AI Paper Atlas

Research map / Video / Video generation

UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control

Yan Wu, Korrawe Karunratanakul, Zhengyi Luo, Siyu Tang

ICCV 2025 · Video › Video generation · approach: Text-to-motion diffusion · 16 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 latent action representation (ablation)UniPhys autoregressive denoising with stabilization · Unconditional rolloutmean episode length: 238.2 -> 2320.3Improved
add stabilization trick (ablation)UniPhys autoregressive denoising with latent action · Unconditional rolloutmean episode length: 148.2 -> 2320.3Improved
add stabilization trick (ablation)UniPhys autoregressive denoising with raw actions · Unconditional rolloutmean episode length: 58.0 -> 238.2Improved
use autoregressive instead of full-sequence denoising (ablation)UniPhys · Unconditional rolloutmean episode length: 231.6 -> 2320.3Improved
use autoregressive instead of gradual denoising (ablation)UniPhys · Unconditional rolloutmean episode length: 1817.6 -> 2320.3Improved
use gradual instead of autoregressive denoising (ablation)UniPhys · Unconditional rolloutFPS: 9.5 -> 18.0Improved
use full-sequence instead of gradual denoising (ablation)UniPhys · Unconditional rolloutFPS: 18.0 -> 23.0Improved
increase Monte-Carlo guidance samples from 1 to 5 (ablation)UniPhys loss-guided sampling · Goal reachingsuccess rate: 26% -> 98%Improved
increase Monte-Carlo guidance samples from 1 to 5 (ablation)UniPhys loss-guided sampling · Goal reachingFPS: 9.2 -> 8.7Hurt
use UniPhys instead of MaskedMimictext-driven control · BABEL text controljerk [mm/s^3]: 4.2 -> 1.2Improved
use UniPhys instead of CLoSDtext-driven control · BABEL text controlcorrect caption rate: 61.6% -> 56.3%Hurt
use UniPhys instead of MaskedMimicfar goal reaching · Goal reaching walk-farsuccess rate: 0.0 -> 0.95Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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