AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks

MohammadReza Davari, Eugene Belilovsky

ECCV 2024 · Architectures and efficiency › Pruning and efficient tuning · approach: Parameter-efficient transfer analysis · 63 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Breadcrumbs sparse masking (both tails) to task vectors instead of plain Task Arithmeticmulti-task merging of CLIP · 8 vision tasks (CLIP)avg normalized accuracy: 77.66 -> 83.35Improved
use magnitude-based masking instead of random sparsification of task vectors (ablation)Task Arithmetic · 8 vision tasks (CLIP)avg normalized accuracy: 74.00 -> 83.35Improved
use Breadcrumbs instead of Fisher Mergingmulti-task merging · 8 vision tasks (CLIP)avg normalized accuracy: 75.11 -> 83.35Improved
merge Breadcrumbs from related-task public models into a fine-tuned modelT5-base · GLUE MRPCaccuracy: 87.9 -> 90.0Improved
merge Breadcrumbs of new tasks into a fine-tuned modelT5-base · GLUE SST-2accuracy: 93.3 -> 94.4Improved
merge Task Arithmetic vectors into a fine-tuned modelT5-base · GLUE SST-2accuracy: 93.3 -> 93.5No clear effect
mask both small and large magnitude weights rather than only one tail (ablation)Model Breadcrumbs · 8 vision tasks (ViT-B-32)avg normalized accuracyImproved
reuse hyperparameters tuned on few tasks when adding more tasks (Breadcrumbs vs Task Arithmetic)Model Breadcrumbs · ImageNet 200-task sequence (ViT-L-14)avg normalized accuracyImproved
scale up CLIP model from ViT-B-32 to ViT-L-14Model Breadcrumbs · 8 vision tasks (CLIP)avg normalized accuracy: 91.48% of fine-tuned (ViT-L-14, 8 tasks)Improved
use Breadcrumbs instead of TIESmulti-task merging · 8 vision tasks (ViT-B-32)avg normalized accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy