AI Paper Atlas

Research map / Video / Video generation

Implicit Preference Alignment for Human Image Animation

Yuanzhi Wang, Xuhua Ren, Jiaxiang Cheng, bing ma, Kai Yu, Tianxiang Zheng, Qinglin Lu, Zhen Cui

ICML 2026 · Video › Video generation · approach: Text-to-motion diffusion · 0 citations (OpenAlex)

Read the paper

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
Align VACE-14B with IPA on self-generated good samples (ablation)VACE-14B · TikTokFVD: 427 -> 288Improved
Add IPA to VACE-14B on the hand-dynamics benchmark (ablation)VACE-14B · Hand-dynamics benchmarkFID-VID: 12.5 -> 8.1Improved
Add Hand-Aware Local Optimization on top of IPA (ablation)IPA · TikTokFID-VID: 7.9 -> 5.9Improved
Add Hand-Aware Local Optimization on top of IPA (ablation)IPA · Hand-dynamics benchmarkSSIM: 0.741 -> 0.757Improved
Use small beta (200) in the implicit-reward loss (ablation)IPA · TikTok and hand benchmarkFID-VID, FVD, SSIM, PSNRHurt
Use large beta (above 600) in the implicit-reward loss (ablation)IPA · TikTok and hand benchmarkFID-VID, FVD, SSIM, PSNRHurt
Raise hand weighting lambda from 0.1 to 10 (ablation)IPA with HALO · TikTokFID-VID: 7.4 -> 5.9Improved
Raise hand weighting lambda from 10 to 100 (ablation)IPA with HALO · TikTokFID-VID: 5.9 -> 6.8Hurt
Use IPA-aligned VACE-14B instead of Wan-AnimateIPA · TikTokFVD: 316 -> 255Improved
Use IPA-aligned VACE-14B instead of Wan-Animate on hand regionsIPA · Hand regionsPSNR-Hand: 14.1 -> 18.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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