Research map / Vision-language and multimodal / Cross-modal learning
MLLM Makes Strong Backbone for Multi-Modal Object Detection
Yifeng Yang, Yutong Li, Jubo Feng, Qinying Gu, Cewu Lu, Guang-Zhong Yang, Xinbing Wang, Nanyang Ye
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 an MLLM-based framework that treats multimodal (RGB-Infrared) object detection as sequence generation, addressing cross-modal fusion and coordinate prediction under cross-entropy supervision.
Problem
Applying multimodal large language models to RGB-Infrared object detection is hard because of visual cross-modal fusion and because coordinate prediction under cross-entropy supervision is poorly suited to localization.
Approach
Casts object detection as sequence generation with an MLLM backbone and proposes mechanisms for RGB-IR fusion and for coordinate prediction beyond plain cross-entropy supervision (specific mechanisms not stated in the available abstract).
Closest papers by meaning
- Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs (ICLR 2026 · similarity 0.88)
- ROD-MLLM: Towards More Reliable Object Detection in Multimodal Large Language Models (CVPR 2025 · similarity 0.88)
- Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models (NeurIPS 2025 · similarity 0.87)
- SSLFusion: Scale and Space Aligned Latent Fusion Model for Multimodal 3D Object Detection (AAAI 2025 · similarity 0.86)
- GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer (ICML 2024 · similarity 0.86)
- Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference (CVPR 2025 · similarity 0.86)
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.
