AI Paper Atlas

Research map / Large language models / AI and society

FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion

Anke Tang, Li Shen, Yong Luo, Enneng Yang, Han Hu, Lefei Zhang, Bo Du, Dacheng Tao

JMLR 2025 · Large language models › AI and society · approach: Benchmarking and reproducibility practice · 49 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
fine-tune the vision encoder on the target taskCLIP-ViT-B/32 · SUN397accuracy: 63.2 -> 75.0Improved
fine-tune the vision encoder on the target taskCLIP-ViT-B/32 · EuroSATaccuracy: 46.0 -> 99.0Improved
fine-tune the vision encoder on the target taskCLIP-ViT-L/14 · SVHNaccuracy: 58.4 -> 97.9Improved
fine-tune on SVHN and evaluate on EuroSAT (negative transfer)CLIP-ViT-B/32 · EuroSATaccuracy: 46.0 -> 9.8Hurt
fine-tune on SVHN and evaluate on MNIST (positive transfer)CLIP-ViT-B/32 · MNISTaccuracy: 48.2 -> 81.8Improved
fine-tune on SVHN and evaluate on MNIST (positive transfer)CLIP-ViT-L/14 · MNISTaccuracy: 76.4 -> 92.2Improved
fine-tune on EuroSAT and evaluate on SVHN (negative transfer)CLIP-ViT-L/14 · SVHNaccuracy: 58.4 -> 33.4Hurt
fine-tune a ResNet-50 on depth estimation and evaluate on segmentationResNet-50 · NYUv2 segmentationmIoU: 52.0 -> 2.3Hurt
fine-tune GPT-2 on CoLA and evaluate on MRPCGPT-2 · GLUE MRPCaccuracy: 80.4 -> 68.4Mixed

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