arXiv Computer Vision October 16, 2026 By Han Su, Meng Tian, Tianyu Huang, Mingyu Gao, Lennox Wei, Dongxu Li, Jianhua Han, Hang Xu, Xiaohe Wu, Wangmeng Zuo

DK-VLM: Geometry as Position for Spatial Reasoning in Vision-Language Models

Read the original on arXiv Computer Vision →

DK‑VLM introduces Dual‑Kernel Attention, where a visual token’s attention is computed from both its input position and its geometric position derived from 3D points and camera poses. A semantic kernel preserves pretrained attention while a geometric kernel modulates attention via point displacements and relative view transformations, with a learned gate fusing the two. The model also employs Reference‑Frame Composition supervision to update its reference frame across successive judgments, achieving top scores on six spatial benchmarks and strong performance on VSI‑Bench and ReVSI‑32.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Jun 12

GeoWorld-VLM: Geometry from World Models for Vision-Language Models

arXiv:2605. 16713v2 Announce Type: replace-cross Abstract: Modern Vision-Language Models (VLMs) achieve strong semantic recognition, yet remain brittle on elementary spatial relations such as left of, on, behind, and between.

By Renjie Gu, Kaichen Zhou, Yan Luo, Mengyu Wang

llms efficiency multimodal benchmarks safety

arXiv Computer Vision

Sep 30

LeRF: Learning Reference Coordinate Frames for Perspective Taking Reasoning

arXiv:2609.36219v1 Announce Type: new Abstract: Perspective taking is a fundamental component of spatial intelligence, requiring models interpret spatial relations from a specified viewpoint, such as...

By Bang Xiao, Wenqi Jia, Ozgur Kara, Tiancheng Shen, Yibo Yang, Bolin Lai, Junho Kim, James Matthew Rehg

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

5d ago

GeoReader: Learning Latent Geometry for Spatial Reasoning in Vision-Language Models

arXiv:2610.18694v1 Announce Type: cross Abstract: Vision-language models (VLMs) struggle with metric and multi-view relationships that remain implicit in RGB observations. Geometry foundation models...

By Rong Li, Shijie Li, Jiangyong Huang, Lingdong Kong, Jiaming Zhou, Dongyue Lu, Zeying Gong, Baoxiong Jia, Junwei Liang, Siyuan Huang

llms nlp fine-tuning multimodal benchmarks safety

arXiv Computation and Language

Sep 30

Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering

arXiv:2609.38177v1 Announce Type: cross Abstract: Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs...

By Jaewoo Jung, Hyeonseo Yu, Honggyu An, Jisang Han, Mungyeom Kim, Minkyeong Jeon, Heeseong Shin, Wonjun Moon, Federico Tombari, Daniel Barath, Marc Pollefeys, Seungryong Kim, Sunghwan Hong

llms multimodal benchmarks

arXiv Machine Learning

Sep 10

Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models

arXiv:2609.06880v1 Announce Type: cross Abstract: Reasoning over language instructions in embodied tasks such as robotics often requires understanding spatial relations from a speaker's situated pers...

By Mimo Shirasaka, Haochen Zhang, Yonatan Bisk

llms robotics multimodal benchmarks

arXiv Computer Vision

Sep 30

Spatial-OPSD: Self-Improving Spatial Reasoning via Label-Free Self-Distillation

Spatial-OPSD is a label‑free self‑improvement framework for vision‑language models that leverages spatial priors such as depth, 3D relations, and camera geometry to provide dense token‑level supervision. During training, a privileged teacher uses these priors while the student learns from only the original visual‑language input, and a recursive round‑wise scheme allows repeated self‑improvement without moving the teacher. Across four VLM families, one round of Spatial‑OPSD improves the five‑benchmark average, and three rounds push a strong spatially specialized model to the open‑source frontier, achieving the highest average among open models and best results on three of five spatial reasoning benchmarks.

By Zhenyu Liu, Zhangquan Chen, Keyi Chen, Mingze Sun, Xiang An, Haodong Jing, Ruqi Huang

llms robotics efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

GeoWorld-VLM: Geometry from World Models for Vision-Language Models

LeRF: Learning Reference Coordinate Frames for Perspective Taking Reasoning

GeoReader: Learning Latent Geometry for Spatial Reasoning in Vision-Language Models

Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering

Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models

Spatial-OPSD: Self-Improving Spatial Reasoning via Label-Free Self-Distillation