Skip To Main Content
Michael S. A on Muck Rack

Michael S. A

As seen in: arXiv, MDPI
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile
Back to Michael S. A’s profile

Articles by Michael S. A

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs

|
By Mike, Michael S. A, de Lucena
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (99) Issue with article?

[2602.06941] Endogenous Resistance to Activation Steering in Language Models

|
By Mike, de Lucena, Michael S. A
| arXiv
[Submitted on 6 Feb 2026] Title:Endogenous Resistance to Activation Steering in Language Models View a PDF of the paper titled Endogenous Resistance to Activation Steering in Language Models, by Alex McKenzie and 8 other authors View PDF HTML (experimental) Abstract:Large language models can resist task-misaligned activation steering during inference, sometimes recovering mid-generation to produce improved responses even when steering remains active.
Open in Who Shared Issue with article?

[2411.00983] Testing Components of the Attention Schema Theory in Artificial Neural Networks

|
By Michael S. A
| arXiv
[Submitted on 1 Nov 2024 ( v1 ), last revised 20 Aug 2025 (this version, v3)] Title:Testing Components of the Attention Schema Theory in Artificial Neural Networks View a PDF of the paper titled Testing Components of the Attention Schema Theory in Artificial Neural Networks, by Kathryn T. Farrell and 2 other authors View PDF HTML (experimental) Abstract:Growing evidence suggests that the brain uses an attention schema, or a simplified model of attention, to help control what it attends to.
Open in Who Shared Issue with article?

[2410.22309] GPT-4o reads the mind in the eyes

|
By James A, Michael S. A
| arXiv
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Open in Who Shared View Duplicates (447) Issue with article?

[2407.10188] Unexpected Benefits of Self-Modeling in Neural Systems

|
By de Lucena, Michael S. A, Diogo Schwerz
| arXiv
[Submitted on 14 Jul 2024] Title:Unexpected Benefits of Self-Modeling in Neural Systems View a PDF of the paper titled Unexpected Benefits of Self-Modeling in Neural Systems, by Vickram N. Premakumar and 6 other authors View PDF HTML (experimental) Abstract:Self-models have been a topic of great interest for decades in studies of human cognition and more recently in machine learning. Yet what benefits do self-models confer?
Open in Who Shared Issue with article?

Chatbots as social companions: How people perceive consciousness, human likeness, and social health benefits in machines

|
By Michael S. A
| arXiv
[Submitted on 17 Nov 2023 ( v1 ), last revised 10 Apr 2025 (this version, v5)] Title:Chatbots as social companions: How people perceive consciousness, human likeness, and social health benefits in machines View a PDF of the paper titled Chatbots as social companions: How people perceive consciousness, human likeness, and social health benefits in machines, by Rose E.
Open in Who Shared Issue with article?

Electrostatic Charging of Fine Powders and Assessment of Charge Polarity Using an Inductive Charge Sensor

|
By Vivek Garg, Tong Deng, Michael S. A
| MDPI
This is an early access version, the complete PDF, HTML, and XML versions will be available soon. Open AccessArticle by Tong Deng *, Vivek Garg and Michael S. A. Bradley The Wolfson Centre for Bulk Solids Handling Technology, Faculty of Engineering and Science, University of Greenwich, Central Avenue, Chatham ME4 4TB, UK * Author to whom correspondence should be addressed.
Open in Who Shared Issue with article?
Show More