AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MA-CIR: A Multimodal Arithmetic Benchmark for Composed Image Retrieval

Jaeseok Byun, Young Kyun Jang, Seokhyeon Jeong, Donghyun Kim, Taesup Moon

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 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
fine-tune E5-V with MA-CIR-tailored text triplets with hard negatives instead of NLI pairsE5-V · MA-CIRAvg R@1 (%): 32.4 -> 48.5Improved
fine-tune E5-V with MA-CIR-tailored text tripletsE5-V · CIRCOmAP@5 (%): 17.6 -> 26.5Improved
fine-tune E5-V with MA-CIR-tailored text tripletsE5-V · CIRRR@1 (%): 30.9 -> 36.8Improved
add hard negatives to our text triplets (ablation)adapted E5-V · MA-CIRAvg R@1 (%): 43.9 -> 48.5Improved
add hard negatives to default RTD triplets (ablation)adapted E5-V · MA-CIRAvg R@1 (%): 38.5 -> 30.2Hurt
use our BLIP-style LLM triplets instead of default RTD triplets (no hard negatives) (ablation)adapted E5-V · MA-CIRAvg R@1 (%): 38.5 -> 43.9Improved
use default RTD triplets instead of NLI pairs (ablation)E5-V · MA-CIR / CIRRAvg R@1 (%): 32.4 -> 38.5Mixed
scale CLIP backbone up to ViT-G/14 (ablation)Slerp and LinCIR · MA-CIRAvg R@1 (%): less than 3% vs over 10% on CIRRNo clear effect
use compositionality fine-tuned CLIP (FSC-CLIP, NegCLIP) (ablation)Slerp and LinCIR · MA-CIRAvg R@1 (%): over 9% on CIRR, little to no gain on MA-CIRNo clear effect
use LLM-based text encoder (E5-V) instead of CLIPZS-CIR · MA-CIRAvg R@1 (%): 23.3 -> 32.4Improved

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