collaborators

5 papers

cs.LG2026

Whole-Brain Connectomic Graph Model Enables Whole-Body Locomotion Control in Fruit Fly

Zehao Jin, Yaoye Zhu, Chen Zhang +1

Animals perform coordinated whole-body movements under the control of neural systems shaped by brain-wide connectivity. The mapping of the whole-brain neural connections, or the co…

cs.LG2026

Decompose Sparsely Where You Should, Absorb Densely Where You Should No

Ruixuan Deng, Zehao Jin, Zekun Wang +1

Sparse autoencoders (SAEs) are typically trained to reconstruct the \textbf{entire} residual stream through a sparse dictionary, implicitly assuming that all activation content is…

cs.CR2026

How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study

Junran Wang, Xinjie Shen, Zehao Jin +1

As Vision-Language Models (VLMs) are increasingly deployed as autonomous cognitive cores for embodied assistants, evaluating their privacy awareness in physical environments become…

cs.CL2026

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention

Zehao Jin, Ruixuan Deng, Junran Wang +2

Activation steering has emerged as a promising alternative for controlling language-model behavior at inference time by modifying intermediate representations while keeping model p…

cs.CL2026

Stochastic Attention: Connectome-Inspired Randomized Routing for Expressive Linear-Time Attention

Zehao Jin, Yanan Sui

The whole-brain connectome of a fruit fly comprises over 130K neurons connected with a probability of merely 0.02%, yet achieves an average shortest path of only 4.4 hops. Despite…