The global elderly population is increasing rapidly, and more and more countries are stepping into the aging society. Because of deterioration in gait-related functions, such as muscle activity, most elderly people have difficulty walking, which is one of the most basic activities of daily living. A wearable lower limb robot exoskeleton offers a viable solution to this issue. Rigid exoskeletons usually have fewer degrees of freedom and require a quite big power supply for actuation, resulting in difficulties during wearing and motion. Soft exoskeletons could be an alternative choice for elderly assistance, due to their advantages of lighter weight, simpler mechanism, and compliance. Therefore, this research proposed a soft array actuator for a lower limb assistive exoskeleton for elderly people. The fully compliant actuation mechanism was designed using flexible Thermoplastic Polyurethane fabric to power the soft exoskeleton, making it compact, light, and comfortable to wear. The proposed array actuator was modeled on kinematics, contacting force, output torque, and dynamics. Mechanical performance of the compliant actuation mechanism during inflation/deflation at different air pressures and during static force testing has been evaluated. The internal air pressure of the soft array actuator reaches 100 kPa in 0.2 s and fully deflates in 0.48 s. It can generate 53.7–55.7 N to output 8.1–11.2 N·m of torque at the endpoint, which is 13.5% –18.7% of the maximum human hip joint torque during natural walking. The proposed soft actuation mechanism, with good wearability and performance, could be a good fit for a robot exoskeleton that improves natural gait and reduces human metabolic consumption during walking among the elderly. Its lightweight design, good invisibility, and high power-to-weight ratio enable the proposed soft array actuator to provide compliant, continuous, and consistent gait assistance without imposing a psychological burden on the elderly.

Large language models (LLMs) have shown strong potential in enhancing text clustering when combined with traditional embedding models.However, existing methods predominantly treat LLMs as static pseudo-oracles, i.e., unidirectionally querying them for similarity assessment or data augmentation, while never seeking feedback from embedding models to improve them.In this work, we propose a training framework that enables bidirectional refinement between LLMs and embedding models.We first design task-aware prompts to guide the LLM in generating interpretations for the input texts.These interpretations are projected into the embedding space, in which interpretations that are preferred by the embedding model are selected based on their distribution densities.The selected interpretations are then used to fine-tune the LLM via preference optimization to prioritize the generation of helpful interpretations.Meanwhile, we enhance the embedding model via contrastive learning on the generated interpretations and perform clustering on the output embeddings, leading to iterative cotraining between the LLM and the embedding model.Experiments on 14 benchmark datasets across 5 tasks demonstrate the effectiveness of our method.

BERT and TFIDF features excel in capturing rich semantics and important words, respectively.Since most existing clustering methods are solely based on the BERT model, they often fall short in utilizing keyword information, which, however, is very useful in clustering short texts.In this paper, we propose a CO-Training Clustering (COTC) framework to make use of the collective strengths of BERT and TFIDF features.Specifically, we develop two modules responsible for the clustering of BERT and TFIDF features, respectively.We use the deep representations and cluster assignments from the TFIDF module outputs to guide the learning of the BERT module, seeking to align them at both the representation and cluster levels.Reversely, we also use the BERT module outputs to train the TFIDF module, thus leading to the mutual promotion.We then show that the alternating co-training framework can be placed under a unified joint training objective, which allows the two modules to be connected tightly and the training signals to be propagated efficiently.Experiments on eight benchmark datasets show that our method outperforms current SOTA methods significantly.

In the massive multiple-input and multiple-output (Massive MIMO) systems, the maximum likelihood (ML) detection problem is NP-hard and becoming classically intricate with the number of transmitting antennas and symbols increasing. The quantum approximate optimization algorithm (QAOA), a leading candidate algorithm running in the noisy intermediate-scale quantum (NISQ) devices, can show quantum advantage for approximately solving combinatorial optimization problems. In this paper, we propose the QAOA based on the maximum likelihood detection solver of binary symbols. In the proposed scheme, we first conduct a universal and compact analytical expression for the expectation value of the 1-level QAOA. Second, a Bayesian optimization based parameters initialization is presented, which can speedup the convergence of the QAOA to a lower local minimum and improve the probability of measuring the exact solution. Compared to the state-of-the-art QAOA based ML detection algorithm, our scheme has the more universal and compact expectation value expression of the 1-level QAOA, and requires few quantum resources and has the higher probability to obtain the exact solution.