DelRec employs surrogate gradient with differentiable interpolation to train recurrent synaptic delays, achieving state-of-the-art accuracy on temporal datasets.

Alexandre Queant, Ulysse Rançon, Benoit R Cottereau et al.

Nearly lossless ANN-to-SNN conversion at the first timestep via Polarity Multi-Spike Mapping, achieving high accuracy.

Hangming Zhang, Zheng Li, Chenxiang Ma et al.

REMS framework models COP as resource-task assignment, enabling versatile metaheuristic algorithms; outperforms GUROBI, SCIP, OR-TOOLS on large/complex instances.

Aijuan Song, Guohua Wu

Proposes ASRC-SNN with adaptive skip connections, achieving state-of-the-art long-term temporal modeling, outperforming traditional RSNN by 2-3% accuracy.

Shang Xu, Jiayu Zhang, Ziming Wang et al.

Proposes Modular GP-GOMEA with multi-tree evolution and subexpression reuse, boosting symbolic regression accuracy and interpretability.

Joe Harrison, Peter A. N. Bosman, Tanja Alderliesten

Proposes a lifelong evolutionary swarm control framework combining NEAT and regularization, achieving over 85% task retention across dynamic environments.

Lorenzo Leuzzi, Simon Jones, Sabine Hauert et al.

SpiLiFormer enhances attention allocation in SNNs using lateral inhibition, outperforming SOTA models by 0.46% on ImageNet-1K.

Zeqi Zheng, Yanchen Huang, Yingchao Yu et al.

Proposes a PFC-HPC interaction-based reinforcement learning model for goal-directed memory control and generalization.

Yicong Zheng, Nora Wolf, Charan Ranganath et al.

RFG replaces backpropagation with randomized weight perturbations, reaching 0.0347 Poisson error and an estimated 66% lower training cost.

Ruyin Wan, Qian Zhang, George Em Karniadakis

LCoDeepNEAT combines Lamarckian genetic algorithms and gradient transfer to optimize CNN architectures and last-layer weights, boosting accuracy and efficiency.

Zaniar Sharifi, Khabat Soltanian, Ali Amiri

LLaMEA-HPO integrates HPO to reduce LLM query costs, achieving comparable or superior algorithm performance.

Niki van Stein, Diederick Vermetten, Thomas Bäck

Proposed STAtten enhances Spike Transformers by integrating block-wise spatial-temporal attention, achieving significant accuracy gains on CIFAR and ImageNet datasets.

Donghyun Lee, Yuhang Li, Youngeun Kim et al.

Sorbet combines PTsoftmax and BSPN to enable energy-efficient transformer-based SNN language models suitable for neuromorphic hardware, achieving 27× energy savings.

Kaiwen Tang, Zhanglu Yan, Weng-Fai Wong

Proposes OPZO, a single-pass online training method with noise and momentum feedback, achieving performance comparable to spatial BP with lower costs.

Mingqing Xiao, Qingyan Meng, Zongpeng Zhang et al.

Introduces a novel drift theorem establishing exponential tail bounds for runtime and regret, enhancing high-probability performance guarantees.

Per Kristian Lehre, Shishen Lin

QKFormer introduces a linear-complexity Q-K attention for hierarchical SNNs, achieving 85.65% top-1 accuracy on ImageNet with 64.96M parameters.

Chenlin Zhou, Han Zhang, Zhaokun Zhou et al.

Meta-SpikeFormer achieves 80% accuracy on ImageNet-1K, surpassing SOTA by 3.7%.

Man Yao, Jiakui Hu, Tianxiang Hu et al.

Proposes semantic subtree inheritance and greedy child selection to improve GP-GOMEA's efficiency with high-arity operators.

Thalea Schlender, Mafalda Malafaia, Tanja Alderliesten et al.

Proposes CLIF neuron to mitigate gradient vanishing, boosting SNN accuracy by 2% on CIFAR-10.

Yulong Huang, Xiaopeng Lin, Hongwei Ren et al.

ReEvo integrates LLMs with reflective evolution to enhance heuristic search for NP-hard problems, achieving state-of-the-art results.

Haoran Ye, Jiarui Wang, Zhiguang Cao et al.