AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

Hao Zhang, Hongyang Li, Feng Li, Tianhe Ren, Xueyan Zou, Shilong Liu, Shijia Huang, Jianfeng Gao, Lei Zhang, Chunyuan Li, Jianwei Yang

ECCV 2024 · Vision-language and multimodal › Multimodal LLMs · approach: Benchmarks and analysis of MLLMs · 107 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
train with grounded visual chat data and connect LLM to a grounding modelLLaVA-G · Grounding-Bench (1000 images)F1: 32.0 (CogVLM-Grounding) -> 37.1Improved
allow gradients from grounding model to flow into the language model (no detach) (ablation)LLaVA-G · Grounding-Bench (30 images)F1: 35.1 -> 43.2Improved
detach grounding model gradient to LLM (ablation)LLaVA-G · Grounding-Bench chat scorechat score (All): 79.3 -> 81.2Improved
require grounded output in the response (ablation)LLaVA-G · LLaVA-Bench (COCO)chat score (All): 81.2 -> 79.7No clear effect
increase grounding-model queries from 50 to 300 (ablation)LLaVA-G · RefCOCO RECACC: 86.71 -> 86.35No clear effect
use marks overlaid on image as grounding prompt instead of the grounding model (ablation)LLaVA-G · Flickr30K phrase grounding (test)top1 accuracy: 83.6 -> 77.9Hurt
use box prompts instead of click prompts (ablation)LLaVA-G · COCO val2017 object classificationaccuracy: 70.8 -> 71.5Improved
use mark size 30 and mask alpha 0.2/0.2 instead of size 20 and alpha 0.4/0.4 (ablation)LLaVA-G marks · Flickr30K phrase grounding (val)top1 accuracy: 72.1 -> 76.6Improved

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