Reasoning over TKGs has two challenges: 1.

This intervention significantly improves the performance of LLaMA models on the TruthfulQA benchmark.

We contend that utilizing existing relational databases is a promising approach to construct a benchmark that has both merits.

Amir Patel is an Associate Professor of Robotics & AI in the Department of Computer Science at University College London (UCL). His research uses robotics methods--sensor fusion, computer vision, mechanical modelling, and optimal control--to understand and quantify animal locomotion, especially high-speed predators such as the cheetah, and to translate these insights into bio-inspired machines. Previously, he served on the faculty of Electrical Engineering at the University of Cape Town, where he founded and directed the African Robotics Unit (ARU). Robot Talk is a weekly podcast that explores the exciting world of robotics, artificial intelligence and autonomous machines. Robot Talk is a weekly podcast that explores the exciting world of robotics, artificial intelligence and autonomous machines.

Senator accused of steamy affair with her bodyguard in bombshell lawsuit from his WIFE: 'Bring MDMA so I can guide you' Socialite who accused playboy twins of sex attack at Hamptons'castle' is found dead in unexplained circumstances Amy Schumer's friends reveal true meaning of thin bikini pictures and why they're'monitoring her'... as depth of ex Chris Fischer's heartbreak is laid bare Hunter Biden's stripper baby mama asks for him to be ARRESTED over claims he is still failing to pay her child support Ellen Greenberg's fiancé Sam Goldberg breaks cover as feds reopen probe into her'suicide'... and late teacher's mother shares incredible sign sent from beyond the grave Nicole Richie addresses her daughter's new identity after unveiling transformation on her 18th birthday '90s Vogue model Niki Taylor looks amazing as she sizzles at age 50 for new campaign Karoline Leavitt reveals the thinking behind Trump's call to cancel elections Family of Tyler Robinson's transgender lover speaks ...

Class imbalance significantly degrades classification performance, yet its effects are rarely analyzed from a unified theoretical perspective. We propose a principled framework based on three fundamental scales: the imbalance coefficient $η$, the sample--dimension ratio $κ$, and the intrinsic separability $Δ$. Starting from the Gaussian Bayes classifier, we derive closed-form Bayes errors and show how imbalance shifts the discriminant boundary, yielding a deterioration slope that predicts four regimes: Normal, Mild, Extreme, and Catastrophic. Using a balanced high-dimensional genomic dataset, we vary only $η$ while keeping $κ$ and $Δ$ fixed. Across parametric and non-parametric models, empirical degradation closely follows theoretical predictions: minority Recall collapses once $\log(η)$ exceeds $Δ\sqrtκ$, Precision increases asymmetrically, and F1-score and PR-AUC decline in line with the predicted regimes. These results show that the triplet $(η,κ,Δ)$ provides a model-agnostic, geometrically grounded explanation of imbalance-induced deterioration.

Community science observational datasets are useful in epidemiology and ecology for modeling species distributions, but the heterogeneous nature of the data presents significant challenges for standardization, data quality assurance and control, and workflow management. In this paper, we present a data workflow for cleaning and harmonizing multiple community science datasets, which we implement in a case study using eBird, iNaturalist, GBIF, and other datasets to model the impact of highly pathogenic avian influenza in populations of birds in the subantarctic. We predict population sizes for several species where the demographics are not known, and we present novel estimates for potential mortality rates from HPAI for those species, based on a novel aggregated dataset of mortality rates in the subantarctic.

Cartographic reasoning is the skill of interpreting geographic relationships by aligning legends, map scales, compass directions, map texts, and geometries across one or more map images. Although essential as a concrete cognitive capability and for critical tasks such as disaster response and urban planning, it remains largely unevaluated. Building on progress in chart and infographic understanding, recent large vision language model studies on map visual question-answering often treat maps as a special case of charts. In contrast, map VQA demands comprehension of layered symbology (e.g., symbols, geometries, and text labels) as well as spatial relations tied to orientation and distance that often span multiple maps and are not captured by chart-style evaluations. To address this gap, we introduce FRIEDA, a benchmark for testing complex open-ended cartographic reasoning in LVLMs. FRIEDA sources real map images from documents and reports in various domains and geographical areas. Following classifications in Geographic Information System (GIS) literature, FRIEDA targets all three categories of spatial relations: topological (border, equal, intersect, within), metric (distance), and directional (orientation). All questions require multi-step inference, and many require cross-map grounding and reasoning. We evaluate eleven state-of-the-art LVLMs under two settings: (1) the direct setting, where we provide the maps relevant to the question, and (2) the contextual setting, where the model may have to identify the maps relevant to the question before reasoning. Even the strongest models, Gemini-2.5-Pro and GPT-5-Think, achieve only 38.20% and 37.20% accuracy, respectively, far below human performance of 84.87%. These results reveal a persistent gap in multi-step cartographic reasoning, positioning FRIEDA as a rigorous benchmark to drive progress on spatial intelligence in LVLMs.

Artificial intelligence methods are increasingly being explored for managing wildfires and other natural hazards. In particular, reinforcement learning (RL) is a promising path towards improving outcomes in such uncertain decision-making scenarios and moving beyond reactive strategies. However, training RL agents requires many environment interactions, and the speed of existing wildfire simulators is a severely limiting factor. We introduce $\texttt{JaxWildfire}$, a simulator underpinned by a principled probabilistic fire spread model based on cellular automata. It is implemented in JAX and enables vectorized simulations using $\texttt{vmap}$, allowing high throughput of simulations on GPUs. We demonstrate that $\texttt{JaxWildfire}$ achieves 6-35x speedup over existing software and enables gradient-based optimization of simulator parameters. Furthermore, we show that $\texttt{JaxWildfire}$ can be used to train RL agents to learn wildfire suppression policies. Our work is an important step towards enabling the advancement of RL techniques for managing natural hazards.