The engine Every edition RSS Refreshed every 30 min 2m ago
PRISM The internet, refracted.

Home Research

OR Else: A Differentiable Trust Region for Policy Optimization

Signal strength 9/100

PPO and the GRPO baseline studied here use clipped surrogate objectives whose favorable-direction saturation introduces an abrupt change in the scalar objective's derivative. We ask whether Output Reset (OR), a smooth one-sided saturation rule, offers a…

PRISM indexes and ranks — it never republishes. The full piece lives with its author on arxiv.org.

Read on arxiv.org

Same wavelength

Stories the engine considers adjacent to this one.

Intelligence arXiv

3D-Aware VLMs with Implicit and Explicit Geometries

Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning. To bridge this gap, we present VLM-IE3D, a unified…

1 min 0 views