20 citations · 157 across the 47 of their papers we have counts for
51 papers
EEG Benchmarking Needs a Task Specification Layer: NeuroDoc for Rulebook-Guided, Executable Benchmark Construction
Chengxuan Qin, Zhige Chen, Shu Peng +9
Electroencephalography (EEG) foundation models increasingly rely on multi-dataset training and evaluation, yet public EEG datasets still lack a shared task specification layer that…
-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
Xianwei Chen, Shimin Zhang, Jibin Wu
Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary for system efficiency, but structurally d…
ReLaX: Reasoning with Latent Exploration for Large Reasoning Models
Shimin Zhang, Xianwei Chen, Yufan Shen +2
Reinforcement Learning with Verifiable Rewards (RLVR) has recently demonstrated remarkable potential in enhancing the reasoning capability of Large Reasoning Models (LRMs). However…
HEAR: An EEG Foundation Model with Heterogeneous Electrode Adaptive Representation
Zhige Chen, Chengxuan Qin, Wenlong You +5
Electroencephalography (EEG) is an essential technique for neuroscience research and brain-computer interface (BCI) applications. Recently, large-scale EEG foundation models have b…
Efficient Training of Spiking Neural Networks by Spike-aware Data Pruning
Chenxiang Ma, Xinyi Chen, Yujie Wu +2
Spiking neural networks (SNNs), recognized as an energy-efficient alternative to traditional artificial neural networks (ANNs), have advanced rapidly through the scaling of models…
ISTASTrack: Bridging ANN and SNN via ISTA Adapter for RGB-Event Tracking
Siying Liu, Zikai Wang, Hanle Zheng +6
RGB-Event tracking has become a promising trend in visual object tracking to leverage the complementary strengths of both RGB images and dynamic spike events for improved performan…
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…
ZeCO: Zero Communication Overhead Sequence Parallelism for Linear Attention
Yuhong Chou, Zehao Liu, Ruijie Zhu +6
Linear attention mechanisms deliver significant advantages for Large Language Models (LLMs) by providing linear computational complexity, enabling efficient processing of ultra-lon…
IML-Spikeformer: Input-aware Multi-Level Spiking Transformer for Speech Processing
Zeyang Song, Shimin Zhang, Yuhong Chou +2
Spiking Neural Networks (SNNs), inspired by biological neural mechanisms, represent a promising neuromorphic computing paradigm that offers energy-efficient alternatives to traditi…
A Systematic Analysis of Hybrid Linear Attention
Dustin Wang, Rui-Jie Zhu, Steven Abreu +9
Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size hidden states. However, linear…
MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion
Wei Hua, Chenlin Zhou, Jibin Wu +2
The combination of Spiking Neural Networks (SNNs) with Vision Transformer architectures has garnered significant attention due to their potential for energy-efficient and high-perf…
Spatio-Temporal Decoupled Learning for Spiking Neural Networks
Chenxiang Ma, Xinyi Chen, Kay Chen Tan +1
Spiking neural networks (SNNs) have gained significant attention for their potential to enable energy-efficient artificial intelligence. However, effective and efficient training o…
LLM Cannot Discover Causality, and Should Be Restricted to Non-Decisional Support in Causal Discovery
Xingyu Wu, Kui Yu, Jibin Wu +1
This paper critically re-evaluates LLMs' role in causal discovery and argues against their direct involvement in determining causal relationships. We demonstrate that LLMs' autoreg…
Neuromorphic Sequential Arena: A Benchmark for Neuromorphic Temporal Processing
Xinyi Chen, Chenxiang Ma, Yujie Wu +2
Temporal processing is vital for extracting meaningful information from time-varying signals. Recent advancements in Spiking Neural Networks (SNNs) have shown immense promise in ef…
EventDiff: A Unified and Efficient Diffusion Model Framework for Event-based Video Frame Interpolation
Hanle Zheng, Xujie Han, Zegang Peng +7
Video Frame Interpolation (VFI) is a fundamental yet challenging task in computer vision, particularly under conditions involving large motion, occlusion, and lighting variation. R…
Diversity-Aware Policy Optimization for Large Language Model Reasoning
Jian Yao, Ran Cheng, Xingyu Wu +2
The reasoning capabilities of large language models (LLMs) have advanced rapidly, particularly following the release of DeepSeek R1, which has inspired a surge of research into dat…
Spiking Neural Networks for Temporal Processing: Status Quo and Future Prospects
Chenxiang Ma, Xinyi Chen, Yanchen Li +7
Temporal processing is fundamental for both biological and artificial intelligence systems, as it enables the comprehension of dynamic environments and facilitates timely responses…
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…
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…
HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models
Yu Zhou, Xingyu Wu, Jibin Wu +2
Model merging is a technique that combines multiple large pretrained models into a single model with enhanced performance and broader task adaptability. It has gained popularity in…
Distance-Forward Learning: Enhancing the Forward-Forward Algorithm Towards High-Performance On-Chip Learning
Yujie Wu, Siyuan Xu, Jibin Wu +4
The Forward-Forward (FF) algorithm was recently proposed as a local learning method to address the limitations of backpropagation (BP), offering biological plausibility along with…
PMSN: A Parallel Multi-compartment Spiking Neuron for Multi-scale Temporal Processing
Xinyi Chen, Jibin Wu, Chenxiang Ma +4
Spiking Neural Networks (SNNs) hold great potential to realize brain-inspired, energy-efficient computational systems. However, current SNNs still fall short in terms of multiscale…
Autonomous Multi-Objective Optimization Using Large Language Model
Yuxiao Huang, Shenghao Wu, Wenjie Zhang +3
Multi-objective optimization problems (MOPs) are ubiquitous in real-world applications, presenting a complex challenge of balancing multiple conflicting objectives. Traditional evo…
Global-Local Convolution with Spiking Neural Networks for Energy-efficient Keyword Spotting
Shuai Wang, Dehao Zhang, Kexin Shi +4
Thanks to Deep Neural Networks (DNNs), the accuracy of Keyword Spotting (KWS) has made substantial progress. However, as KWS systems are usually implemented on edge devices, energy…