AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates

Shresth Grover, Priyank Pathak, Akash Kumar, Yogesh Rawat

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 1 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
replace single-shot scene graph with incremental scene graph updates (SGI) (ablation)GPT-4o · CoSPlan Maze-E Step Completionaccuracy (%): 46.1 -> 56.1Improved
replace single-shot scene graph with SGI (ablation)Intern-VLM 2 · CoSPlan Blocks-World-E Step Completionaccuracy (%): 18.9 -> 29.2Improved
replace single-shot scene graph with SGI (ablation)GPT-4o · CoSPlan Error Detection (Robo-VQA-E)accuracy (%): 44.2 -> 57.4Improved
replace single-shot scene graph with SGI (ablation)Qwen2 VL-8B · CoSPlan Step Completion (all tasks)accuracy (%): Maze-E 28.3 -> 28.5; Blocks-E 18.8 -> 18.5No clear effect
add scene graph over CoT prompting (ablation)GPT-4o · CoSPlan Error Detection (Maze-E)accuracy (%): 40.3 -> 35.3Hurt
use ground-truth (oracle) scene graph instead of VLM-generated (ablation)SGI on Intern-2 · CoSPlan Maze-E Step Completionaccuracy (%): 43.2 -> 59.0Improved
perturb scene graph object positions (noisy SG) (ablation)SGI on Intern-2 · CoSPlan Blocks-World-E Step Completionaccuracy (%): 29.2 -> 25.4Hurt
increase number of errors in the context (ablation)InternVLM (SG) · Maze-E Step Completionaccuracy (%): 41.2 -> 22.5 (1 -> 7 errors)Hurt
apply SGI to VQA by iterating over MCQ optionsIntern-VLM · Spatial-Map VQAaccuracy (%): 41.3 -> 44.3Improved
apply SGI instead of SG on VQACoG-VLM · Spatial-Map VQAaccuracy (%): 36.7 -> 35.8Hurt
add scene graph over vanilla prompt for open-source VLMs (ablation)Janus-pro-7B · CoSPlan Robo-VQA-E Step Completionaccuracy (%): 14.1 -> 21.3Improved
increase initial context length (more performed steps) (ablation)VLMs on CoSPlan · CoSPlan Step Completionaccuracy (%)Improved

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