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.

Emulates insect path integration on BrainScaleS-2 with spike-based short-term memory, achieving high-precision autonomous navigation.

Korbinian Schreiber, Timo Wunderlich, Philipp Spilger et al.

Darwin3 employs a novel ISA supporting large-scale SNNs with on-chip learning, achieving 2.35 million neurons and 28.3x code density improvement.

De Ma, Xiaofei Jin, Shichun Sun et al.

Proposes NIR as a unified instruction set for neuromorphic systems, enabling cross-platform model reproduction across 7 simulators and 4 hardware platforms.

Jens E. Pedersen, Steven Abreu, Matthias Jobst et al.

Metaheuristic-optimized neural network predicts mobile energy use, handles missing data, improves accuracy by 15%.

Seyed Jalaleddin Mousavirad, Luís A. Alexandre

Proposed co-learning of synaptic delays, weights, and neuronal adaptation in SNN, achieving state-of-the-art speech recognition accuracy with fewer parameters.

Lucas Deckers, Laurens Van Damme, Ing Jyh Tsang et al.

This study benchmarks large-scale SNN inference on SATA and SpikeSim, revealing actual energy efficiency is far below estimates due to hardware bottlenecks.

Abhiroop Bhattacharjee, Ruokai Yin, Abhishek Moitra et al.

Proposes RL-assisted evolutionary algorithms (RL-EA), leveraging deep RL (DQN, PPO) to enhance optimization, outperforming traditional EA on benchmarks with 15% average improvement.

Yanjie Song, Yutong Wu, Yangyang Guo et al.

Spike-driven Transformer combines SNN and Transformer, achieving 77.1% accuracy on ImageNet-1K.

Man Yao, Jiakui Hu, Zhaokun Zhou et al.

Introduces delay learning in deep SNNs via dilated convolutions with learnable spacings, achieving state-of-the-art accuracy on temporal benchmarks.

Ilyass Hammouamri, Ismail Khalfaoui-Hassani, Timothée Masquelier

Introduces a deep TTFS-based SNN with exact ReLU equivalence, achieving state-of-the-art accuracy with less than 0.3 spikes/neuron, enhancing energy efficiency.

Ana Stanojevic, Stanisław Woźniak, Guillaume Bellec et al.

N4SR method uses neural networks for symbolic regression, generating physically plausible models from small datasets.

Jiří Kubalík, Erik Derner, Robert Babuška

L5PC-inspired MCC architecture reduces energy consumption by 62%, excels in multimodal audio-visual noise suppression, leveraging context-sensitive two-point neurons.

Ahsan Adeel, Adewale Adetomi, Khubaib Ahmed et al.

Proposes a microservice-based neuromorphic system integration framework to address heterogeneity and communication challenges.

Mattias Nilsson, Olov Schelén, Anders Lindgren et al.

Spikformer combines Spiking Neural Network with Transformer, achieving 74.81% accuracy on ImageNet with 4 time steps.

Zhaokun Zhou, Yuesheng Zhu, Chao He et al.

Leveraging large language models (e.g., GPT-3) to guide mutation in genetic programming, generating diverse Python robots with over 300,000 solutions, enabling zero-shot generalization.

Joel Lehman, Jonathan Gordon, Shawn Jain et al.

Using NSGA-II to optimize CNN+LSTM hyperparameters with five objectives, analyzing their impact on vehicle trajectory prediction.

Fergal Stapleton, Edgar Galván, Ganesh Sistu et al.

Proposes a trajectory-based online algorithm selection framework combining landscape and internal state features, with warm-starting, outperforming static strategies on BBOB and YABBOB datasets.

Ana Kostovska, Anja Jankovic, Diederick Vermetten et al.

MS-ResNet achieves 482 layers on CIFAR-10 and 76.02% accuracy on ImageNet.

Yifan Hu, Lei Deng, Yujie Wu et al.

This study shows how Transformers with recurrent position encodings mimic spatial representations in the hippocampal formation.

James C. R. Whittington, Joseph Warren, Timothy E. J. Behrens