The recent improvements of artificial intelligence (AI) technologies present a revolutionary opportunity for a wide variety of services. One of the most impactful AI technologies, gaining hundreds of millions of users in mere months, are conversational agents based on Large Language Models (LLMs). An obvious application example of conversational agents is found in gaming, where players often engage in conversation with non-player-characters (NPCs). The use of contemporary AI in this context is expected to bring unprecedented levels of adaptability and freedom of expression to in-game conversations, but may come with its own set of drawbacks, such as increased response latency, which may impair user experience during such interactions. In this paper we present the results of a user study investigating the impact of two different types of latency — time to first token and time per output token — on the overall Quality of Experience and player experience in a conversational task with an LLM-powered NPC in a text-based fantasy role-playing game. Conducted with a sample of fairly regular AI users (N=20), our study provides valuable insights regarding the possible threshold for noticeable latency for this type of service.

Current best local descriptors are learned on a large data set of matching and non-matching keypoint pairs. However, data of this kind are not always available, since the detailed keypoint correspondences can be hard to establish. On the other hand, we can often obtain labels for pairs of keypoint bags. For example, keypoint bags extracted from two images of the same object under different views form a matching pair, and keypoint bags extracted from images of different objects form a non-matching pair. On average, matching pairs should contain more corresponding keypoints than non-matching pairs. We describe an end-to-end differentiable architecture that enables the learning of local keypoint descriptors from such weakly labeled data. In addition, we discuss how to improve the method by incorporating the procedure of mining hard negatives. We also show how our approach can be used to learn convolutional features from unlabeled video signals and 3D models.

Current best local descriptors are learned on a large dataset of matching and non-matching keypoint pairs. However, data of this kind is not always available since detailed keypoint correspondences can be hard to establish. On the other hand, we can often obtain labels for pairs of keypoint bags. For example, keypoint bags extracted from two images of the same object under different views form a matching pair, and keypoint bags extracted from images of different objects form a non-matching pair. On average, matching pairs should contain more corresponding keypoints than non-matching pairs. We describe an end-to-end differentiable architecture that enables the learning of local keypoint descriptors from such weakly-labeled data.

Abstract An image mosaic is an assembly of a large number of small images, usually called tiles, taken from a specific dictionary/codebook. When viewed as a whole, the appearance of a single large image emerges, i.e. each tile approximates a small block of pixels. ASCII art is a related (and older) graphic design technique for producing images from printable characters. Although automatic procedures for both of these visualization schemes have been studied in the past, some are computationally heavy and cannot offer real‐time and interactive performance. We propose an algorithm able to reproduce the quality of existing non‐photorealistic rendering techniques, in particular ASCII art and image mosaics, obtaining large performance speed‐ups. The basic idea is to partition the input image into a rectangular grid and use a decision tree to assign a tile from a pre‐determined codebook to each cell. Our implementation can process video streams from webcams in real time and it is suitable for modestly equipped devices. We evaluate our technique by generating the renderings of a variety of images and videos, with good results. The source code of our engine is publicly available.