Understanding the temporal dynamics of biological growth is critical across diverse fields such as microbiology, agriculture, and biodegradation research. Although vision-language models like Contrastive Language Image Pretraining (CLIP) have shown strong capabilities in joint visual-textual reasoning, their effectiveness in capturing temporal progression remains limited. To address this, we propose CLIPTime, a multimodal, multitask framework designed to predict both the developmental stage and the corresponding timestamp of fungal growth from image and text inputs. Built upon the CLIP architecture, our model learns joint visual-textual embeddings and enables time-aware inference without requiring explicit temporal input during testing. To facilitate training and evaluation, we introduce a synthetic fungal growth dataset annotated with aligned timestamps and categorical stage labels. CLIPTime jointly performs classification and regression, predicting discrete growth stages alongside continuous timestamps. We also propose custom evaluation metrics, including temporal accuracy and regression error, to assess the precision of time-aware predictions. Experimental results demonstrate that CLIPTime effectively models biological progression and produces interpretable, temporally grounded outputs, highlighting the potential of vision-language models in real-world biological monitoring applications.

Robots have progressed over the years from clunky hunks of metal to complex, AI-enabled machines capable of running, speaking, and even painting pictures. But even with all those advances humans still can't help but place robots in bizarre and uncomfortable situations. This year, researchers took advanced robots and had them clean up karate-chopped Coke cans, suck up cigarette butts, wear a fleshy, lab-grown face, and pick up dog poo. Two-legged, humanoid robots, which could one day work on factory floors, were gut-punched and forced to wear festive clothes while performing acrobatics. Here are just a few of the oddest things we did to robots this year.

From breaking down toxins to changing the inner workings of the human mind, mushrooms are capable of some seriously impressive features. But now, researchers have taken a fungi's amazing abilities to a new level as they teach a mushroom to crawl in a robot body. Scientists from Cornwell University in New York have created a new type of'biohybrid robot' which puts the humble mushroom in the driver's seat. Natural electrical signals in the mushroom that are triggered by light are able to control the hybrid device's insect-style legs. The researchers say that robots of the future could make use of these fungal brains to respond to navigate more unpredictable environments.

Sinister, brain-controlling mushrooms are a staple in sci-fi shows and literature. While brainwashed humans doing the bidding of fungi remains fantasy, researchers have now learned how to control a robot's movement using electrical signals produced by the mycelium of the common King oyster mushroom. This part machine, part fungus robot could one day serve as a building block for more advanced "biohybrid" chimeras that can remotely analyze agricultural fields for potentially harmful changes in soil chemistry. Researchers from Cornell University and University of Florence in Italy wanted to see if electrical signals pulsing through the mycelium of fungi could be translated into a controlling input for robots. The findings were published last month in the journal Science Robotics.

Upon first glance, the Unconventional Computing Laboratory looks like a regular workspace, with computers and scientific instruments lining its clean, smooth countertops. But if you look closely, the anomalies start appearing. A series of videos shared with PopSci show the weird quirks of this research: On top of the cluttered desks, there are large plastic containers with electrodes sticking out of a foam-like substance, and a massive motherboard with tiny oyster mushrooms growing on top of it. No, this lab isn't trying to recreate scenes from "The Last of Us." The researchers there have been working on stuff like this for awhile: It was founded in 2001 with the belief that the computers of the coming century will be made of chemical or living systems, or wetware, that are going to work in harmony with hardware and software.

HBO's smash-hit adaptation The Last of Us is the latest in a string of horror stories featuring fungi as the source of fear. The zombie-like outbreak that takes place in the show, which is based on the dystopian video game series of the same name, stems from a mutated version of a parasitic mushroom which fictionally evolves to attack humans instead of insects. In Mexican Gothic, by Silvia Moreno-Garcia, the narrator knows something isn't right with a family and their mansion, and soon discovers an intergenerational secret intertwined with a mycelium network. In last year's What Moves the Dead, by T. Kingfisher, it's a mycologist who discovers the root of the town's sudden mysterious illnesses. Science-fiction's fungal fascination goes back much farther.

A mushroom variety that is often been considered useless has now become the prime candidate for computer chip bases. Scientists say the mushroom's skins work nearly as well as traditional computer chip substrates. Researchers from the Johannes Kepler University in Austria stumbled upon the biodegradable alternative while analyzing the uses of fungi-derived materials. Their study, published in the journal Science Advances, shows Ganoderma lucidum mushroom skin works well as a substitute for the substrate used in electrical circuits. "There was a fair share of serendipity involved," Martin Kaltenbrunner, head of the university's Division of Soft Matter Physics and co-author of the paper, told CNN.

As artificial intelligence advances at an unprecedented pace, we tend to see its arrival in emotional terms -- usually, either excitement or fear. But Noumena, a collective of designers, engineers and architects, is looking at AI and robots more practically. What form will they take, how will they survive and develop, and where will they live? It aims to explore those idea with an exhibition entitled "Robotic Habitats." Noumena's project assumes that deep learning systems will grow out of their narrow Go-playing abilities and soon match humans at many, if not most, tasks.