AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

MoSA: Mosaic Shared Adaptation of Large Language Models

Xiequn Wang, Zhan Zhuang, Shengda Luo, Yu Zhang

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging

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
use balanced random tessellation instead of row-stripe grouping (ablation)MoSA · Commonsense reasoning (Llama-3-8B)average accuracy: 87.05 -> 87.63Improved
use balanced random tessellation instead of column-stripe grouping (ablation)MoSA · Commonsense reasoning (Llama-3-8B)average accuracy: 86.65 -> 87.63Improved
use balanced group sizes instead of skewed group sizes (ablation)MoSA · Commonsense reasoning (Llama-3-8B)average accuracy: 74.36 -> 87.63Improved
adapt FFN projections in addition to QKV (ablation)MoSA · Commonsense reasoning (Llama-3-8B)average accuracy: 87.16 -> 87.63Improved
adapt attention QKV in addition to FFN (ablation)MoSA · Commonsense reasoning (Llama-3-8B)average accuracy: 87.35 -> 87.63Improved
adapt value projection instead of key projection only (ablation)MoSA · Commonsense reasoning (Llama-3-8B)average accuracy: 82.12 -> 86.29Improved
reduce budget to LoRA r=1 equivalent (0.022% params) (ablation)MoSA · Commonsense reasoning (Llama-3-8B)average accuracy: 80.79 -> 86.81No clear effect
raise learning rate from 1e-5 to 5e-5 (ablation)MoSA · Commonsense reasoning (Llama-3-8B)average accuracy: 87.63 -> 86.21Hurt
vary random seed of tessellation (ablation)MoSA · Commonsense reasoning (Llama-3-8B)average accuracy: mean 87.45, std 0.14No clear effect
use MoSA instead of HiRALlama-3-8B PEFT · GSM8K (trained on MetaMathQA)accuracy: 70.81 -> 78.00Improved
use MoSA instead of HiRALlama-2-7B PEFT · Commonsense reasoning (8 tasks avg)average accuracy: 81.42 -> 83.83Improved
use MoSA instead of HiRALlama-3-8B PEFT · ConvAI2 (average of metrics)average score: 47.80 -> 50.14Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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