AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

MyVLM: Personalizing VLMs for User-Specific Queries

Yuval Alaluf, Elad Richardson, Sergey Tulyakov, Kfir Aberman, Danny Cohen-Or

ECCV 2024 · Vision-language and multimodal › Visual question answering · approach: Multimodal LLM question answering · 37 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 regularization and augmentations to concept embedding training (ablation)MyVLM · MyVLM dataset subset (10 concepts)Recall (%): 25.88 -> 84.87Improved
add image and caption augmentations (ablation)MyVLM · MyVLM dataset subset (10 concepts)Recall (%): 72.77 -> 84.87Improved
increase training images from 1 to 4 (ablation)MyVLM on BLIP-2 · MyVLM datasetRecall (%): 75.42 -> 87.11Improved
increase training images from 1 to 4 (ablation)MyVLM on LLaVA · MyVLM datasetRecall (%): 88.93 -> 95.97Improved
learn a concept embedding with concept heads instead of LLM-guided keyword replacementLLaVA captioning (all) · MyVLM datasetRecall (%): 46.23 -> 95.97Improved
learn a concept embedding instead of keyword replacement for people on BLIP-2BLIP-2 captioning (people) · MyVLM datasetRecall (%): 84.33 -> 79.76No clear effect
learn a concept embedding instead of in-context prompting (OpenFlamingo) for objectspersonalized captioning (objects) · MyVLM datasetRecall (%): 49.77 -> 95.10Improved
apply MyVLM personalization on BLIP-2 captioningBLIP-2 · Standard captioning metrics (all)CIDEr: 1.89 -> 1.28Hurt
apply MyVLM personalization on LLaVA captioningLLaVA · Standard captioning metrics (all)CIDEr: 0.17 -> 0.58Improved

Later papers that compared with this method

2 later accepted papers report MyVLM as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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