AI Paper Atlas

Research map / Video / Video generation

Scalable RF Simulation in Generative 4D Worlds

Zhiwei Zheng, Dongyin Hu, Mingmin Zhao

ICML 2026 · Video › Video generation · approach: Text-to-motion diffusion · 0 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
add path masking (ablation)state-aware causal transformer · motion generationFID: 0.747 -> 0.238Improved
add path masking (ablation)state-aware causal transformer · motion generationR-Precision: 0.643 -> 0.755Improved
add spatial state information (ablation)state-aware causal transformer · motion generationmean path error: 0.250 -> 0.151Improved
add spatial state information (ablation)state-aware causal transformer · motion generationmean ending error: 0.460 -> 0.287Improved
use masking rate [0.5, 0.9] instead of [0.1, 0.5] (ablation)path masking · motion generationFID: 0.396 -> 0.238Improved
use masking rate [0.5, 0.9] instead of [0.1, 0.9] (ablation)path masking · motion generationFID: 0.298 -> 0.238Improved
lengthen contiguous masking segment from 5 to 15 points (ablation)path masking · motion generationR-Precision: 0.755 -> 0.776Improved
lengthen contiguous masking segment from 5 to 15 points (ablation)path masking · motion generationmean path error: 0.151 -> 0.228Hurt
pool path tokens into one token (mean) instead of keeping all tokens (ablation)state-aware causal transformer · motion generationmean path error: 0.151 -> 0.201Hurt
add WaveVerse simulated data (4x) to real training dataRF imaging model · RF imagingMAE: 20.10 -> 18.08Improved
add Standard RT simulated data (4x) to real training dataRF imaging model · RF imagingMAE: 20.10 -> 22.28Hurt
add WaveVerse simulated data (19x) to real training dataactivity classifier · human activity recognitionaccuracy: 31.6% -> 71.6%Improved

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