AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MMRL++: Parameter-Efficient and Interaction-Aware Representation Learning for Vision-Language Models

Yuncheng Guo, Xiaodong Gu

IJCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 5 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 SRRA (shared plus low-rank residual aligners) to MMRL (ablation)MMRL · Base-to-novel (11 datasets avg)HM: 81.20 -> 81.27; trainable params 4.992M -> 0.813MImproved
add PRC (progressive composition) to MMRL (ablation)MMRL · Base-to-novel (11 datasets avg)HM: 81.20 -> 81.39Improved
add PRC on top of SRRA (ablation)MMRL++ · Base-to-novel (11 datasets avg)HM: 81.27 -> 81.77Improved
add representation tokens to the text branch (ablation)MMRL++ · Base-to-novel (11 datasets avg)HM: 77.30 -> 81.77Improved
add representation tokens to the vision branch (ablation)MMRL++ · Base-to-novel (11 datasets avg)HM: 78.28 -> 81.77Improved
use representation features for base-class inference (decoupling strategy) (ablation)MMRL++ · Base-to-novel (11 datasets avg)HM: 80.64 -> 81.77Improved
use only class token features for novel classes (decoupling) (ablation)MMRL++ · Base-to-novel (11 datasets avg)HM: 81.00 -> 81.77Improved
add shared representation space for both modalities (ablation)MMRL++ · Base-to-novel (11 datasets avg)Novel accuracy: 76.94 -> 78.32Improved
use balanced shared space instead of biased MaPLe-like mapping (ablation)MMRL++ · Base-to-novel (11 datasets avg)HM: 80.91 -> 81.77Improved
vary balance weight alpha from 0.0 / 1.0 to 0.7 (ablation)MMRL++ · Base-to-novel (11 datasets avg)HM: 79.01 -> 81.77; 80.29 -> 81.77Improved
replace MMRL by MMRL++ for stabilityMMRL++ · EuroSAT novel (3 seeds)std of novel accuracy: 5.05 -> 0.54Improved
increase low-rank dimension r2 beyond 64 (ablation)MMRL++ · Base-to-novel (11 datasets avg)HM: 81.77 -> 81.04 (r2=256) and 80.42 (r2=512)No clear effect

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