activity
20212024
most citedHow Multimodal Integration Boost the Performance of LLM for Optimization: Case Study on Capacitated Vehicle Routing Problems

6 citations · 21 across the 11 of their papers we have counts for

collaborators

11 papers

eess.AS2024

Towards Ultra-Low-Power Neuromorphic Speech Enhancement with Spiking-FullSubNet

Xiang Hao, Chenxiang Ma, Qu Yang +2

Speech enhancement is critical for improving speech intelligibility and quality in various audio devices. In recent years, deep learning-based methods have significantly improved s…

cs.AI20246 cited

How Multimodal Integration Boost the Performance of LLM for Optimization: Case Study on Capacitated Vehicle Routing Problems

Yuxiao Huang, Wenjie Zhang, Liang Feng +2

Recently, large language models (LLMs) have notably positioned them as capable tools for addressing complex optimization challenges. Despite this recognition, a predominant limitat…

cs.NE20241 cited

Scaling Supervised Local Learning with Augmented Auxiliary Networks

Chenxiang Ma, Jibin Wu, Chenyang Si +1

Deep neural networks are typically trained using global error signals that backpropagate (BP) end-to-end, which is not only biologically implausible but also suffers from the updat…

cs.NE2024

Efficient Online Learning for Networks of Two-Compartment Spiking Neurons

Yujia Yin, Xinyi Chen, Chenxiang Ma +2

The brain-inspired Spiking Neural Networks (SNNs) have garnered considerable research interest due to their superior performance and energy efficiency in processing temporal signal…

cs.NE20243 cited

Towards Multi-Objective High-Dimensional Feature Selection via Evolutionary Multitasking

Yinglan Feng, Liang Feng, Songbai Liu +2

Evolutionary Multitasking (EMT) paradigm, an emerging research topic in evolutionary computation, has been successfully applied in solving high-dimensional feature selection (FS) p…

cs.NE2023

LC-TTFS: Towards Lossless Network Conversion for Spiking Neural Networks with TTFS Coding

Qu Yang, Malu Zhang, Jibin Wu +2

The biological neurons use precise spike times, in addition to the spike firing rate, to communicate with each other. The time-to-first-spike (TTFS) coding is inspired by such biol…