# 3D-VCD：通过视觉对比解码缓解3D具身智能体中的幻觉

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-04-09 08:00
- AIHOT 链接：https://aihot.virxact.com/items/cmod736np00f8sl4eun0knf6s
- 原文链接：https://arxiv.org/abs/2604.08645

## AI 摘要

本文提出首个面向3D具身智能体的推理时视觉对比解码框架3D-VCD，用于缓解多模态大模型在三维环境中的幻觉问题。该方法通过对物体类别、空间坐标及几何范围施加语义与几何扰动构建扭曲的3D场景图，通过对比原始与扭曲场景的预测差异，抑制受语言先验驱动而非场景证据支持的不可靠token。在3D-POPE和HEAL基准测试中，该方法无需重新训练即显著提升了具身智能体的基础推理能力。

## 正文

Large multimodal models are increasingly used as the reasoning core of embodied agents operating in 3D environments, yet they remain prone to hallucinations that can produce unsafe and ungrounded decisions. Existing inference-time hallucination mitigation methods largely target 2D vision-language settings and do not transfer to embodied 3D reasoning, where failures arise from object presence, spatial layout, and geometric grounding rather than pixel-level inconsistencies. We introduce 3D-VCD, the first inference-time visual contrastive decoding framework for hallucination mitigation in 3D embodied agents. 3D-VCD constructs a distorted 3D scene graph by applying semantic and geometric perturbations to object-centric representations, such as category substitutions and coordinate or extent corruption. By contrasting predictions under the original and distorted 3D contexts, our method suppresses tokens that are insensitive to grounded scene evidence and are therefore likely driven by language priors. We evaluate 3D-VCD on the 3D-POPE and HEAL benchmarks and show that it consistently improves grounded reasoning without any retraining, establishing inference-time contrastive decoding over structured 3D representations as an effective and practical route to more reliable embodied intelligence.