AI Theory

RL optimizes quantum error-correcting codes, slashing physical qubit overhead for fault-tolerant quantum computing.

Aligned LLMs’ safety often anchors in the template region, creating vulnerabilities. Detaching safety mechanisms shows promise in mitigation.

LLMs personalize based on user names, but this study reveals that cultural presumptions in LLM responses risk reinforcing stereotypes.

ASTRAL, a novel automated safety testing tool, reveals DeepSeek-R1’s significantly higher unsafe response rate compared to OpenAI’s o3-mini, highlighting critical safety concerns in advanced LLMs.

Researchers used ASTRAL to systematically test OpenAI’s 03-mini LLM’s safety, revealing key vulnerabilities and highlighting the need for continuous, robust safety mechanisms in large language models.

Machine learning overlooks robustness to an unknowable future; this paper contrasts reinforcement learning with biological evolution, revealing that ML’s formalisms limit engagement with unknown unkno…

Machine learning models can enable secure computations previously impossible with cryptography, achieving privacy and efficiency in Trusted Capable Model Environments (TCMEs).

Game-theoretic LLMs: Agent Workflow for Negotiation Games enhances large language model (LLM) rationality in strategic decision-making through novel game-theoretic workflows.

A new lossy compression framework handles reconstruction distribution divergence by integrating a bottleneck, extending minimum entropy coupling and offering guaranteed performance.