Functional Alignment Can Mislead: Examining Model Stitching

Damian Smith, Harvey Mannering, Antonia Marcu
2/14/2026

No confident code implementation found for this paper.

Semantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

No Preference Left Behind: Group Distributional Preference Optimization

100% match1 repo162026

Linearly Constrained Bilevel Optimization: A Smoothed Implicit Gradient Approach

99% match2026

Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework

99% match1 repo132026

Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions

99% match2026

Position: AI Agents Need Authenticated Delegation

98% match2026

UniMODE: Unified Monocular 3D Object Detection

98% match2026

Cite this paper

@article{smith2026functional,
  title  = {Functional Alignment Can Mislead: Examining Model Stitching},
  author = {Damian Smith and Harvey Mannering and Antonia Marcu},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:52607753a65da73ca237d9a35cff9a629c78936b},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/52607753a65da73ca237d9a35cff9a629c78936b.svg)](https://codeofpaper.com/paper/52607753a65da73ca237d9a35cff9a629c78936b)

Discussion