Large language models are increasingly capable of producing creative texts, yet most studies on AI-generated poetry focus on English -- a language that dominates training data. In this paper, we examine the perception of AI- and human-written Czech poetry. We ask if Czech native speakers are able to identify it and how they aesthetically judge it. Participants performed at chance level when guessing authorship (45.8\% correct on average), indicating that Czech AI-generated poems were largely indistinguishable from human-written ones. Aesthetic evaluations revealed a strong authorship bias: when participants believed a poem was AI-generated, they rated it as less favorably, even though AI poems were in fact rated equally or more favorably than human ones on average. The logistic regression model uncovered that the more the people liked a poem, the less probable was that they accurately assign the authorship. Familiarity with poetry or literary background had no effect on recognition accuracy. Our findings show that AI can convincingly produce poetry even in a morphologically complex, low-resource (with respect of the training data of AI models) Slavic language such as Czech. The results suggest that readers' beliefs about authorship and the aesthetic evaluation of the poem are interconnected.

Developing high-performing, yet interpretable models remains a critical challenge in modern AI. Concept-based models (CBMs) attempt to address this by extracting human-understandable concepts from a global encoding (e.g., image encoding) and then applying a linear classifier on the resulting concept activations, enabling transparent decision-making. However, their reliance on holistic image encodings limits their expressiveness in object-centric real-world settings and thus hinders their ability to solve complex vision tasks beyond single-label classification. To tackle these challenges, we introduce Object-Centric Concept Bottlenecks (OCB), a framework that combines the strengths of CBMs and pre-trained object-centric foundation models, boosting performance and interpretability. We evaluate OCB on complex image datasets and conduct a comprehensive ablation study to analyze key components of the framework, such as strategies for aggregating object-concept encodings. The results show that OCB outperforms traditional CBMs and allows one to make interpretable decisions for complex visual tasks.

We introduce a general, scalable computational framework for multi-axis 3D printing based on implicit neural fields (INFs) that unifies all stages of toolpath generation and global collision-free motion planning. In our pipeline, input models are represented as signed distance fields, with fabrication objectives such as support-free printing, surface finish quality, and extrusion control being directly encoded in the optimization of an implicit guidance field. This unified approach enables toolpath optimization across both surface and interior domains, allowing shell and infill paths to be generated via implicit field interpolation. The printing sequence and multi-axis motion are then jointly optimized over a continuous quaternion field. Our continuous formulation constructs the evolving printing object as a time-varying SDF, supporting differentiable global collision handling throughout INF-based motion planning. Compared to explicit-representation-based methods, INF-3DP achieves up to two orders of magnitude speedup and significantly reduces waypoint-to-surface error. We validate our framework on diverse, complex models and demonstrate its efficiency with physical fabrication experiments using a robot-assisted multi-axis system.

Both single-view video inputs were generated using existing video generation models (Brooks et al., 2024; Runway, 2024). Auto-regressive generation is applied to extend the video length. A BSTRACT High resolution panoramic video content is paramount for immersive experiences in Virtual Reality, but is non-trivial to collect as it requires specialized equipment and intricate camera setups. In this work, we introduce VideoPanda, a novel approach for synthesizing 360 videos conditioned on text or single-view video data. VideoPanda leverages multi-view attention layers to augment a video diffusion model, enabling it to generate consistent multi-view videos that can be combined into immersive panoramic content. VideoPanda is trained jointly using two conditions: text-only and single-view video, and supports autoregressive generation of long-videos. To overcome the computational burden of multi-view video generation, we randomly subsample the duration and camera views used during training and show that the model is able to gracefully generalize to generating more frames during inference. Extensive evaluations on both real-world and synthetic video datasets demonstrate that VideoPanda generates more realistic and coherent 360 panoramas across all input conditions compared to existing methods. First and second author contributed equally. To enable such experiences, it is essential to have access to high-quality and high-resolution panoramic videos. However, recording such videos is both expensive and time-consuming, as it requires intricate camera setups and specialized equipment.

