arXiv Computer Vision September 2, 2026 By Kaizhen Tan, Yang Feng, Heqing Du, Siru Tao, Xin Xu, Hanzhe Hong

Teaching Vision-Language Models to Use the Scale They Are Given: Label-Free Equivariance Training for Metric Physical Reasoning

Read the original on arXiv Computer Vision →

The paper introduces EquiSD, a label‑free training method that exploits scale equivariance to improve metric grounding in vision‑language models. By projecting model predictions onto a scale‑equivariant family and fine‑tuning on the resulting targets, EquiSD boosts a 3B model’s median response slope from 0.66 to 0.94 and raises mean relative accuracy by 9.2 points across simulated scales, with positive transfer to real QuantiPhy videos.

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.

Hugging Face Trending Papers

Sep 1

Teaching Vision-Language Models to Use the Scale They Are Given: Label-Free Equivariance Training for Metric Physical Reasoning

Metric questions about video require vision-language models to use supplied real-world references to convert visual measurements into physical units. Yet we find that current models use this scale inf...

llms fine-tuning multimodal

arXiv AI

Oct 21

On the Limits of Scale: Inverse Scaling in Vision-Language Models

arXiv:2610.27360v1 Announce Type: cross Abstract: Scaling laws suggest that increasing model size, training data, and compute generally yields monotonic performance improvements. While this often hol...

By Rohit Saxena, Alessandro Suglia, Marek Rei, Pasquale Minervini

llms multimodal benchmarks

arXiv AI

Jun 16

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

arXiv:2606. 15134v1 Announce Type: cross Abstract: Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched.

By Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja

llms rag efficiency multimodal benchmarks

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 23

Metric-Bench: Exploring In-context Spatial Metric Reasoning in VLMs for Indoor Scenes

Metric-Bench introduces a new benchmark for Vision‑Language Models (VLMs) that focuses on metric‑spatial reasoning in indoor scenes by using in‑image reference objects with known dimensions. The accompanying MetricReasoner fine‑tuning recipe employs structured prompts and numerical rewards to implicitly learn 2D‑to‑3D mapping without camera intrinsics. Experiments show that this approach improves spatial metric understanding by 43.1 % over existing models and boosts downstream embodied tasks, while also delivering gains on general VLM benchmarks.

By Yuling Xi, Haokai Zhang, Muzhi Zhu, Hao Zhong, Zongze Du, Hengyu Zhao, Chenchen Jing, Yufei Yin, Bin Qin, Yongjie Yang, Zhenbo Luo, Hao Chen, Chunhua Shen

llms agents robotics fine-tuning multimodal benchmarks

arXiv AI

Oct 2

Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes

arXiv:2610.02117v1 Announce Type: cross Abstract: On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a froze...

By Sophia Sirko-Galouchenko, Monika Wysoczanska, Andrei Bursuc, Nicolas Thome, Spyros Gidaris

llms efficiency multimodal benchmarks

One email a morning, machine-written

Related stories

Teaching Vision-Language Models to Use the Scale They Are Given: Label-Free Equivariance Training for Metric Physical Reasoning

On the Limits of Scale: Inverse Scaling in Vision-Language Models

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

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

Metric-Bench: Exploring In-context Spatial Metric Reasoning in VLMs for Indoor Scenes

Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes