Why it's high time we stopped anthropomorphising ants We have long drawn parallels between ants and humans. Now we are comparing the insects to computers. Pollution is making many cities unlivable for their human inhabitants, but it is also tearing ant families and communities apart. Ants recognise each other by sniffing a thin layer of hydrocarbons on the outside of their exoskeletons; each colony has a specific "smell". But a new study reveals that ozone emissions can change the structure of these hydrocarbons.

Advances in diffusion models for generative artificial intelligence have recently propagated to the time series (TS) domain, demonstrating state-of-the-art performance on various tasks. However, prior works on TS diffusion models often borrow the framework of existing works proposed in other domains without considering the characteristics of TS data, leading to suboptimal performance. In this work, wepropose Adaptive Noise schedule for Time series diffusion models (ANT), which automatically predetermines proper noise schedules for given TS datasets based on their statistics representing non-stationarity. Our intuition is that an optimal noise schedule should satisfy the following desiderata: 1) It linearly reduces the non-stationarity of TS data so that all diffusion steps are equally meaningful, 2) the data is corrupted to the random noise at the final step, and 3) the number of steps is sufficiently large. The proposed method is practical for use in that it eliminates the necessity of finding the optimal noise schedule with a small additional cost to compute the statistics for given datasets, which can be done offline before training.

Ant evolution favored large colonies over individual strength. Breakthroughs, discoveries, and DIY tips sent every weekday. Here's a fun (and creepy) fact: The Earth is home to approximately 20 quadrillion ants . To put zeroes on it, that's around 20,000,000,000,000,000 of the six-legged insects living all around us. How did such diminutive creatures attain their prominent--and ecologically vital -role on the planet?

New research shows ill pupae emit a chemical signal before ever leaving their cocoons. Breakthroughs, discoveries, and DIY tips sent every weekday. Ants are some of nature's most selfless animals. They practice social distancing when ill, consistently act for the good of the colony, and will die to protect their queen from outsiders. This evolutionary drive is so strong that at least one ant species will even willingly sacrifice before they leave their cocoons.

This highlights the importance of selecting an appropriate schedule for each dataset.

Additional ablation studies on Ant is shown in Figure 1a for a thorough comparison. We show in Figure 1 the visualization of the late stage policy of one seed from Walker2d-v2 environment.

Biological swarms, such as ant colonies, achieve collective goals through decentralized and stochastic individual behaviors. Similarly, physical systems composed of gases, liquids, and solids exhibit random particle motion governed by entropy maximization, yet do not achieve collective objectives. Despite this analogy, no unified framework exists to explain the stochastic behavior in both biological and physical systems. Here, we present empirical evidence from \textit{Formica polyctena} ants that reveals a shared statistical mechanism underlying both systems: maximization under different energy function constraints. We further demonstrate that robotic swarms governed by this principle can exhibit scalable, decentralized cooperation, mimicking physical phase-like behaviors with minimal individual computation. These findings established a unified stochastic model linking biological, physical, and robotic swarms, offering a scalable principle for designing robust and intelligent swarm robotics.

Abstract-- Autonomous driving systems remain critically vulnerable to the long-tail of rare, out-of-distribution scenarios with semantic anomalies. While Vision Language Models (VLMs) offer promising reasoning capabilities, naive prompting approaches yield unreliable performance and depend on expensive proprietary models, limiting practical deployment. We introduce SA V ANT (Semantic Analysis with Vision-Augmented Anomaly deT ection), a structured reasoning framework that achieves high accuracy and recall in detecting anomalous driving scenarios from input images through layered scene analysis and a two-phase pipeline: structured scene description extraction followed by multi-modal evaluation. Our approach transforms VLM reasoning from ad-hoc prompting to systematic analysis across four semantic layers: Street, Infrastructure, Movable Objects, and Environment. SA V ANT achieves 89.6% recall and 88.0% accuracy on real-world driving scenarios, significantly outperforming unstructured baselines. More importantly, we demonstrate that our structured framework enables a fine-tuned 7B parameter open-source model (Qwen2.5VL) to achieve 90.8% recall and 93.8% accuracy--surpassing all models evaluated while enabling local deployment at near-zero cost. By automatically labeling over 9,640 real-world images with high accuracy, SA V ANT addresses the critical data scarcity problem in anomaly detection and provides a practical path toward reliable, accessible semantic monitoring for autonomous systems.

The insects build differently when exposed to a pathogen. Breakthroughs, discoveries, and DIY tips sent every weekday. When the COVID-19 pandemic struck, we had to completely reorganize our spaces to avoid close contact. Transparent barriers were erected between seats, cashiers and customers, receptionists and patients, while stickers encouraged people to sit or stand at least six feet away from each other. A new study, however, reveals that we're not the only ones who take such actions to lessen the spread of a disease.