arXiv:2512.18309v1 Announce Type: new Abstract: We introduce Embedded Safety-Aligned Intelligence (ESAI), a theoretical framework for multi-agent reinforcement learning that embeds alignment constraints directly into agents internal representations using differentiable internal alignment embeddings. Unlike external reward shaping or post-hoc safety constraints,…
arXiv:2512.13634v2 Announce Type: replace-cross Abstract: We consider statistical tasks in high dimensions whose loss depends on the data only through its projection into a fixed-dimensional subspace spanned by the parameter vectors and certain ground truth vectors. This includes classifying mixture…
arXiv:2512.18317v1 Announce Type: new Abstract: This paper presents a trustworthy reinforcement learning approach for the control of industrial compressed air systems. We develop a framework that enables safe and energy-efficient operation under realistic boundary conditions and introduce a multi-level explainability…
arXiv:2512.19004v1 Announce Type: cross Abstract: Diffusion Large Language Models (DLLMs) enable fully parallel token decoding but often remain impractical at inference time due to the many denoising iterations required to refine an information-free, fully masked initialization into coherent text. Most…
A new method could enable users to design portable medical devices, like a splint, that can be rapidly converted from flat panels to a 3D object without any tools.
arXiv:2512.19190v1 Announce Type: cross Abstract: Walking has always been a primary mode of transportation and is recognized as an essential activity for maintaining good health. Despite the need for safe walking conditions in urban environments, sidewalks are frequently obstructed by…
arXiv:2301.11321v3 Announce Type: replace Abstract: Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, but counteracting off-policy bias without exacerbating variance is challenging. Classically, off-policy bias is corrected in a per-decision manner: past temporal-difference errors are re-weighted by…
arXiv:2507.22782v3 Announce Type: replace-cross Abstract: This paper introduces Team-Attention-Actor-Critic (TAAC), a reinforcement learning algorithm designed to enhance multi-agent collaboration in cooperative environments. TAAC employs a Centralized Training/Centralized Execution scheme incorporating multi-headed attention mechanisms in both the actor and critic. This…
arXiv:2512.18901v1 Announce Type: cross Abstract: We present Gabliteration, a novel neural weight modification technique that advances beyond traditional abliteration methods by implementing adaptive multi-directional projections with regularized layer selection. Our approach addresses the fundamental limitation of existing methods that compromise…
arXiv:2511.07329v2 Announce Type: replace Abstract: It introduces FractalNet, a fractal-inspired computational architectures for advanced large language model analysis that mainly challenges model diversity on a large scale in an efficient manner. The new set-up involves a template-driven generator, runner, and…
