AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Beyond Adapter Retrieval: Latent Geometry-Preserving Composition via Sparse Task Projection

Pengfei Jin, Peng Shu, Sifan Song, Sekeun Kim, Qing Xiao, Cheng Chen, Tianming Liu, Xiang Li, Quanzheng Li

AAAI 2026 · Image generation › Autoregressive and latent generation · approach: Latent diffusion with learned tokenizers · 6 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
use l1 sparse projection instead of uniform averagingadapter composition · Prostate-E zero-shotDice: 64.6% -> 79.1%Improved
use l1 sparse projection instead of uniform averagingadapter composition · AbdAtlas zero-shotDice: 19.2% -> 64.5%Improved
add l1 sparsity to least-squares combination (ablation)adapter composition · Prostate-E zero-shotDice: 52.0% -> 79.1%Improved
add l1 sparsity to least-squares combination (ablation)adapter composition · AbdAtlas zero-shotDice: 2.5% -> 64.5%Improved
compose multiple adapters instead of nearest only (ablation)adapter composition · Prostate-EDice: 0.1% -> 79.1%Improved
compose multiple adapters instead of nearest only (ablation)adapter composition · Prostate-ADice: 90.5% -> 90.5%No clear effect
use sparse projection vs least-squares on report generationadapter composition · CT Abdomen ROUGE-LROUGE-L: 0.1393 -> 0.1379Hurt
use sparse projection vs uniform average on report generationadapter composition · X-ray ROUGE-LROUGE-L: 0.1776 -> 0.2084Improved
add in-domain supervised LoRA to candidate pool (ablation)sparse composition · Prostate-CDice: 90.5% -> 90.8%Improved
use sparse projection for SD v1.5 adapter compositionadapter composition · MS COCO 100 prompts (SD v1.5)preference win rateImproved

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