1 citations · 1 across the 7 of their papers we have counts for
9 papers
Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It
Zehao Jin, Ruixuan Deng, Junran Wang
Pretrained transformers use little of their depth to follow references in context. Thirteen base models reliably follow only 1.4-3.6 lines, and extra pretrained loops add little. A…
Persona Dosing: Calibrated Activation Steering for Graded Trait Control
Zehao Jin, Junran Wang, Ruixuan Deng +4
An activation-steering coefficient sets intervention strength, but requesting a particular degree of persona expression requires a behavioral scale. We study persona dosing: contro…
AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flow
Junran Wang, Zehao Jin, Tianyu Luan +3
Text-to-image diffusion transformers (DiTs) are powerful generators, yet direct prompting provides limited control interface for style intensity and can fail to suppress unwanted c…
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…
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…
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…
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…
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…
Learning Principle of Least Action with Reinforcement Learning
Zehao Jin, Joshua Yao-Yu Lin, Siao-Fong Li
Nature provides a way to understand physics with reinforcement learning since nature favors the economical way for an object to propagate. In the case of classical mechanics, natur…