AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

VLM4D: Towards Spatiotemporal Awareness in Vision Language Models

Shijie Zhou, Alexander Vilesov, Xuehai He, Ziyu Wan, Shuwang Zhang, Aditya Nagachandra, Di Chang, Dongdong Chen, Xin Eric Wang, Achuta Kadambi

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 35 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
supervised fine-tuning on real VLM4D training split (ablation)Qwen2-VL-7B · VLM4D real test splitaccuracy: 38.3 -> 54.5Improved
supervised fine-tuning on real VLM4D training split (ablation)Qwen2.5-VL-7B · VLM4D real test splitaccuracy: 43.4 -> 55.6Improved
add synthetic data to real data for SFT (ablation)Qwen2.5-VL-7B · VLM4D real test splitaccuracy: 55.6 -> 56.3No clear effect
add synthetic data to real data for SFT (ablation)Qwen2-VL-7B · VLM4D real test splitaccuracy: 54.5 -> 55.5No clear effect
fine-tune on synthetic data only (ablation)Qwen2-VL-7B · VLM4D real test splitaccuracy: 38.3 -> 42.5Improved
use reconstructed 4D global feature field as inputInternVideo2-8B · VLM4D DAVIS 2016 (Direct Output)accuracy: 24.3 -> 29.0Improved
use reconstructed 4D global feature field as inputInternVideo2-8B · VLM4D DAVIS 2016 (CoT)accuracy: 36.0 -> 37.4Improved
use rendered global-view video instead of original 2D video (ablation)InternVideo2-8B · VLM4D DAVIS 2016 (CoT)accuracy: 36.0 -> 32.7Hurt
chain-of-thought prompting instead of direct output (ablation)evaluated VLMs · VLM4DaccuracyNo clear effect
dense captions in video SFT datasets contain spatiotemporal termsShareGPT4Video · manual check of 100 labelslabel accuracy: less than 10%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy