Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models episode artwork

EPISODE · Dec 26, 2025 · 22 MIN

Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models

from Daily Paper Cast · host Jingwen Liang, Gengyu Wang

🤗 Upvotes: 42 | cs.CV Authors: Shengchao Zhou, Yuxin Chen, Yuying Ge, Wei Huang, Jiehong Lin, Ying Shan, Xiaojuan Qi Title: Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models Arxiv: http://arxiv.org/abs/2512.20557v1 Abstract: Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relationship in 3D space over time, largely due to the scarcity of scalable 4D-aware training resources. To bridge this gap across aspects of dataset, benchmark and model, we introduce DSR Suite. First, we propose an automated pipeline that generates multiple-choice question-answer pairs from in-the-wild videos for DSR. By leveraging modern vision foundation models, the pipeline extracts rich geometric and motion information, including camera poses, local point clouds, object masks, orientations, and 3D trajectories. These geometric cues enable the construction of DSR-Train for learning and further human-refined DSR-Bench for evaluation. Compared with previous works, our data emphasize (i) in-the-wild video sources, (ii) object- and scene-level 3D requirements, (iii) viewpoint transformations, (iv) multi-object interactions, and (v) fine-grained, procedural answers. Beyond data, we propose a lightweight Geometry Selection Module (GSM) to seamlessly integrate geometric priors into VLMs, which condenses question semantics and extracts question-relevant knowledge from pretrained 4D reconstruction priors into a compact set of geometry tokens. This targeted extraction avoids overwhelming the model with irrelevant knowledge. Experiments show that integrating DSR-Train and GSM into Qwen2.5-VL-7B significantly enhances its dynamic spatial reasoning capability, while maintaining accuracy on general video understanding benchmarks.

Episode metadata supplied by the publisher feed · Published Dec 26, 2025

🤗 Upvotes: 42 | cs.CV Authors: Shengchao Zhou, Yuxin Chen, Yuying Ge, Wei Huang, Jiehong Lin, Ying Shan, Xiaojuan Qi Title: Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models Arxiv: http://arxiv.org/abs/2512.20557v1 Abstract: Vision-language models (VLM) excel at general understanding yet remain weak at dynamic spatial reasoning (DSR), i.e., reasoning about the evolvement of object geometry and relationship in 3D space over time, largely due to the scarcity of scalable 4D-aware training resources. To bridge this gap across aspects of dataset, benchmark and model, we introduce DSR Suite. First, we propose an automated pipeline that generates multiple-choice question-answer pairs from in-the-wild videos for DSR. By leveraging modern vision foundation models, the pipeline extracts rich geometric and motion information, including camera poses, local point clouds, object masks, orientations, and 3D trajectories. These geometric cues enable the construction of DSR-Train for learning and further human-refined DSR-Bench for evaluation. Compared with previous works, our data emphasize (i) in-the-wild video sources, (ii) object- and scene-level 3D requirements, (iii) viewpoint transformations, (iv) multi-object interactions, and (v) fine-grained, procedural answers. Beyond data, we propose a lightweight Geometry Selection Module (GSM) to seamlessly integrate geometric priors into VLMs, which condenses question semantics and extracts question-relevant knowledge from pretrained 4D reconstruction priors into a compact set of geometry tokens. This targeted extraction avoids overwhelming the model with irrelevant knowledge. Experiments show that integrating DSR-Train and GSM into Qwen2.5-VL-7B significantly enhances its dynamic spatial reasoning capability, while maintaining accuracy on general video understanding benchmarks.

PodParley-generated summary based on available episode metadata and transcript content.

NOW PLAYING

Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models

0:00 22:56

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of Daily Paper Cast?

This episode is 22 minutes long.

When was this Daily Paper Cast episode published?

This episode was published on December 26, 2025.

What is this episode about?

🤗 Upvotes: 42 | cs.CV Authors: Shengchao Zhou, Yuxin Chen, Yuying Ge, Wei Huang, Jiehong Lin, Ying Shan, Xiaojuan Qi Title: Learning to Reason in 4D: Dynamic Spatial Understanding for...

Can I download this Daily Paper Cast episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!