Skip to content
Back to skills

Cosinegate Semantic Dynamic Routing Via Cosine Incompatibility In Residual Networks

ASecurity

**arXiv ID:** 2512.22206 **Authors:** Yogeswar Reddy Thota **Published:** 2025-12-21T18:26:18Z **Abstract:** Modern deep residual networks perform substantial redundant computation by evaluating all residual blocks for every input, even when identity mappings suffice. We introduce CosineGate, an end-to-end differentiable architecture for dynamic routing in residual networks that uses cosine incompatibility between identity and residual feature representations as a self-supervised skip signal....

  • 3 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 11, 2026
tools

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill cosinegate-semantic-dynamic-routing-via-cosine-incompatibility-in-residual-networks --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cosinegate Semantic Dynamic Routing Via Cosine Incompatibility In Residual Networks?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Cosinegate Semantic Dynamic Routing Via Cosine Incompatibility In Residual Networks
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-cosinegate-semantic-dynamic-routing-via-cosine-inc/badge)](https://www.skillsdirectory.com/skills/hiyenwong-cosinegate-semantic-dynamic-routing-via-cosine-inc)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# CosineGate: Semantic Dynamic Routing via Cosine Incompatibility in Residual Networks

**arXiv ID:** 2512.22206
**Authors:** Yogeswar Reddy Thota
**Published:** 2025-12-21T18:26:18Z
**Abstract:**
Modern deep residual networks perform substantial redundant computation by evaluating all residual blocks for every input, even when identity mappings suffice. We introduce CosineGate, an end-to-end differentiable architecture for dynamic routing in residual networks that uses cosine incompatibility between identity and residual feature representations as a self-supervised skip signal. CosineGate measures semantic redundancy through the Cosine Incompatibility Ratio (CIR), defined as 1 - cos(x, F(x)), and uses Gumbel-Softmax relaxation to enable per-sample, per-block gating during training. A progressive FLOPs regularization term controls average compute usage without destabilizing optimization. On CIFAR-10, CosineGate spans the accuracy-efficiency Pareto frontier: an aggressive configuration achieves 89.9 percent accuracy with 24.1 percent FLOPs savings, a balanced configuration achieves 91.3 percent accuracy with 28.5 percent savings at epoch 160, and a conservative configuration reaches a peak of 93.2 percent accuracy with minimal compute reduction. These results match or exceed ResNet-20 (91.3 percent) while reducing computation, without auxiliary supervision, distillation, or task-specific heuristics. Our results demonstrate that simple geometric measures of feature incompatibility provide a principled and effective signal for dynamic residual routing.

## Skill Description

This skill is generated from the arXiv paper: CosineGate: Semantic Dynamic Routing via Cosine Incompatibility in Residual Networks (2512.22206).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2512.22206](http://arxiv.org/abs/2512.22206v1)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.