AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning

Hang Du, Jiayang Zhang, Guoshun Nan, Wendi Deng, Zhenyan Chen, Chenyang Zhang, Wang Xiao, Shan Huang, Yuqi Pan, Tao Qi, Sicong Leng

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 3 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 stage-wise curriculum with reasoning steps instead of plain fine-tuningMantis · MIR in-domain (average)accuracy (%): 33.71% -> 35.99%Improved
add stage-wise curriculum with reasoning steps instead of plain fine-tuningLLaVA-Next-Interleave · MIR in-domain (average)accuracy (%): 34.42% -> 36.58%Improved
add stage-wise curriculum with reasoning steps instead of plain fine-tuningLLaVA-OneVision · MIR in-domain (average)accuracy (%): 42.36% -> 47.60%Improved
add stage-wise curriculum with reasoning steps instead of plain fine-tuningQwen2-VL · MIR in-domain (average)accuracy (%): 45.15% -> 51.76%Improved
add stage-wise curriculum with reasoning steps instead of plain fine-tuningmPLUG-Owl3 · MIR in-domain (average)accuracy (%): 36.51% -> 40.36%Improved
fine-tune on MIR with plain QA pairsQwen2-VL · MIR in-domain (average)accuracy (%): 40.44% -> 45.15%Improved
add curriculum method over plain tuningMantis · MIRBENCHaccuracy (%): 43.10% -> 40.82%Hurt
add curriculum method over plain tuningLLaVA-Next-Interleave · MUIRBenchaccuracy (%): 41.32% -> 40.25%Hurt
add curriculum method over plain tuningQwen2-VL · MUIRBenchaccuracy (%): 45.51% -> 46.67%Mixed
progress from stage 1 to stage 2 (less reasoning guidance) (ablation)Qwen2-VL · MIR in-domain (average)accuracy (%): 38.01% -> 36.73%Hurt
progress through later stages 3, 4, 5 (ablation)Qwen2-VL · MIR in-domain (average)accuracy (%): 36.73% -> 41.03% -> 45.97% -> 51.76%Improved
train through all five stages (ablation)Qwen2-VL · MIR Sequentialaccuracy (%): 32.22% -> 36.66%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