Unfortunately, very little to no attention is paid towards addressing calibration ofDNN-based visual object detectors, that occupysimilar space and importance inmanydecision making systems astheir visual classification counterparts. In this work, we study the calibration of DNN-based object detection models, particularly under domain shift.

Neural Information Processing Systems http://nips.cc/

World Bank Chief Economist Indermit Gill speaks during an interview in Washington on Feb. 3. | JIJI WASHINGTON - World Bank Chief Economist Indermit Gill has expressed hopes for Japan's cooperation in addressing global economic disparities that may widen due to the uneven adoption of artificial intelligence technology. In a recent interview, Gill said he believes that productivity gains from the adoption of AI could become a key driver of growth in a global economy that has lost its longterm growth momentum. Although the uneven adoption of AI could widen global economic disparities, Gill said Japan could play a key role in addressing this risk by promoting technology transfer through trade and investment. In a time of both misinformation and too much information, quality journalism is more crucial than ever. By subscribing, you can help us get the story right.

Insidious secret life of promiscuous neurosurgeon found dead in his $2.5m mansion America's best and worst states to retire revealed - and why Florida is no longer the obvious winner Texas Gov. Abbott warns ICE'losing respect' as Minneapolis shooting scandal rocks Trump Is Angelina Jolie quitting America? Private struggles emerge... as actress weighs major lifestyle that threatens to rupture her family Young single mother's selfless final act after finding out she had just weeks to live Seven dead in private jet crash as audio reveals voice said'Let there be light' seconds before tragedy at snowy Maine airport Defiant Trump dismisses Alzheimer's fears as he struggles to recall name of disease in interview NFL's'scripted' conspiracy theory resurfaces as fans find five-month old post hinting at Super Bowl 60 matchup Stunning twist of fate that saw Brittany leave Patrick Mahomes weeks after he was drafted by the Chiefs... Kate Hudson's Oscar nomination torched as an'abomination' amid toxic family feud over Song Sung Blue Mystery of Egypt's Giza pyramids deepens as hidden megastructure 4,000 feet below is revealed Prophecy from apocalyptic'messiah' warns of death so widespread'even birds won't escape' A poem written over 120 years ago by a revered religious figure has resurfaced as some fear its prediction of an apocalyptic event could be coming true today. Hazrat Mirza Ghulam Ahmad, also known as the Promised Messiah and the Imam Mahdi, wrote a 1905 poem describing massive earthquakes and destruction across the world, which some have now interpreted as a warning of World War III . In the poem, published around the time of his death in 1908, Ahmad predicted streams of blood flowing from widespread death, entire regions being wiped out, a massive earthquake, and even strange sky events beyond scientific explanation. It mentions of calamity befalling the Czar of Russia has been seen by some as foreshadowing modern conflicts involving Russia, such as the war in Ukraine and continued tensions with the US and NATO .

Traditional feature engineering approaches for molecular sequence classification suffer from sparsity issues and computational complexity, while deep learning models often underperform on tabular biological data. This paper introduces a novel topological approach that transforms molecular sequences into images by combining Chaos Game Representation (CGR) with Rips complex construction from algebraic topology. Our method maps sequence elements to 2D coordinates via CGR, computes pairwise distances, and constructs Rips complexes to capture both local structural and global topological features. We provide formal guarantees on representation uniqueness, topological stability, and information preservation. Extensive experiments on anticancer peptide datasets demonstrate superior performance over vector-based, sequence language models, and existing image-based methods, achieving 86.8\% and 94.5\% accuracy on breast and lung cancer datasets, respectively. The topological representation preserves critical sequence information while enabling effective utilization of vision-based deep learning architectures for molecular sequence analysis.

Large language models (LLMs) increasingly mediate human communication, decision support, content creation, and information retrieval. Despite impressive fluency, these systems frequently produce biased or stereotypical content, especially when prompted with socially sensitive language. A growing body of research has demonstrated that such biases disproportionately affect low-resource languages, where training data is limited and culturally unrepresentative. This paper presents a comprehensive study of inference-time bias mitigation, a strategy that avoids retraining or fine-tuning and instead operates directly on model outputs. Building on preference-ranking models (PRMs), we introduce a unified evaluation framework comparing three methods: (1) baseline single-word generation, (2) PRM-Select best-of-N sampling, and (3) PRM-Sequential refinement guided by PRM critiques. We evaluate these techniques across 200 English prompts and their Urdu counterparts, designed to reflect socio-cultural contexts relevant to gender, ethnicity, religion, nationality, disability, profession, age, and socioeconomic categories. Using GPT-3.5 as a candidate generator and GPT-4o-mini as a PRM-based bias and utility scorer, we provide an extensive quantitative analysis of bias reduction, utility preservation, and cross-lingual disparities. Our findings show: (a) substantial gains over the baseline for both languages; (b) consistently lower fairness scores for Urdu across all methods, highlighting structural inequities in multilingual LLM training; and (c) distinct improvement trajectories between PRM-Select and PRM-Sequential. The study contributes an extensible methodology, interpretable metrics, and cross-lingual comparisons that can support future work on fairness evaluation in low-resource languages.

Accurate forecasting of urban air pollution is essential for protecting public health and guiding mitigation policies. While Deep Learning (DL) and hybrid pipelines dominate recent research, their complexity and limited interpretability hinder operational use. This study investigates whether lightweight additive models -- Facebook Prophet (FBP) and NeuralProphet (NP) -- can deliver competitive forecasts for particulate matter (PM$_{2.5}$, PM$_{10}$) in Beijing, China. Using multi-year pollutant and meteorological data, we applied systematic feature selection (correlation, mutual information, mRMR), leakage-safe scaling, and chronological data splits. Both models were trained with pollutant and precursor regressors, with NP additionally leveraging lagged dependencies. For context, two machine learning baselines (LSTM, LightGBM) and one traditional statistical model (SARIMAX) were also implemented. Performance was evaluated on a 7-day holdout using MAE, RMSE, and $R^2$. Results show that FBP consistently outperformed NP, SARIMAX, and the learning-based baselines, achieving test $R^2$ above 0.94 for both pollutants. These findings demonstrate that interpretable additive models remain competitive with both traditional and complex approaches, offering a practical balance of accuracy, transparency, and ease of deployment.

Resilient road infrastructure is a cornerstone of the UN Sustainable Development Goals. Yet a primary indicator of network functionality and resilience is critically lacking: a comprehensive global baseline of road surface information. Here, we overcome this gap by applying a deep learning framework to a global mosaic of Planetscope satellite imagery from 2020 and 2024. The result is the first global multi-temporal dataset of road pavedness and width for 9.2 million km of critical arterial roads, achieving 95.5% coverage where nearly half the network was previously unclassified. This dataset reveals a powerful multi-scale geography of human development. At the planetary scale, we show that the rate of change in pavedness is a robust proxy for a country's development trajectory (correlation with HDI = 0.65). At the national scale, we quantify how unpaved roads constitute a fragile backbone for economic connectivity. We further synthesize our data into a global Humanitarian Passability Matrix with direct implications for humanitarian logistics. At the local scale, case studies demonstrate the framework's versatility: in Ghana, road quality disparities expose the spatial outcomes of governance; in Pakistan, the data identifies infrastructure vulnerabilities to inform climate resilience planning. Together, this work delivers both a foundational dataset and a multi-scale analytical framework for monitoring global infrastructure, from the dynamics of national development to the realities of local governance, climate adaptation, and equity. Unlike traditional proxies such as nighttime lights, which reflect economic activity, road surface data directly measures the physical infrastructure that underpins prosperity and resilience - at higher spatial resolution.