image model
Pangram expands its AI detection tools to video and images
The company is moving into more kinds of AI slop. Pangram, maker of a widely used tool for detecting AI-generated text, released new tools for flagging AI-generated image and video slop. With the update, Pangram subscribers can upload videos and get an assessment of whether AI was used to create or edit the clip. The company says the tool is able to distinguish between clips that are partially AI and those that are entirely AI-generated. The tool also comes with a heatmap that can flag which aspects of the video are likely to be AI.
Learning to See by Looking at Noise
Current vision systems are trained on huge datasets, and these datasets come with costs: curation is expensive, they inherit human biases, and there are concerns over privacy and usage rights. To counter these costs, interest has surged in learning from cheaper data sources, such as unlabeled images. In this paper, we go a step further and ask if we can do away with real image datasets entirely, by learning from procedural noise processes. We investigate a suite of image generation models that produce images from simple random processes. These are then used as training data for a visual representation learner with a contrastive loss. In particular, we study statistical image models, randomly initialized deep generative models, and procedural graphics models. Our findings show that it is important for the noise to capture certain structural properties of real data but that good performance can be achieved even with processes that are far from realistic. We also find that diversity is a key property for learning good representations.
Hands On With Google's Nano Banana Pro Image Generator
Google's latest AI image model is vastly better than the previous release at generating text in images. You can expect companies to go buck wild with this update. Nano Banana Pro generated this image, assembling a crowd of standalone characters into one scene. Corporate AI slop feels inescapable in 2025. From website banner ads to outdoor billboards, images generated by businesses using AI tools surround me.
Do Blind Spots Matter for Word-Referent Mapping? A Computational Study with Infant Egocentric Video
Shi, Zekai, Cai, Zhixi, Stefanov, Kalin
Typically, children start to learn their first words between 6 and 9 months, linking spoken utterances to their visual referents. Without prior knowledge, a word encountered for the first time can be interpreted in countless ways; it might refer to any of the objects in the environment, their components, or attributes. Using longitudinal, egocentric, and ecologically valid data from the experience of one child, in this work, we propose a self-supervised and biologically plausible strategy to learn strong visual representations. Our masked autoencoder-based visual backbone incorporates knowledge about the blind spot in human eyes to define a novel masking strategy. This mask and reconstruct approach attempts to mimic the way the human brain fills the gaps in the eyes' field of view. This represents a significant shift from standard random masking strategies, which are difficult to justify from a biological perspective. The pre-trained encoder is utilized in a contrastive learning-based video-text model capable of acquiring word-referent mappings. Extensive evaluation suggests that the proposed biologically plausible masking strategy is at least as effective as random masking for learning word-referent mappings from cross-situational and temporally extended episodes.