Research & Innovation

Global: Researchers Unveil Benchmark and Detection Framework to Reduce AI Hallucinations in Materials ScienceResearchers have released a new benchmark dataset and a multi‑stage detection system aimed at curbing factual errors…

Global: Researchers Reveal Foundation Models May Overlook Underlying Physics When Adapted to New TasksKeyon Vafa, Peter G. Chang, Ashesh Rambachan, and Sendhil Mullainathan released a study on arXiv in July…

Global: New Heuristics Enable Numeric Planning with Infinite Action SpacesA team of researchers led by Ángel Aso-Mollar, along with Diego Aineto, Enrico Scala, and Eva Onaindia, submitted a preprint on…

Global: Estimating Vehicle Speed with a Smartphone AccelerometerA team of researchers disclosed a new approach on January 12, 2024, that estimates vehicle speed using only the three‑axis accelerometer found in…

Global: Agent2World Framework Boosts Symbolic World Model Generation for LLM PlanningBackgroundResearchers from an international team announced on arXiv in December 2025 a new multi‑agent system called Agent2World, designed to improve…

Global: LLM‑Driven System Replicates Expert Feature Extraction Across Clinical CohortsA research team introduced SNOW, a multi‑agent large language model (LLM) workflow that autonomously generates patient‑level clinical features from unstructured electronic…

Global: New Benchmark Evaluates Spatial Reasoning in Multimodal LLMsA team of researchers has introduced GamiBench, a benchmark designed to assess spatial reasoning and 2D-to-3D planning capabilities in multimodal large language…

Global: Study Finds Humans Struggle to Identify AI-Generated ImagesIn an online experiment conducted by Adrien Pavão and collaborators, participants were asked to classify 20 images as either real photographs or…

Global: Synthetic Chain-of-Thought Datasets Enhance Language Model Reasoning Even When Final Answers Are WrongA team of AI researchers has reported that language models can improve their reasoning performance by training…

Global: Adaptive Label Correction Boosts Ordinal Image Classification AccuracyResearchers publishing on arXiv in September 2025 introduced a novel data‑centric technique, ORDinal Adaptive Correction (ORDAC), to detect and amend noisy labels…