AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Instruction Tuning-free Visual Token Complement for Multimodal LLMs

Dongsheng Wang, Jiequan Cui, Miaoge Li, Wang Lin, Bo Chen, Hanwang Zhang

ECCV 2024 · Vision-language and multimodal › Multimodal LLMs · approach: Visual instruction tuning · 5 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 VTC complementary visual tokens to the frozen MLLMBLIP2 · LVLM-eHub Visdialscore: 10.73 -> 77.20Improved
add VTC tokens to MiniGPT-4MiniGPT-4 · LVLM-eHub ScienceQAaccuracy: 25.43 -> 37.85Improved
add VTC tokens to InstructBLIPInstructBLIP · LVLM-eHub ScienceQAaccuracy: 46.26 -> 46.21No clear effect
add VTC tokens to BLIP2BLIP2 · MME Code Reasoningscore: 75.00 -> 70.50Hurt
add VTC tokens after LoRA fine-tuning the LLMInstructBLIP · MME Perceptionscore: 121.42 -> 124.31Improved
add 32 extra learnable visual queries (64 total) instead of VTC (ablation)BLIP2 · MME Perceptionscore: 133.79 -> 133.95No clear effect
reuse VTC module for two iterations at test time instead of one (ablation)VTC · OKVQA, IconQA, GQAnormalized VQAImproved
increase iterations beyond two (ablation)VTC · OKVQA, IconQA, GQAnormalized VQANo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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