Invited Speakers

Ryota Kanai

Founder & CEO: ARAYA, Co-Founder: ALIGN

Workshop 1: “Global Workspace: A Key to AI Consciousness, Brain-to-Brain Interfaces, and the Future of Humanity.”

Adam Gleave

CEO & Co-Founder: FAR.AI, Board Member: Safe AI Forum, London Initiative for Safe AI, and METR

Workshop 2: “Securing Advanced AI: Capabilities, Risks and Solutions.”

Posters

Ong, Jia Jun et al. — "Identifying Cooperative Personalities in Multi-agent Contexts through..."

Ong, Jia Jun et al. — "Identifying Cooperative Personalities in Multi-agent Contexts through..."
Wijk et al. — "RE-Bench: Evaluating frontier AI R&D capabilities of language model agents..."

Wijk et al. — "RE-Bench: Evaluating frontier AI R&D capabilities of language model agents..."
Papyshev et al. — "Optimal AI Liability for Unavoidable Risks: A Game-Theoretic Perspective"

Papyshev et al. — "Optimal AI Liability for Unavoidable Risks: A Game-Theoretic Perspective"
Freedman et al. — "Active Teacher Selection for Reinforcement Learning from Human Feedback"

Freedman et al. — "Active Teacher Selection for Reinforcement Learning from Human Feedback"
Yamashina — "Why Accelerating Human–Machine Interfaces (HMI) Matters"

Yamashina — "Why Accelerating Human–Machine Interfaces (HMI) Matters"
Menke and Tan — "How Effective Is Constitutional AI in Small LLMs?"

Menke and Tan — "How Effective Is Constitutional AI in Small LLMs?"
Bereska et al. — "Towards Measuring Superposition with Sparse Autoencoders"

Bereska et al. — "Towards Measuring Superposition with Sparse Autoencoders"
Nešić — "Right to AI: Ensuring Equitable Access to AI Resources"

Nešić — "Right to AI: Ensuring Equitable Access to AI Resources"
Farr and Pang — "Management of Substrate-Specific AI Capabilities (MoSSAIC)"

Farr and Pang — "Management of Substrate-Specific AI Capabilities (MoSSAIC)"
Hayashi — "From Collective Predictive Coding to Human–AI Synergy: A Path for Symbiotic Coordination"

Hayashi — "From Collective Predictive Coding to Human–AI Synergy: A Path for Symbiotic Coordination"
Noel — "Alternative approach for Sparse Embeddings for AI Mechanical Interpretability"

Noel — "Alternative approach for Sparse Embeddings for AI Mechanical Interpretability"
Mizumoto et al. — "Virtue Ethics as an Alternative to Current AI Safety Approaches"

Mizumoto et al. — "Virtue Ethics as an Alternative to Current AI Safety Approaches"
Kierans et al. — "Catastrophic Liability: Managing Systemic Risks in Frontier AI Development"

Kierans et al. — "Catastrophic Liability: Managing Systemic Risks in Frontier AI Development"
Aoyagi — "Singular Learning Theory and Deep Neural networks"

Aoyagi — "Singular Learning Theory and Deep Neural networks"
Petersen — "Desire Homuncularism"

Petersen — "Desire Homuncularism"
Thornley, Roman, Ziakas et al. — "Towards shutdownable agents via stochastic choice"

Thornley, Roman, Ziakas et al. — "Towards shutdownable agents via stochastic choice"
Cruz — "Understanding the learned look-ahead behavior of chess neural networks"

Cruz — "Understanding the learned look-ahead behavior of chess neural networks"