AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs

Yunqiu Xu, Linchao Zhu, Yi Yang

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 25 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
feed image sequence instead of merged imageQwen2-VL-72B · MC-BenchAcc: 51.4 -> 71.4Improved
feed image sequence instead of merged imageQwen2-VL-72B · MC-BenchAP50: 26.0 -> 30.7Improved
feed image sequence instead of merged imageQwen2-VL-7B · MC-BenchAcc: 51.4 -> 54.9Improved
feed image sequence instead of merged imageQwen-VL-Chat 7B · MC-BenchAcc: 44.9 -> 33.4Hurt
feed image sequence instead of merged imageInternVL2.5-8B · MC-BenchAcc: 51.4 -> 36.4Hurt
scale LLM from 7B to 72B (sequence input)Qwen2-VL · MC-BenchAcc: 54.9 -> 71.4Improved
multi-context instruction tuningQwen2-VL-7B · MC-BenchAcc: 54.9 -> 57.7Improved
multi-context instruction tuningQwen2-VL-7B · MC-BenchAP50: 19.1 -> 22.6Improved
use GPT-4o to generate referring phrases and G-DINO to localize instead of GPT-4o end-to-endGPT-4o · MC-BenchAP50: 2.8 -> 36.2Improved
single-image grounding specialist training instead of generalistspecialist MLLMs · MC-BenchAccHurt
add synthetic instance-level data to instruction tuning data (ablation)Finetuned Baseline · MC-BenchAcc and AP50Improved
add only collected image-level multi-context data (ablation)Qwen2-VL-7B · MC-BenchAcc and AP50Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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