Reducing global poverty is a key objective of the Sustainable Development Goals (SDGs). Achieving this requires high-frequency, granular data to capture neighborhood-level changes, particularly in data scarce regions such as low- and middle-income countries. To fill in the data gaps, recent computer vision methods combining machine learning (ML) with earth observation (EO) data to improve poverty estimation. However, while much progress have been made, they often omit intra-annual variations, which are crucial for estimating poverty in agriculturally dependent countries. We explored the impact of integrating intra-annual NDVI information with annual multi-spectral data on model accuracy. To evaluate our method, we created a simulated dataset using Landsat imagery and nighttime light data to evaluate EO-ML methods that use intra-annual EO data. Additionally, we evaluated our method against the Demographic and Health Survey (DHS) dataset across Africa. Our results indicate that integrating specific NDVI-derived features with multi-spectral data provides valuable insights for poverty analysis, emphasizing the importance of retaining intra-annual information.

Socio-technical networks represent emerging cyber-physical infrastructures that are tightly interwoven with human networks. The coupling between human and technical networks presents significant challenges in managing, controlling, and securing these complex, interdependent systems. This paper investigates game-theoretic frameworks for the design and control of socio-technical networks, with a focus on critical applications such as misinformation management, infrastructure optimization, and resilience in socio-cyber-physical systems (SCPS). Core methodologies, including Stackelberg games, mechanism design, and dynamic game theory, are examined as powerful tools for modeling interactions in hierarchical, multi-agent environments. Key challenges addressed include mitigating human-driven vulnerabilities, managing large-scale system dynamics, and countering adversarial threats. By bridging individual agent behaviors with overarching system goals, this work illustrates how the integration of game theory and control theory can lead to robust, resilient, and adaptive socio-technical networks. This paper highlights the potential of these frameworks to dynamically align decentralized agent actions with system-wide objectives of stability, security, and efficiency.

In this work, we propose Asynchronous Perception Machine (APM), a computationally-efficient architecture for test-time-training (TTT). APM can process patches of an image one at a time in any order asymmetrically and still encode semantic-awareness in the net. We demonstrate APM's ability to recognize out-of-distribution images without dataset-specific pre-training, augmentation or any-pretext task. APM offers competitive performance over existing TTT approaches. To perform TTT, APM just distills test sample's representation once. APM possesses a unique property: it can learn using just this single representation and starts predicting semantically-aware features. APM demostrates potential applications beyond test-time-training: APM can scale up to a dataset of 2D images and yield semantic-clusterings in a single forward pass. APM also provides first empirical evidence towards validating GLOM's insight, i.e. input percept is a field. Therefore, APM helps us converge towards an implementation which can do both interpolation and perception on a shared-connectionist hardware. Our code is publicly available at this link: https://rajatmodi62.github.io/apm_project_page/.

Earth observation data have shown promise in predicting species richness of vascular plants ($\alpha$-diversity), but extending this approach to large spatial scales is challenging because geographically distant regions may exhibit different compositions of plant species ($\beta$-diversity), resulting in a location-dependent relationship between richness and spectral measurements. In order to handle such geolocation dependency, we propose Spatioformer, where a novel geolocation encoder is coupled with the transformer model to encode geolocation context into remote sensing imagery. The Spatioformer model compares favourably to state-of-the-art models in richness predictions on a large-scale ground-truth richness dataset (HAVPlot) that consists of 68,170 in-situ richness samples covering diverse landscapes across Australia. The results demonstrate that geolocational information is advantageous in predicting species richness from satellite observations over large spatial scales. With Spatioformer, plant species richness maps over Australia are compiled from Landsat archive for the years from 2015 to 2023. The richness maps produced in this study reveal the spatiotemporal dynamics of plant species richness in Australia, providing supporting evidence to inform effective planning and policy development for plant diversity conservation. Regions of high richness prediction uncertainties are identified, highlighting the need for future in-situ surveys to be conducted in these areas to enhance the prediction accuracy.