Visual and linguistic concepts naturally organize themselves in a hierarchy, where a textual concept "dog" entails all images that contain dogs. Despite being intuitive, current large-scale vision and language models such as CLIP do not explicitly capture such hierarchy. We propose MERU, a contrastive model that yields hyperbolic representations of images and text. Hyperbolic spaces have suitable geometric properties to embed tree-like data, so MERU can better capture the underlying hierarchy in image-text datasets. Our results show that MERU learns a highly interpretable and structured representation space while being competitive with CLIP's performance on standard multi-modal tasks like image classification and image-text retrieval.

As artificial intelligence (AI) continues to permeate various domains, concerns surrounding trust and transparency in AI-driven inference and training processes have emerged, particularly with respect to potential biases and traceability challenges. Decentralized solutions such as blockchain have been proposed to tackle these issues, but they often struggle when dealing with large-scale models, leading to time-consuming inference and inefficient training verification. To overcome these limitations, we introduce BRAIN, a Blockchain-based Reliable AI Network, a novel platform specifically designed to ensure reliable inference and training of large models. BRAIN harnesses a unique two-phase transaction mechanism, allowing real-time processing via pipelining by separating request and response transactions. Each randomly-selected inference committee commits and reveals the inference results, and upon reaching an agreement through a smart contract, then the requested operation is executed using the consensus result. Additionally, BRAIN carries out training by employing a randomly-selected training committee. They submit commit and reveal transactions along with their respective scores, enabling local model aggregation based on the median value of the scores. Experimental results demonstrate that BRAIN delivers considerably higher inference throughput at reasonable gas fees. In particular, BRAIN's tasks-per-second performance is 454.4293 times greater than that of a naive single-phase implementation.

Voluntary behavior of humans appears to be composed of small, elementary building blocks or behavioral primitives. While this modular organization seems crucial for the learning of complex motor skills and the flexible adaption of behavior to new circumstances, the problem of learning meaningful, compositional abstractions from sensorimotor experiences remains an open challenge. Here, we introduce a computational learning architecture, termed surprise-based behavioral modularization into event-predictive structures (SUBMODES), that explores behavior and identifies the underlying behavioral units completely from scratch. The SUBMODES architecture bootstraps sensorimotor exploration using a self-organizing neural controller. While exploring the behavioral capabilities of its own body, the system learns modular structures that predict the sensorimotor dynamics and generate the associated behavior. In line with recent theories of event perception, the system uses unexpected prediction error signals, i.e., surprise, to detect transitions between successive behavioral primitives. We show that, when applied to two robotic systems with completely different body kinematics, the system manages to learn a variety of complex and realistic behavioral primitives. Moreover, after initial self-exploration the system can use its learned predictive models progressively more effectively for invoking model predictive planning and goal-directed control in different tasks and environments.

Neural networks have proven their capabilities by outperforming many other approaches on regression or classification tasks on various kinds of data. Other astonishing results have been achieved using neural nets as data generators, especially in settings of generative adversarial networks (GANs). One special application is the field of image domain translations. Here, the goal is to take an image with a certain style (e.g. a photography) and transform it into another one (e.g. a painting). If such a task is performed for unpaired training examples, the corresponding GAN setting is complex, the neural networks are large, and this leads to a high peak memory consumption during, both, training and evaluation phase. This sets a limit to the highest processable image size. We address this issue by the idea of not processing the whole image at once, but to train and evaluate the domain translation on the level of overlapping image subsamples. This new approach not only enables us to translate high-resolution images that otherwise cannot be processed by the neural network at once, but also allows us to work with comparably small neural networks and with limited hardware resources. Additionally, the number of images required for the training process is significantly reduced. We present high-quality results on images with a total resolution of up to over 50 megapixels and emonstrate that our method helps to preserve local image details while it also keeps global consistency.