RaRe：用 MLLM 思维链推理改进开放词汇场景图生成

技术上 RaRe 分两步：先通过自监督对比学习把推理嵌入与文本化的关系描述对齐，再用面向具体性的强化学习目标优化推理生成，促使模型产出与目标物体对绑定的语义证据，提升关系间可区分性。在 VG150 和 PSG 两个基准上，RaRe 在类别均衡识别指标上超过现有基线，但作者也明确指出增益随数据集与候选框设置不同而有所波动。

Reasoning-Aware Relational Representation Learning for Open-Vocabulary Scene Graph Generation

Open-Vocabulary Scene Graph Generation (OV-SGG) requires models to recognize visual relationships beyond the training vocabulary, yet existing methods often rely on dataset-specific object--predicate co-occurrence patterns. Under long-tailed distributions and noisy object localization, such reliance leads to biased, entangled relation representations, limiting both rare-relation recognition and generalization to unseen predicates. To address these challenges, we propose RaRe, a reasoning-aware relational representation learning framework that transforms MLLM-generated chain-of-thought (CoT) rationales into structured relation embeddings. Rather than using CoT only as an intermediate reasoning trace for final prediction, RaRe directly optimizes the rationale-derived representation space to improve inter-relation discriminability. Specifically, RaRe first aligns rationale embeddings with textualized relation descriptions through self-supervised contrastive learning, and then refines rationale generation with a specificity-oriented reinforcement learning objective that encourages semantically object-pair-specific relational evidence. Experiments on VG150 and PSG demonstrate improved category-balanced recognition over existing baselines, while the additional gains from learning vary across datasets and proposal settings. Code available at: https://artanic30.github.io/project_pages/RaRe.

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：RaRe、MLLM、场景图生成、对比学习，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Jiawei Xiao, Boya Wang, Longtian Qiu, Shan Ning, Xuming He），经 AITOP 多维评分管线结构化提炼。