AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MMIFEvol: Towards Evolutionary Multimodal Instruction Following

Haoyu Wang, Sihang Jiang, Xiangru Zhu, Yuyan Chen, Xiaojun Meng, Jiansheng Wei, Yitong Wang, Yanghua Xiao

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Visual instruction tuning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MMIFEvol, an evolutionary framework for building multimodal instruction-following data and benchmarks with difficulty stratification, addressing shortcomings of existing datasets.

Problem

Existing multimodal instruction-following datasets and benchmarks lack difficulty stratification, among other shortcomings noted in the abstract (only the first is visible).

Approach

An evolutionary approach that progressively increases instruction difficulty to produce multimodal instruction-following data at graded difficulty levels; details beyond the abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
SFT on MMIFEvol single-task instructions (ablation)LLaVA-NeXT-7B · MIA-Benchtotal score: 69.4 -> 73.5Improved
SFT on MMIFEvol multi-task instructions instead of single-task (ablation)LLaVA-NeXT-7B · MIA-Benchtotal score: 73.5 -> 76.2Improved
SFT on MMIFEvol multi-task instructions (ablation)Qwen2.5-VL-7B · MIA-Benchtotal score: 83.8 -> 90.7Improved
SFT on MMIFEvol multi-task instructions (ablation)InternVL3-8B · MIA-Benchtotal score: 84.5 -> 93.6Improved
SFT on MMIFEvol multi-task instructions (ablation)InternVL3-8B · MM-IFEvalaccuracy: 44.1 -> 47.8Improved
SFT on MMIFEvol single-task instructions (ablation)LLaVA-NeXT-7B · MM-IFEvalaccuracy: 36.4 -> 36.9No clear effect
go from single-task to multi-task instructions7 MLLMs · MMIFEvolpreference (P): Gemini 75.3 -> 67.3; LLaVA-NeXT 26.7 -> 4.1Hurt
go from single-task to multi-task instructions7 MLLMs · MMIFEvolaccuracy (A): LLaVA-OneVision 68.1 -> 40.4Hurt
go from single-task to multi-task instructionsGemini2.0-Flash and InternVL3-8B · MMIFEvolfollowing (F): Gemini 86.7 -> 84.7; LLaVA-OneVision 68.6 -> 40.0Mixed

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