AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Attention to Threat-Relevant Objects: Reasoning Detection in Autonomous Driving via Multimodal Large Language Models

Yulin He, Wei Chen, Xinbiao Gan, Siqi Wang, Haotian Wang, Yusong Tan

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces threat-oriented reasoning detection for autonomous driving, localizing threat objects and reasoning about their threat levels from a driver-centric perspective using multimodal LLMs.

Problem

Traditional autonomous driving detection is class-based and does not identify which objects pose real potential risk to the driver; the paper targets localizing threat objects and reasoning about their threat levels.

Approach

Shifts from class-based detection to threat-oriented reasoning detection, framing it as a task solved with multimodal large language models from a driver-centric perspective.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add ThreatCoT (image-level + object-level reasoning with expert toolchain) (ablation)Qwen2.5VL-7B · Threat-ReasonDetMean CRecall: 54.7 -> 59.1Improved
add ThreatCoT (ablation)InternVL3-8B · Threat-ReasonDetMean CRecall: 63.5 -> 66.5Improved
add ThreatCoT (ablation)InternVL3-8B · Threat-ReasonDetMean L1: 0.84 -> 0.69Improved
add image-level information only to ThreatCoT (ablation)InternVL3-8B · Threat-ReasonDetM-CRecall / M-L1: 63.5 -> 62.8 recall; 0.84 -> 0.80 L1Mixed
add object-level cues (class, depth) on top of image-level info (ablation)InternVL3-8B · Threat-ReasonDetM-CRecall: 62.8 -> 66.5Improved
add format reward (ablation)VisionReasoner-7B (GRPO) · Threat-ReasonDetM-CRecall: 53.9 -> 58.3Improved
add non-repeat reward on top of format reward (ablation)VisionReasoner-7B (GRPO) · Threat-ReasonDetM-CRecall: 58.3 -> 51.8Hurt
add prediction number reward on top of format + non-repeat (ablation)VisionReasoner-7B (GRPO) · Threat-ReasonDetM-CRecall: 51.8 -> 63.6Improved
add prediction number reward (ablation)VisionReasoner-7B (GRPO) · Threat-ReasonDetM-L1: 1.06 -> 0.78Improved
ThreatReasoner (GRPO) vs VisionReasonerend-to-end MLLM · Threat-ReasonDetMean CRecall: 53.9 -> 63.6Improved

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