Evaluating language models inherit biases through both their biases across multiple languages is critical as training and alignment processes (Feng et al., 2023; LLMs trained in one linguistic and cultural context Scherrer et al., 2024; Motoki et al., 2024). Identifying may not generalize fairly or accurately to others, the opinions and values that LLMs possess has leading to culturally inappropriate or biased outputs been a particularly intriguing area of research, as it when used globally. Our multilingual experiments carries significant sociological and quantitative implications further reveal that models exhibit different for real-world applications (Naous et al., biases in their secondary languages, such as Arabic 2023). Understanding the biases embedded in these and Chinese, which underscores the importance of powerful tools is crucial, given their widespread cross-linguistic evaluations in understanding bias use and the potential influence they may exert on resilience. Furthermore, we introduce a comprehensive users, often in unintended ways (Hartmann et al., human evaluation to compare how humans 2023) or in downstream tasks, such as content moderation.

Multi-modal large language models (MLLMs) are expected to support multi-turn queries of interchanging image and text modalities in production. However, the current MLLMs trained with visual-question-answering (VQA) datasets could suffer from degradation, as VQA datasets lack the diversity and complexity of the original text instruction datasets with which the underlying language model was trained. To address this degradation, we first collect a lightweight, 5k-sample VQA preference dataset where answers were annotated by Gemini for five quality metrics in a granular fashion and investigate standard Supervised Fine-tuning, rejection sampling, Direct Preference Optimization (DPO) and SteerLM algorithms. Our findings indicate that with DPO, we can surpass the instruction-following capabilities of the language model, achieving a 6.73 score on MT-Bench, compared to Vicuna's 6.57 and LLaVA's 5.99. This enhancement in textual instruction-following capability correlates with boosted visual instruction performance (+4.9\% on MM-Vet, +6\% on LLaVA-Bench), with minimal alignment tax on visual knowledge benchmarks compared to the previous RLHF approach. In conclusion, we propose a distillation-based multi-modal alignment model with fine-grained annotations on a small dataset that restores and boosts MLLM's language capability after visual instruction tuning.

I am honoured to be chairing the delivery of the inaugural International Scientific Report on Advanced AI Safety. I am proud to publish this interim report which is the culmination of huge efforts by many experts over the six months since the work was commissioned at the Bletchley Park AI Safety Summit in November 2023. We know that advanced AI is developing very rapidly, and that there is considerable uncertainty over how these advanced AI systems might affect how we live and work in the future. AI has tremendous potential to change our lives for the better, but it also poses risks of harm. That is why having this thorough analysis of the available scientific literature and expert opinion is essential. The more we know, the better equipped we are to shape our collective destiny.

If a video game designed to predict the presidential election is correct, then Donald Trump will take the White House. I played Stardock's'The Political Machine,' which forecasted Trump's shock win in 2016, to see what America could expect once the polls close Tuesday night. The simulation is a turn-based, map-trotting game -- not unlike'Risk' or any other tabletop game of political strategy -- except the board itself reacts to you and your opponent's moves based on historic turnout data, debate focus groups and more. The game's makers claim it'relies heavily on demographic issue patterns' like job, race, sex and income level to determine'what issues [voters] care about,' data the team has updated regularly ever since they created the first edition back in 2004. Initially, I found the game confusing, complicated and frankly dorky, but in time I was enthusiastically buying up local ads, setting up campaign offices and hiring'smear merchants' to spread devious rumors about my opponent: Donald J. Trump.

Meta is opening up its Llama AI models to government agencies and contractors working on national security, the company said in an update. The group includes more than a dozen private sector companies that partner with the US government, including Amazon Web Services, Oracle and Microsoft, as well as defense contractors like Palantir and Lockheed Martin. Mark Zuckerberg hinted at the move last week during Meta's earnings call, when he said the company was "working with the public sector to adopt Llama across the US government." Now, Meta is offering more details about the extent of that work. Oracle, for example, is "building on Llama to synthesize aircraft maintenance documents so technicians can more quickly and accurately diagnose problems, speeding up repair time and getting critical aircraft back in service."

The number of people living in urban areas has tripled in the last 50 years, meaning when a major natural disaster such as an earthquake strikes a city, more lives are in danger. Meanwhile, the strength and frequency of extreme weather events has increased--a trend set to continue as the climate warms. That is spurring efforts around the world to develop a new generation of earthquake monitoring and climate forecasting systems to make detecting and responding to disasters quicker, cheaper, and more accurate than ever. On Nov. 6, at the Barcelona Supercomputing Center in Spain, the Global Initiative on Resilience to Natural Hazards through AI Solutions will meet for the first time. The new United Nations initiative aims to guide governments, organizations, and communities in using AI for disaster management.