gradient-optimization

Tag

Cards List
#gradient-optimization

On the Depth Scalability of Logic Gate Networks

arXiv cs.LG · 2026-07-27 Cached

The paper identifies two causes why logic gate networks fail to benefit from increased depth and proposes Input-Anchored Logic Gate Networks (IALGNs) that condition each layer on original inputs, achieving consistent depth-accuracy improvements beyond 100 layers.

0 favorites 0 likes
#gradient-optimization

Inverse Critical Experiment Design via Gradient Optimization and a Multigroup Attention-Based Neural Network Architecture

arXiv cs.LG · 2026-06-04 Cached

Researchers from MIT present a methodology for inverse design of nuclear critical experiments using deep neural networks with a novel multigroup attention pooling architecture and gradient-based optimization to maximize neutronic similarity coefficients. The approach is applied to validate a HALEU fuel transportation cask, achieving high similarity scores for three configurations of interest.

0 favorites 0 likes
#gradient-optimization

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

Hugging Face Daily Papers · 2026-04-16 Cached

LeapAlign is a post-training method that improves flow matching model alignment with human preferences by reducing computational costs through two-step trajectory shortcuts while enabling stable gradient propagation to early generation steps. The method outperforms state-of-the-art approaches when fine-tuning Flux models across various image quality and text-alignment metrics.

0 favorites 0 likes
← Back to home

Submit Feedback