AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

FAAR: Efficient Frequency-Aware Multi-Task Fine-Tuning via Automatic Rank Selection

Maxime Fontana, Michael Spratling, Miaojing Shi

CVPR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning · 0 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 Performance-Driven Rank Shrinking with DoRA to MTLoRA-style high-rank adaptation (ablation)MTLoRA (high rank) · PASCAL-ContextDelta m (%): +1.36 -> +4.92Improved
add Task-Spectral Pyramidal Decoder (frequency filter) (ablation)FAAR high rank · PASCAL-ContextDelta m (%): +3.83 with TS-PDImproved
add XT-Cons to TS-PD (ablation)TS-PD · PASCAL-ContextDelta m (%): +3.83 -> +4.63Improved
combine PDRS with DoRA and TS-PD + XT-Cons (full FAAR) (ablation)FAAR · PASCAL-ContextDelta m (%): +4.92 -> +5.28Improved
swap LoRA for DoRA in high-rank MTLoRA (ablation)MTLoRA (r=64) · PASCAL-ContextDelta m (%): +2.55 -> +1.36Hurt
swap LoRA for DoRA in low-rank MTLoRA (ablation)MTLoRA (low rank) · PASCAL-ContextDelta m (%): -2.56 -> -2.31Improved
use DoRA instead of LoRA together with PDRS (ablation)high + PDRS · PASCAL-ContextDelta m (%): +2.83 -> +4.92 (TS-PD removed)Improved
add rank shrinking (PDRS) to high-rank MTLoRA with DoRA (ablation)high + TS-PD + XT-Cons · PASCAL-Contextparameters: rank from 64 to about 5; 3.38M params vs 8.34M MTLoRAImproved
vary initial rank rinit among 64, 32, 16 (ablation)FAAR · PASCAL-Contextoverall performanceNo clear effect
apply FAAR instead of MTL full fine-tuningSwin-Tiny MTL · NYUD-v2Delta m (%): -8.49 -> -7.88; 28.10M -> 2.85M paramsImproved
FAAR vs single-task training on small datasetFAAR · NYUD-v2Delta m (%): -7.88 vs 0 single-taskHurt
apply FAAR vs TADFormerSwin-Tiny MTL PEFT · PASCAL-ContextDelta m (%): +4.24 -> +5.28Improved

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