48 citations · 69 across the 18 of their papers we have counts for
19 papers
FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution
FangZhi Zhong, Xuerui Qiu, Yuqi Pan +4
Long-context reasoning in large language models incurs substantial computation and memory costs. Visual text compression (VTC) reduces input length by rendering text as images, but…
Spiking Neural Networks for fMRI-Based Visual Semantic Decoding
Jiahong Zhang, Jinning Zhao, Sijun Shen +3
Functional magnetic resonance imaging (fMRI)-based visual decoding aims to recover visual information from measured brain activity, commonly by mapping fMRI responses into latent v…
Beyond Transformers: Linear Attention Policy for Open-Vocabulary Object Goal Navigation
Jiahong Zhang, Yifan Lin, Yandong Zhang +6
Open-Vocabulary Object Goal Navigation (OVON) requires agents to operate under partial observability, making effective internal state updates critical for navigation performance. T…
SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference
Yuqi Pan, Jinghao Zhuang, Yupeng Feng +16
Scaling context length is reshaping large-model development, yet full-attention Transformers suffer from prohibitive computation and inference bottlenecks at long sequences. A key…
SpikeMLLM: Spike-based Multimodal Large Language Models via Modality-Specific Temporal Scales and Temporal Compression
Han Xu, Zhiyong Qin, Di Shang +6
Multimodal Large Language Models (MLLMs) have achieved remarkable progress but incur substantial computational overhead and energy consumption during inference, limiting deployment…
Spike-driven Large Language Model
Han Xu, Xuerui Qiu, Baiyu Chen +7
Current Large Language Models (LLMs) are primarily based on large-scale dense matrix multiplications. Inspired by the brain's information processing mechanism, we explore the funda…
Parallel Training in Spiking Neural Networks
Yanbin Huang, Man Yao, Yuqi Pan +5
The bio-inspired integrate-fire-reset mechanism of spiking neurons constitutes the foundation for efficient processing in Spiking Neural Networks (SNNs). Recent progress in large m…
BrainFuse: a unified infrastructure integrating realistic biological modeling and core AI methodology
Baiyu Chen, Yujie Wu, Siyuan Xu +9
Neuroscience and artificial intelligence represent distinct yet complementary pathways to general intelligence. However, amid the ongoing boom in AI research and applications, the…
Adaptive Hopfield Network: Rethinking Similarities in Associative Memory
Shurong Wang, Yuqi Pan, Zhuoyang Shen +3
Associative memory models are content-addressable memory systems fundamental to biological intelligence and are notable for their high interpretability. However, existing models ev…
SpikingBrain: Spiking Brain-inspired Large Models
Yuqi Pan, Yupeng Feng, Jinghao Zhuang +16
Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows lin…
Scaling Linear Attention with Sparse State Expansion
Yuqi Pan, Yongqi An, Zheng Li +6
The Transformer architecture, despite its widespread success, struggles with long-context scenarios due to quadratic computation and linear memory growth. While various linear atte…
Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation
Zhenxin Lei, Man Yao, Jiakui Hu +4
Spiking Neural Networks (SNNs) have a low-power advantage but perform poorly in image segmentation tasks. The reason is that directly converting neural networks with complex archit…
Efficient 3D Recognition with Event-driven Spike Sparse Convolution
Xuerui Qiu, Man Yao, Jieyuan Zhang +5
Spiking Neural Networks (SNNs) provide an energy-efficient way to extract 3D spatio-temporal features. Point clouds are sparse 3D spatial data, which suggests that SNNs should be w…
Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training
Man Yao, Xuerui Qiu, Tianxiang Hu +7
The ambition of brain-inspired Spiking Neural Networks (SNNs) is to become a low-power alternative to traditional Artificial Neural Networks (ANNs). This work addresses two major c…
MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
Yuhong Chou, Man Yao, Kexin Wang +7
Various linear complexity models, such as Linear Transformer (LinFormer), State Space Model (SSM), and Linear RNN (LinRNN), have been proposed to replace the conventional softmax a…
Scalable Autoregressive Image Generation with Mamba
Haopeng Li, Jinyue Yang, Kexin Wang +4
We introduce AiM, an autoregressive (AR) image generative model based on Mamba architecture. AiM employs Mamba, a novel state-space model characterized by its exceptional performan…
RSC-SNN: Exploring the Trade-off Between Adversarial Robustness and Accuracy in Spiking Neural Networks via Randomized Smoothing Coding
Keming Wu, Man Yao, Yuhong Chou +4
Spiking Neural Networks (SNNs) have received widespread attention due to their unique neuronal dynamics and low-power nature. Previous research empirically shows that SNNs with Poi…
SpikeVoice: High-Quality Text-to-Speech Via Efficient Spiking Neural Network
Kexin Wang, Jiahong Zhang, Yong Ren +4
Brain-inspired Spiking Neural Network (SNN) has demonstrated its effectiveness and efficiency in vision, natural language, and speech understanding tasks, indicating their capacity…
Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips
Man Yao, Jiakui Hu, Tianxiang Hu +5
Neuromorphic computing, which exploits Spiking Neural Networks (SNNs) on neuromorphic chips, is a promising energy-efficient alternative to traditional AI. CNN-based SNNs are the c…