6 papers · 1 filter
The Sharp Directions Are Against You: Curvature Analysis of Activation Steering
Seyedarmin Azizi, Arya Fayyazi, Parsa Razmara +3
Activation steering adds a vector to a language model's internal representations at inference time. It is a lightweight alternative to fine-tuning for behavioral control. The stand…
Best Practices in EEG Analysis: Preprocessing, Modeling, and Machine Learning
Parsa Razmara, Woojae Jeong, Aditya Kommineni +3
Electroencephalography (EEG) analysis requires careful choices in preprocessing, statistical modeling, and machine learning because EEG signals are highly susceptible to artifacts,…
CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits
Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad +2
Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment. Existing steering methods, such as Contrastive Activation Addition (CAA), ty…
An Approach to Simultaneous Acquisition of Real-Time MRI Video, EEG, and Surface EMG for Articulatory, Brain, and Muscle Activity During Speech Production
Jihwan Lee, Parsa Razmara, Kevin Huang +16
Speech production is a complex process spanning neural planning, motor control, muscle activation, and articulatory kinematics. While the acoustic speech signal is the most accessi…
NeuroMambaLLM: Dynamic Graph Learning of fMRI Functional Connectivity in Autistic Brains Using Mamba and Language Model Reasoning
Yasaman Torabi, Parsa Razmara, Hamed Ajorlou +1
Large Language Models (LLMs) have demonstrated strong semantic reasoning across multimodal domains. However, their integration with graph-based models of brain connectivity remains…
Feasibility of simultaneous EEG-fMRI at 0.55 T: Recording, Denoising, and Functional Mapping
Parsa Razmara, Takfarinas Medani, Majid Abbasi Sisara +6
Simultaneous recording of electroencephalography (EEG) and functional MRI (fMRI) can provide a more complete view of brain function by merging high temporal and spatial resolutions…