AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

LLaVA-KD: A Framework of Distilling Multimodal Large Language Models

Yuxuan Cai, Jiangning Zhang, Haoyang He, Xinwei He, Ao Tong, Zhenye Gan, Chengjie Wang, Zhucun Xue, Yong Liu, Xiang Bai

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 44 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 distilled pre-training (DPT) before SFT (ablation)PT-SFT Qwen1.5-0.5B · Avg10 (10 benchmarks)Avg10: 54.7 -> 55.6Improved
add distilled fine-tuning (DFT) after DPT-SFT (ablation)DPT-SFT · Avg10 (10 benchmarks)Avg10: 55.6 -> 57.9Improved
add SFT stage between DPT and DFT (ablation)DPT-DFT · Avg10 (10 benchmarks)Avg10: 55.9 -> 57.9Improved
use DPT instead of plain PT in the SFT-DFT pipeline (ablation)PT-SFT-DFT · Avg10 (10 benchmarks)Avg10: 56.6 -> 57.9Improved
use DPT instead of plain PT in the no-SFT pipeline (ablation)PT-DFT · Avg10 (10 benchmarks)Avg10: 55.8 -> 55.9No clear effect
add a second DFT stage (DPT-DFT-DFT) (ablation)DPT-SFT-DFT · Avg10 (10 benchmarks)Avg10: 57.9 -> 58.0No clear effect
add RDist to MDist during DPT (ablation)DPT MDist only · Avg10 (10 benchmarks)Avg10: 55.1 -> 55.6Improved
add RDist to MDist during DFT (ablation)DFT MDist only · Avg10 (10 benchmarks)Avg10: 57.7 -> 57.9Improved
add MDist to RDist during DFT (ablation)DFT RDist only · Avg10 (10 benchmarks)Avg10: 57.0 -> 57.9Improved
add visual-token distillation to response distillation in DFT (ablation)MDist DFT · Avg10 (10 benchmarks)Avg10: 57.2 -> 57.7Improved
also distill prompt tokens together with response and visual tokens in DFT (ablation)MDist DFT · Avg10 (10 benchmarks)Avg10: 57.7 -> 57.1Hurt
use MDist+RDist instead of FKL/JSD under PT-DFT (ablation)PT-DFT · Avg10 (10 benchmarks)Avg10: 55.5 -> 55.8Improved

Later papers that compared with this method

1 later accepted paper reports LLaVA-KD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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