Research map / Detection and segmentation / Open-set and few-shot detection
Reasoning-based Spatial Prior (RSP): Learning Spatial Priors from Multimodal LLMs for Object Detection
Cagri Gungor, Qingshuang Chen, Hongda Mao, Chi Zhang, Yelin Kim
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Reasoning-based Spatial Prior (RSP), which transfers spatial priors from multimodal LLM reasoning to a specialized object detector for grounding implicit-intention queries.
Problem
Grounding natural language queries with implicit intentions to precise bounding boxes: MLLMs reason well about which object is meant but struggle to produce precise boxes, while specialized detectors localize well but lack high-level reasoning.
Approach
Learn spatial priors from an MLLM's reasoning and inject them into a specialized detector (e.g., GroundingDINO-style), combining MLLM intention reasoning with detector localization precision. Details beyond the abstract are not stated.
Experimental setup
Baselines: GroundingDINO
Builds on: GroundingDINO
Closest papers by meaning
- Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas (ICML 2025 · similarity 0.90)
- Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models (NeurIPS 2025 · similarity 0.89)
- SIFThinker: Spatially-Aware Image Focus for Visual Reasoning (AAAI 2026 · similarity 0.89)
- SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models (ICLR 2026 · similarity 0.89)
- Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs (CVPR 2024 · similarity 0.89)
- SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models (NeurIPS 2024 · similarity 0.88)
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.
