collaborators

8 papers

cs.LG2026

Riemannian Attention Mechanisms for Transformers: A Theoretical Framework and Architecture Design

Sen Song

All Transformer-based large language models compute attention via the Euclidean inner product, an architectural choice that Dong et al. (2021) proved causes representational rank t…

eess.SP2026

EEG-JEPA: Structured Latent Prediction for EEG Foundation Models

Jinhao Li, Zhiyuan Ma, Xueqiao Han +8

Electroencephalography (EEG) foundation models aim to learn reusable representations from large-scale unlabeled recordings. A common pretraining strategy is masked waveform reconst…

cs.LG2026

Rethinking EEG-Based Disease Diagnosis: Decoupling Instance Representation Learning from Subject-Level Supervision

Zhiyuan Ma, Zeyuan Li, Zhiyi Lu +7

The paper introduces BridgeMIL, a two-stage method that first learns EEG instance representations without using inherited labels and then applies subject-level supervision via a mu…

cs.CL2026

Why Attend to Everything? Focus is the Key

Hengshuai Yao, Xing Chen, Ahmed Murtadha +8

Standard attention scales quadratically with sequence length. Efficient attention methods reduce this O(n^2) cost, but when retrofitted into pretrained models, they often degrade p…

q-bio.NC2026

Training-Driven Representational Geometry Modularization Predicts Brain Alignment in Language Models

Yixuan Liu, Zhiyuan Ma, Likai Tang +5

How large language models (LLMs) align with the neural representation and computation of human language is a central question in cognitive science. Using representational geometry…

cs.LG2026

Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks

Jinhao Li, Yuhao Sun, Zhiyuan Ma +5

Recurrent spiking neural networks (RSNNs) are a promising substrate for energy-efficient control policies, but training them for high-dimensional, long-horizon reinforcement learni…