Junxiang Zhang — accepted AI-conference papers

2026

Omni-fMRI: A Universal Atlas-Free fMRI Foundation Model

Mo Wang, Wenhao Ye, Junfeng Xia, Junxiang Zhang, Xuanye Pan, Minghao Xu +3

ICML 2026poster

Self-supervised fMRI foundation models have shown promising transfer performance, yet most rely on predefined region-level parcellations that discard fine-grained voxel information and introduce atlas-dependent biases. We propose Omni-fMRI, an atlas-free foundation model that operates directly on vo…

Cited by 7 Source ↗Scholar ↗

2026

SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement

Yuan Ge, Junxiang Zhang, Xiaoqian Liu, Bei Li, Xiangnan Ma, Chenglong Wang +7

AAAI 2026technical

Speech-to-Speech (S2S) Large Language Models (LLMs) are foundational to natural human-computer interaction, enabling end-to-end spoken dialogue systems. However, evaluating these models remains a fundamental challenge. We propose SageLM, an end-to-end, multi-aspect, and explainable speech LLM for co

Cited by 0 Source ↗PDF ↗Scholar ↗