AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving

Finn Rasmus Schäfer, Yuan Gao, Dingrui Wang, Thomas Stauner, Stephan Günnemann, Mattia Piccinini, Sebastian Schmidt, Johannes Betz

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 1 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
provide explicit ego-motion trajectory text (Summary) instead of vision onlyQwen3-VL-8B · EgoDyn-Benchbalanced accuracy: 38.9 -> 59.6Improved
add visual frames to text-only trajectory input under best encoding (ablation)Qwen3-VL-8B · EgoDyn-Benchbalanced accuracy: +2.6ppNo clear effect
add Timeseries kinematic encoding instead of Summary (ablation)Qwen3-VL-8B · EgoDyn-Bench trajectory encodingbalanced accuracy: 54.7 -> 62.2Improved
use Coordinates encoding instead of Summary (ablation)Qwen3-VL-8B · EgoDyn-Bench trajectory encodingbalanced accuracy: 54.7 -> 46.6Hurt
use Full (Timeseries + Coordinates) encoding instead of Summary (ablation)Qwen3-VL-8B · EgoDyn-Bench trajectory encodingbalanced accuracy: 54.7 -> 61.3Improved
add a single static visual frame to no-visual input (ablation)Qwen3-VL-8B · EgoDyn-Bench vision-onlyWPCR: 20.0 -> 97.4Improved
add multiple temporally ordered frames beyond a single static frame (ablation)Qwen3-VL-8B · EgoDyn-Bench vision-onlybalanced accuracy: 39.0 (shuffled) vs 38.9 (ordered)No clear effect
increase temporal resolution to 10 FPS (ablation)Qwen3-VL · EgoDyn-Bench vision-onlybalanced accuracy: +0.4ppNo clear effect
scale up to closed-source model (gemini-3-pro-preview) from best open 8B modelvision-only VLMs · EgoDyn-Bench vision-onlybalanced accuracy: 39.9 -> 47.0No clear effect
use domain-specific driving VLA instead of general open-source VLM of similar sizeRoboTron-Drive · EgoDyn-Bench vision-onlybalanced accuracy: 38.6 (RoboTron-Drive) vs 38.9 (Qwen3-VL-8B)No clear effect
use Visual Odometry geometric baseline instead of VLMsGPT-5.1 · EgoDyn-Bench vision-only (subset)balanced accuracy: 55.1 -> 63.8Improved
evaluate on real, simulated or style-transferred domain (ablation)Qwen3-VL-8B · EgoDyn-Bench domain gapbalanced accuracy: 40.0 / 39.7 / 41.0No clear effect

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