Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Improving Allocentric Spatial Reasoning of VLMs via Perspective-conditional Prompt-based Contrastive Decoding

AbstractVision-Language models (VLMs) have demonstrated impressive capabilities across diverse domains, yet they fail significantly in allocentric spatial reasoning, which requires perspective-taking from object-centric viewpoints rather than the camera’s perspective. This capability is essential for real-world applications including robotics, autonomous driving, and embodied AI. In this work, we identify this limitation as a prevalent camera viewpoint bias and propose Perspective-Conditional Prompt-based Contrastive Decoding (PCD), a training-free method that leverages VLMs’ capabilities while exploiting this performance gap. By contrasting responses to allocentric versus egocentric framings of identical spatial configurations, PCD explicitly suppresses camera viewpoint bias without requiring fine-tuning or external foundation models. Evaluating on allocentric benchmarks including 3DSRBench, OmniSpatial, ViewSpatial-Bench, and SpatialMQA, we demonstrate that PCD improves accuracy by up to 32.3 points on Qwen2.5-VL-7B, with consistent gains observed on recent, larger-scale VLMs. Our approach offers substantial computational advantages, achieving 8.65× faster inference and a 37.4% memory reduction compared to multi-model pipeline framework.

More from EMNLP 2026

All EMNLP 2026 papers →