Paleontology, the study of past life, fundamentally relies on fossils to reconstruct ancient ecosystems and understand evolutionary dynamics. Trilobites, as an important group of extinct marine arthropods, offer valuable insights into Paleozoic environments through their well-preserved fossil records. Reconstructing trilobite behaviour from static fossils will set new standards for dynamic reconstructions in scientific research and education. Despite the potential, current computational methods for this purpose like text-to-video (T2V) face significant challenges, such as maintaining visual realism and consistency, which hinder their application in science contexts. To overcome these obstacles, we introduce an automatic T2V prompt learning method. Within this framework, prompts for a fine-tuned video generation model are generated by a large language model, which is trained using rewards that quantify the visual realism and smoothness of the generated video. The fine-tuning of the video generation model, along with the reward calculations make use of a collected dataset of 9,088 Eoredlichia intermedia fossil images, which provides a common representative of visual details of all class of trilobites. Qualitative and quantitative experiments show that our method can generate trilobite videos with significantly higher visual realism compared to powerful baselines, promising to boost both scientific understanding and public engagement.

Crowdfunding refers to releasing fund-raising projects and raising funds through the Internet. To explore the relationship between platform resource investment and value creation in interactive learning between initiators and supporters, this article constructs a three-party game model among the platform, supporters, and the initiator, based on evolutionary game theory, and then obtains the replicator dynamics function of the player and analyzes the evolution trend. Further, this article analyzes the optimal pricing decision of the platform and the initiator under different crowdfunding modes and its optimal mode. The results show that there are two Evolutionary Stable Strategies that are accepted by three players under certain parameters, and the equilibrium point remains stable under external interference. When the net income of initiators participating in value co-creation increases, it can promote the crowdfunding platform to actively participate in the value co-creation process, while it will inhibit the participation of the platform when the net loss of initiators participating in value co-creation increases. In addition, although supporters will also be affected by the willingness of the platform to participate in value co-creation, the willingness of initiators to participate has a greater impact on supporters. As for the mode selection, when the platform does not provide fee preference, considering that the prices of the initiators in the crowdfunding period are the same, single-stage crowdfunding is the dominant mode, and the income of the platform and the initiators is also higher than that under the two-stage crowdfunding. When the product price in the single-stage crowdfunding period is lower than that in the two-stage sales period, the two-stage crowdfunding is the best choice for the initiator.

An aesthetics evaluation model is at the heart of predicting users’ aesthetic experience and developing user interfaces with higher quality. However, previous methods on aesthetic evaluation largely ignore the interpretability of the model and are consequently not suitable for many human-computer interaction tasks. We solve this problem by using a hyper-network to learn the overall aesthetic rating as a combination of individual aesthetic attribute scores. We further introduce a specially designed attentional mechanism in attribute score estimators to enable the users to know exactly which parts/elements of visual inputs lead to the estimated score. We demonstrate our idea by designing an intelligent photography guidance system. Computational results and user studies demonstrate the interpretability and effectiveness of our method.

Value decomposition multi-agent reinforcement learning methods learn the global value function as a mixing of each agent's individual utility functions. Coordination graphs (CGs) represent a higher-order decomposition by incorporating pairwise payoff functions and thus is supposed to have a more powerful representational capacity. However, CGs decompose the global value function linearly over local value functions, severely limiting the complexity of the value function class that can be represented. In this paper, we propose the first non-linear coordination graph by extending CG value decomposition beyond the linear case. One major challenge is to conduct greedy action selections in this new function class to which commonly adopted DCOP algorithms are no longer applicable. We study how to solve this problem when mixing networks with LeakyReLU activation are used. An enumeration method with a global optimality guarantee is proposed and motivates an efficient iterative optimization method with a local optimality guarantee. We find that our method can achieve superior performance on challenging multi-agent coordination tasks like MACO.