Search

Most current research on commonsense question answering (CQA) has focused on proposing different techniques in natural language processing and text information retrieval. However, for human cognition, retrieving and organizing desired answers from text knowledge related to commonsense questions is far less intuitive and comprehensive than it is when using multi-modal knowledge, such as related images and videos. Motivated by this, we propose a framework for trying the acquisition of diverse modal information, and embedding and integrating it into CQA tasks, further improving the performance and user experience. Specifically, this paper proposes the integration of multi-modal knowledge, including images, image description statements, image scene graphs, and knowledge sub-graphs, into a CQA system. It introduces a parallel embedding technique for this multi-modal knowledge and employs an alignment-interaction-fusion mechanism to facilitate the seamless integration of this multi-modal knowledge. Through extensive experiments, the effectiveness and superiority of our proposed method are demonstrated.

Behavior Trees are widely used in many games, however, they are normally designed in a static way which is hard to deal with dynamic environments. One of the factors that restrict the performance of BTs is the optimization of resources used among subtasks, which has not been paid much attention. In this paper, we concentrate on the problem of dynamic allocation of agents for BTs, i.e., an important resource in games. We design a novel hierarchical learning framework, including the allocation learning module and the action learning module, to find strategies for agent allocation and action selection. Each agent is associated with a network for encoding observations, which is then assigned to a subtask by the allocation learning network. Each subtask uses a network to compute action for the corresponding agent. We design how the losses are computed for the two modules respectively and present the whole training procedure.

In many real-world settings, it is crucially vital for agents to learn to communicate and cooperate. Different cooperation models have been proposed to represent cooperative relations among agents. However, the intensity of the cooperative relation has not received much attention. In particular, how it varied with spatial-temporal information has not been studied deeply. In this paper, we propose a temporal dynamic weighted graph convolution based multi-agent reinforcement learning framework (TWG-Q). We design a weighted graph convolutional network to capture cooperative information among agents. On top of that, a temporal weight learning mechanism is introduced to characterize intensities of cooperations. We design a novel temporal convolutional network in the temporal dimension to extract effective features for the multi-agent reinforcement learning. Extensive experiments show that our method significantly improves the performance of multi-agent reinforcement learning on the public benchmark of micromanagement tasks in StarCraft II.

With the increasing deployment and subsequent retirement of photovoltaic (PV) modules, it is urgent to selectively recover critical metals involved, such as indium (In) and gallium (Ga). Activated carbon, a widely used eco-friendly adsorbent for metal ions, often requires large amounts of toxic chemicals and complicated modifications to achieve selective adsorption. Herein, a novel adsorbent with outstanding ability for In and Ga recovery, phosphoryl-functionalized waste biomass-derived mesoporous activated carbon (P-PDA@MAC), was synthesized via a green and facile one-pot method. This approach eliminates the use of toxic organic reagents and enables functionalization at ambient temperature and pressure, aligning with the principles of green chemistry. Using ethyl phenylphosphinate (EPP) as a precursor, the obtained EPP–PDA@MAC exhibited superior adsorption capacity for In3+ (125.1 mg g−1) and Ga3+ (140.7 mg g−1) and high selectivity (SF XIn = 382.4, SF XGa = 239.0) over competing ions Al3+, Zn2+, Cd2+, Cu2+, and Mg2+. Surprisingly, this adsorbent demonstrated excellent reusability, maintaining adsorption efficiencies above 85% over 9 cycles in a static system and 98% over 50 cycles in a capacitive deionization system. The superior adsorption ability of EPP–PDA@MAC was ascribed to the abundant and stable phosphoryl groups, facilitated by the adhesive polydopamine coating and covalent phosphoryl-functionalization on the high surface area of MAC. Furthermore, a comparison of the adsorption ability, green metrics, and production costs with those of commercial adsorbents underscores the significant industrial application potential of EPP–PDA@MAC. The successful extraction of 99.9% In (purity = 97.79%) and Ga (purity = 90.40%) from waste copper indium gallium selenide PV modules by EPP–PDA@MAC highlights its potential and industrial viability for the circular economy. [ABSTRACT FROM AUTHOR]