arXiv AI October 9, 2026 By Xintao Zong, Wenxuan Liu, Jianhao Ding, Zhaofei Yu, Tiejun Huang

MSGAT: Multi-Head Spiking Graph Attention with Similarity-Space Fusion for Image-Text Retrieval

MSGAT introduces a Multi-head Spiking Graph Attention Network that models structural relationships for image-text retrieval using spike-driven graph reasoning. It employs dynamic attention heads to capture complementary relational patterns and a two-branch multi-granularity fusion framework. The proposed Sim-Fuse strategy aligns coarse- and fine-grained matching relations in similarity space, avoiding interference between sparse spike representations and continuous global features, achieving state‑of‑the‑art performance on Flickr30K and MSCOCO with significant energy savings.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language

Sep 7

Large Language Models with At Most One Spike per Neuron

The paper presents a spiking neural network (SNN) approach that uses time-to-first-spike (TTFS) coding to limit each neuron to at most one spike per time window, enabling energy-efficient large language models (LLMs). A reference-based strategy is introduced to encode the four core LLM components—embedding layers, layer normalization, attention-related operations, and dropout—allowing the construction of a fully TTFS-based SNN architecture trained end-to-end. Experiments on BERT and GPT-2 show performance comparable to artificial neural network (ANN) counterparts on natural language understanding and common-sense reasoning, while achieving a 1.5‑billion‑parameter spiking LLM and providing an estimate of spike-related energy consumption.

By Zhuoya Zhao, Parsa Omidi, Aref Jafari, Richard Naud

llms rag

arXiv Computer Vision

Aug 21

Spiking Local Interaction and Adaptive Complementary Fusion for Spiking Transformer

arXiv:2608. 19238v1 Announce Type: cross Abstract: Spiking Transformers model token interactions primarily through spiking self-attention (SSA).

By Dongcheng Zhao, Sicheng Shen, Zhenyu Yang, Zhiyuan Li, Jinyan Yu, Yongjian Wang, Tiechui Yao, Wenli Zhang, Tielin Zhang

llms computer-vision benchmarks

arXiv AI

Jun 11

SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks

arXiv:2606. 12287v1 Announce Type: cross Abstract: The Transformer architecture is widely regarded as the most powerful tool for natural language processing, but due to a high number of complex operations, it inherently faces the issue of high energy consumption.

By Claas Beger, Florian Walter, Alois Knoll

llms rag computer-vision nlp

arXiv Computation and Language

Oct 1

Spike-driven Vision-Language-Action Model

arXiv:2609.39514v1 Announce Type: new Abstract: Vision-language-action (VLA) models bridge multimodal understanding and robotic control, advancing the dominant paradigm for embodied intelligence. How...

By Shuai Wang, Malu Zhang, Mingquan Liu, Weihui Dai, Dehao Zhang, Jieyuan Zhang, Yimeng Shan, Zijian Zhou, Yang Yang

llms rag robotics multimodal

arXiv Machine Learning

Jul 20

Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework

arXiv:2607. 15687v1 Announce Type: new Abstract: Multimodal-attributed graphs (MAGs), whose nodes carry modalities such as images and text alongside topological structure, now pervade applications including social platforms, e-commerce, and biomedical networks, offering richer semantic signals than single-modality graphs.

By Xunkai Li, Guohao Fu, Yuming Ai, Zhengyu Wu, Hongchao Qin, Rong-Hua Li, Guoren Wang

fine-tuning multimodal safety

arXiv AI

Aug 7

Ge$^\text{2}$mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformer

arXiv:2604. 08894v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) offer superior energy efficiency over Artificial Neural Networks (ANNs).

By Zecheng Hao, Shenghao Xie, Kang Chen, Wenxuan Liu, Zhaofei Yu, Tiejun Huang

llms benchmarks