SNN-BERT: Training-efficient Spiking Neural Networks for energy-efficient BERT.

Spiking Neural Networks (SNNs) are naturally suited to process sequence tasks such as NLP with low power, due to its brain-inspired spatio-temporal dynamics and spike-driven nature. Current SNNs employ "repeat coding" that re-enter all input tokens at each timestep, which fails to fully exploit temporal relationships between the tokens and introduces memory overhead. In this work, we align the number of input tokens with the timestep and refer to this input coding as "individual coding". To cope with the increase in training time for individual encoded SNNs due to the dramatic increase in timesteps, we design a Bidirectional Parallel Spiking Neuron (BPSN) with following features: First, BPSN supports spike parallel computing and effectively avoids the issue of uninterrupted firing; Second, BPSN excels in handling adaptive sequence length tasks, which is a capability that existing work does not have; Third, the fusion of bidirectional information enhances the temporal information modeling capabilities of SNNs; To validate the effectiveness of our BPSN, we present the SNN-BERT, a deep direct training SNN architecture based on the BERT model in NLP. Compared to prior repeat 4-timestep coding baseline, our method achieves a 6.46× reduction in energy consumption and a significant 16.1% improvement, raising the performance upper bound of the SNN domain on the GLUE dataset to 74.4%. Additionally, our method achieves 3.5× training acceleration and 3.8× training memory optimization. Compared with artificial neural networks of similar architecture, we obtain comparable performance but up to 22.5× energy efficiency. We would provide the codes.

Enhancing Lithium-Sulfur Battery Performance with MXene: Specialized Structures and Innovative Designs.

Established in 1962, lithium-sulfur (Li-S) batteries boast a longer history than commonly utilized lithium-ion batteries counterparts such as LiCoO2 (LCO) and LiFePO4 (LFP) series, yet they have been slow to achieve commercialization. This delay, significantly impacting loading capacity and cycle life, stems from the long-criticized low conductivity of the cathode and its byproducts, alongside challenges related to the shuttle effect, and volume expansion. Strategies to improve the electrochemical performance of Li-S batteries involve improving the conductivity of the sulfur cathode, employing an adamantane framework as the sulfur host, and incorporating catalysts to promote the transformation of lithium polysulfides (LiPSs). 2D MXene and its derived materials can achieve almost all of the above functions due to their numerous active sites, external groups, and ease of synthesis and modification. This review comprehensively summarizes the functionalization advantages of MXene-based materials in Li-S batteries, including high-speed ionic conduction, structural diversity, shuttle effect inhibition, dendrite suppression, and catalytic activity from fundamental principles to practical applications. The classification of usage methods is also discussed. Finally, leveraging the research progress of MXene, the potential and prospects for its novel application in the Li-S field are proposed.