AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks

Wish Suharitdamrong, Tony Alex, Muhammad Awais, Sara Atito

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 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 inter-modal fusion pathway to LoRA (CoLA r=16 vs LoRA r=16)dual-encoder PEFT · REC avg RefCOCO/+/gaccuracy avg (%): 82.3 -> 83.4Improved
add inter-modal pathway vs parameter-matched LoRA (r=54)dual-encoder PEFT · REC avgaccuracy avg (%): 81.8 -> 83.4Improved
add inter-modal pathway to LoRAdual-encoder PEFT · RES avgmIoU avg: 72.2 -> 73.7Improved
raise LoRA rank from 16 to 54 to match parametersLoRA · REC avgaccuracy avg (%): 82.3 -> 81.8Hurt
raise LoRA rank from 16 to 54LoRA · AVEaccuracy (%): 79.2 -> 79.2No clear effect
add CoLA over LoRAdual-encoder PEFT · AVEaccuracy (%): 79.2 -> 80.7Improved
add CoLA over LoRAdual-encoder PEFT · AVSmIoU: 80.1 -> 80.9Improved
use non-shared low-rank matrices between intra and inter pathways instead of fully shared (ablation)CoLA · RefCOCOgREC avg: 81.2 -> 81.7Improved
use progressive cross-modal propagation instead of uniform or module-wise (ablation)CoLA · RefCOCOgavg REC+RES: 76.1 -> 76.5Improved
module-wise instead of uniform propagation (ablation)CoLA · RefCOCOgavg REC+RES: 76.1 -> 76.1No clear effect
use Kronecker factorization of Phi at symmetric rank (ablation)CoLA · AVEaccuracy (%): 80.7 -> 79.9Hurt
add asymmetric ranks (intra 8, inter 32) with Kronecker Phi (ablation)CoLA · AVEaccuracy (%): 80.7 -> 81.44Improved

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