AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Shengbang Tong, David Fan, Jiachen Li, Yunyang Xiong, Xinlei Chen, Koustuv Sinha, Michael Rabbat, Yann LeCun, Saining Xie, Zhuang Liu

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Visual instruction tuning · 180 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 visual understanding data to joint training (vs generation-only) (ablation)VPiT LLaMA-3 8B · COCO-30K, 200k generation dataFID: 110.7 -> 15.2Improved
add visual understanding data to joint training (vs generation-only) (ablation)VPiT LLaMA-3 8B · COCO-30K, 5M generation dataFID: 27.7 -> 14.3Improved
joint train with ImageQA data (ablation)VPiT · COCO-30K, 200k generation dataFID: 110.5 -> 18.9Improved
joint train with VideoQA data (ablation)VPiT · COCO-30K, 200k generation dataFID: 110.5 -> 26.5Improved
joint train with pure video data (ablation)VPiT · COCO-30K, 200k generation dataFID: 110.5 -> 84.7Improved
joint train with image-to-image data (ablation)VPiT · COCO-30K, 200k generation dataFID: 110.5 -> 97.5Improved
increase VQA data from 1M to 7M (200k generation data) (ablation)VPiT · Image QA averageaccuracy: 46.4 -> 55.8Improved
increase VQA data from 1M to 7M (200k generation data) (ablation)VPiT · COCO-30KFID: 28.3 -> 18.2Improved
increase generation data from 200k to 4M (1M VQA) (ablation)VPiT · Image QA averageaccuracy: 46.4 -> 51.4Improved
increase generation data from 200k to 4M (7M VQA) (ablation)VPiT · Image QA averageaccuracy: 55.8 -> 56.2No clear effect
increase generation data from 200k to 4M (1M VQA) (ablation)VPiT · COCO-30KFID: 28.3 -> 18.4Improved
use cosine similarity loss instead of L1 loss (ablation)VPiT LLaMA-3 8B · Image QA averageaccuracy: 53.83 -> 55.93Improved

Later papers that compared with this method

2 later accepted papers report MetaMorph as a baseline in their results tables; 1 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 1 of 2 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