Accepted Papers

Accepted Oral Presentations

Resisting temptation: A delayed gratification experiment of two embodied reinforcement learning agents.

Niall Donnelly

Nature Based Functional Analysis --a `general intelligence' approach--

Marcus Abundis

From AGI to ASI: Mapping the Societal and Systemic Impact of Superintelligence

Soumya Banerjee

Ethical, Legal, and Policy Implications of Superintelligence: A Framework for Responsible Development

Faezeh Safari

Simulating Ourselves to Death

Constantine Andoniou

Accepted Lightning Talks

Morality as Systemic Fitness: A Complexity-Based Approach to Ethical Artificial Superintelligence

Oliver Bridge

Re-Envisioning Superintelligence using Generative AI and Science Fiction

Soumya Banerjee

Exploring the Mimicry of Biological Intelligence in Artificial General Superintelligence (AGSI) Systems: Multidomain Applications and Surpassing Human Capability

John Fehr

Cognitive scientific approaches to evaluating mechanical reasoning in LLMs: Output layer evidence of shallow world model use

Cole Robertson, Phillip Wolff

Making, Observing and Measuring Reflective Righteous Superintelligent Agents Safely in a Virtual Environment

Shagofta Shabashkhan

Embodied AI: a new paradigm for AI Safety?

Rebecca Raper

Synthetic Samsara: AI, Forgetting, and the Simulation of Cycles

Soumya Banerjee, Patrick Mario Simon Wagner

Accepted Workshops

Machines with Morals: interdisciplinary perspectives

Oliver Bridge, Rebecca Raper

Doctoral Symposium

Faezeh Safari, ASEEL ISMAEL ALI, Mahsa Mohammadi Eshkaftaki, Shagofta Shabashkhan, Soroush Karimi