contact range. The attack happened just outside Novorossiysk harbour, supposedly a safe port on the eastern edge of the Black Sea, to which Russia had relocated much of its navy fleet based in Sevastopol after Ukraine sank its Black Sea flagship in May. Daylight footage showed the Olenegorsky Gornyak listing severely to port as it was towed to Novorossiysk harbour. "This poses a great dilemma for the Russians," wrote Phillips O'Brien, professor of strategy at St Andrews University.

Russian forces took down more than a dozen Ukrainian drones flying towards the capital Moscow and the city of Sevastopol in the annexed Crimean peninsula, according to the country's defence ministry. The attack on Moscow on Thursday is the latest in a series of Ukrainian drone raids deep inside Russian territory. The defence ministry said in a statement that two drones "flying in the direction of the city of Moscow were destroyed", while 11 others were brought down near the city of Sevastopol. Two of the Ukrainian drones were "hit by on-duty anti-aircraft defence equipment, another nine were suppressed by means of electronic warfare and crashed in the Black Sea before reaching the target", the ministry said of the attack. There was no immediate comment from Ukraine.

Differential equation discovery, a machine learning subfield, is used to develop interpretable models, particularly in nature-related applications. By expertly incorporating the general parametric form of the equation of motion and appropriate differential terms, algorithms can autonomously uncover equations from data. This paper explores the prerequisites and tools for independent equation discovery without expert input, eliminating the need for equation form assumptions. We focus on addressing the challenge of assessing the adequacy of discovered equations when the correct equation is unknown, with the aim of providing insights for reliable equation discovery without prior knowledge of the equation form.