AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

On Large Multimodal Models as Open-World Image Classifiers

Alessandro Conti, Massimiliano Mancini, Enrico Fini, Yiming Wang, Paolo Rota, Elisa Ricci

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 12 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
ask the model to be more generic (ablation)LMMs · fine-grained, very fine-grained and DTDcorrect but generic share: +9.1%Improved
ask the model to be more specific (ablation)LMMs · fine-grained, very fine-grained and DTDprediction correctnessHurt
use domain-specific prompts (e.g. flower, car) (ablation)LMMs · fine-grained, very fine-grained and DTDcorrect and specific share: 12.5%Improved
use domain-specific prompt on LLaVA-OV 0.5B (ablation)LLaVA-OV 0.5B · fine-grained datasetscorrect and specific share: +29%Improved
use domain-specific prompt on Qwen2VL 7B (ablation)Qwen2VL 7B · fine-grained datasetscorrect and specific share: +15%Improved
add test-time chain-of-thought reasoning prompts (ablation)Qwen2VL · OW classificationcorrect and specific share: up to +13%Improved
use multi-turn LlamaV-o1 prompt (ablation)InternVL2 and Qwen2VL · OW classificationwrong and generic share: +1.7Hurt
replace base models with reasoning-tailored versions (InternVL2.5, Qwen2.5VL) (ablation)InternVL2 and Qwen2VL · OW classificationcorrect and wrong-similar predictions: +6.6% correct, +3.7% wrong but specificMixed
prompt for multiple labels (list objects, caption, describe) (ablation)LMMs · OW classificationtext inclusionImproved
compare LMMs against contrastive OW baselinesLMMs vs CaSED/CLIP retrieval · 10 datasetsmetric/group wins: 11/16Improved
compare Qwen2VL 2B on FGVCAircraftQwen2VL 2B · FGVCAircrafttext inclusion: 25.6 vs 4.6Improved
allow multi-label tags for wrong predictionsLMMs · OW classificationwrong predictions matching an image tag: 30% to 60%Improved

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