No article text was recorded for this version.
model stitching
Version 2 of 225 papers33 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders
- Blog: How to Characterize The Landscape of Overparameterized Convolutional Neural Networks
- Blog: Towards a learning theory of representation alignment
- Blog: If you've trained one you've trained them all: inter-architecture similarity increases with robustness
- Blog: Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity
- Blog: Similarity and Matching of Neural Network Representations
- Blog: Subliminal Effects in Your Data: A General Mechanism via Log-Linearity
- Blog: Revisiting Model Stitching to Compare Neural Representations
- Blog: Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking
- Blog: Model Stitching: Looking For Functional Similarity Between Representations
- Blog: Functional Alignment Can Mislead: Examining Model Stitching
- Blog: Investigating Representation Universality: Case Study on Genealogical Representations
- Blog: How Not to Stitch Representations to Measure Similarity: Task Loss Matching Versus Direct Matching
- Blog: On the Functional Similarity of Robust and Non-Robust Neural Representations
- Blog: Efficiency for Free: Ideal Data Are Transportable Representations
- Blog: Understanding the Inner-workings of Language Models Through Representation Dissimilarity
- Blog: Stitchable Neural Networks
- Blog: On the Emergence of Cross-Task Linearity in Pretraining-Finetuning Paradigm
- Blog: Do neural networks trained with topological features learn different internal representations?
- Blog: Identifying Interpretable Subspaces in Image Representations
- Blog: TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
- Blog: Generalization from Starvation: Hints of Universality in LLM Knowledge Graph Learning
- Blog: Understanding image representations by measuring their equivariance and equivalence
- Blog: Linearly Decoding Refused Knowledge in Aligned Language Models
- Blog: All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_model_stitching_567f3a9a,
title = {model stitching},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/model-stitching/rdr_567f3a9a6704475fa982c4e6c5863c18},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_model_stitching_567f3a9a_v2,
title = {model stitching},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/model-stitching/rdr_567f3a9a6704475fa982c4e6c5863c18/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}