AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

TDSS: Task Dynamic-Synergistic Skill Adaptation for Boosting Efficient and Scalable Multi-Task Learning in Dense Visual Prediction

Haiming Yao, Qiyu Chen, Wei Luo, Zheng Zhang, Jianxing Liao, Wei You

AAAI 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 TSAI to the baseline (ablation)TDSS · PASCAL-Context (Swin-T, 4 tasks)Delta_m: 0 -> +5.76Improved
add TDSA to the baseline (ablation)TDSS · PASCAL-Context (Swin-T, 4 tasks)Delta_m: 0 -> +0.94Improved
combine TDSA and TSAI (ablation)TDSS · PASCAL-Context (Swin-T, 4 tasks)Delta_m: +5.76 -> +8.37Improved
add skill experts and dynamic task gating (ablation)TDSA · PASCAL-Context (Swin-T, 4 tasks)Delta_m: +7.85 -> +8.37Improved
insert TDSA in both attention and FFN rather than one (ablation)TDSS · PASCAL-Context (Swin-T, 4 tasks)Delta_m: +7.41 / +7.19 -> +8.37Improved
increase number of skills M from 10 (ablation)TDSA · PASCAL-Context (Swin-T, 4 tasks)Delta_m: +8.37 (M=10) vs +8.12 / +8.13 / +8.23No clear effect
increase low-rank dimension R beyond C/4 (ablation)TDSA · PASCAL-Context (Swin-T, 4 tasks)Delta_m: +8.37 -> +8.76 (R=C/2), params 3.52M -> 5.89MMixed
more synergistic modules K (1 -> 4 -> 6) (ablation)TSAI · PASCAL-Context (Swin-T, 4 tasks)Delta_m: +5.29 -> +8.37 -> +9.18Improved
use lateral topology versus MTLoRA/TADFormerTDSS · PASCAL-Context (Swin-T, 4 tasks)GPU memory (GB): 14.65 vs 18.22 / 20.30Improved
use TDSS rather than MTLoRATDSS · PASCAL-Context (Swin-T, 4 tasks)Training time (s/batch): 0.232 -> 0.380Hurt
use task-specific scale fusion with global interaction (ablation)TSAI · PASCAL-Context (Swin-T, 4 tasks)Delta_mImproved

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