AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Evidence-Grounded Trustworthy Multimodal Reasoning and Evaluation Benchmark in Complex Urban Scenes

Zhaoyang Wei, Bowen Jiang, Xumeng Han, Jiashu Li, Xuehui Yu, Yuling Liu, Guorong Li, Zhenjun Han, Jianbin Jiao

IJCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 10 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 EGVOR (reflective SFT plus RL on evidence atoms)Qwen2.5-VL-7B · AD2-Benchaverage score: 55.0 -> 67.7Improved
train with EGVORQwen2.5-VL-7B · AD2-Bench Basic Perceptionaverage score: 59.3 -> 72.6Improved
train with EGVORQwen2.5-VL-7B · AD2-Bench Detectionscore: 51.0 -> 69.7Improved
train with EGVORQwen2.5-VL-7B · AD2-Bench OCR-CERcharacter error rate: 15.4 -> 13.0Improved
add reflective SFT stage (ablation)Qwen3.5-9B · AD2-Benchaverage score: 59.0 -> 64.6Improved
add RL with spatial and semantic rewards after SFT (ablation)Qwen3.5-9B · AD2-Benchaverage score: 64.6 -> 69.4Improved
add reflective SFT stage (ablation)Qwen3.5-9B · TreeBench OCRaccuracy: 75.0 -> 66.2Hurt
add reflective SFT stage (ablation)Qwen3.5-9B · TreeBench Contact & Occlusionaccuracy: 53.7 -> 41.5Hurt
add reflective SFT stage (ablation)Qwen3.5-9B · TreeBench Object Retrievalaccuracy: 68.8 -> 87.5Improved
add RL after SFT (ablation)Qwen3.5-9B · TreeBenchoverall accuracy: 46.5 -> 54.1Improved
add RL after SFT (ablation)Qwen3.5-9B · TreeBench Perspective Transformaccuracy: 11.8 -> 23.5Improved
add RL after SFT (ablation)Qwen3.5-9B · TreeBench Orderingaccuracy: 21.1 -> 38.6Improved

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