Archives AI News

SortScrews: A Dataset and Baseline for Real-time Screw Classification

arXiv:2603.13027v1 Announce Type: cross Abstract: Automatic identification of screw types is important for industrial automation, robotics, and inventory management. However, publicly available datasets for screw classification are scarce, particularly for controlled single-object scenarios commonly encountered in automated sorting systems. In…

Thermodynamics of Reinforcement Learning Curricula

arXiv:2603.12324v1 Announce Type: new Abstract: Connections between statistical mechanics and machine learning have repeatedly proven fruitful, providing insight into optimization, generalization, and representation learning. In this work, we follow this tradition by leveraging results from non-equilibrium thermodynamics to formalize curriculum…

Maximum Entropy Exploration Without the Rollouts

arXiv:2603.12325v1 Announce Type: new Abstract: Efficient exploration remains a central challenge in reinforcement learning, serving as a useful pretraining objective for data collection, particularly when an external reward function is unavailable. A principled formulation of the exploration problem is to…

Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models

arXiv:2603.05773v2 Announce Type: replace-cross Abstract: Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the persistence of jailbreak attacks suggests a fundamental mechanistic decoupling. We propose the textbf{underline{D}}isentangled textbf{underline{S}}afety textbf{underline{H}}ypothesis textbf{(DSH)}, positing that…

Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models

arXiv:2603.05773v2 Announce Type: replace-cross Abstract: Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the persistence of jailbreak attacks suggests a fundamental mechanistic decoupling. We propose the textbf{underline{D}}isentangled textbf{underline{S}}afety textbf{underline{H}}ypothesis textbf{(DSH)}, positing that…