AI Paper Atlas

Research map / Video / Video generation

LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion

Yisu Zhang, Chenjie Cao, Chaohui Yu, Jianke Zhu

ICCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 3 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 scaling token for camera/motion amplitude (ablation)LiON-LoRA · Camera and motion strength controllinear controllabilityImproved
add scaling token for motion strength instead of adapter scale (ablation)LiON-LoRA · Motion strength (Pearson correlation with optical flow)Pearson correlationImproved
add layer-wise norm normalization of LoRA outputs (ablation)LiON-LoRA fusion · Camera LoRA fusion (forward + orbit left)fusion smoothnessImproved
increase training set from 100 to 7k samples at 4k iterations (ablation)LiON-LoRA · Orbit left camera controlRotErr: 0.802 -> 1.227Hurt
increase training set from 100 to 7k samples at 4k iterations (ablation)LiON-LoRA · Orbit left camera controlFVD: 175.3 -> 232.5Hurt
train 10k instead of 4k iterations with 100 samples (ablation)LiON-LoRA · Orbit left camera controlRotErr: 0.802 -> 0.710Improved
train 10k instead of 4k iterations with 100 samples (ablation)LiON-LoRA · Orbit left camera controlFVD: 175.3 -> 184.6Hurt
train 10k instead of 4k iterations with 7k samples (ablation)LiON-LoRA · Orbit left camera controlRotErr: 1.227 -> 0.896Improved
LiON-LoRA vs DimensionX-S* on basic camera posesCogVideoX · DL3DV basic camera posesFVD: 193.3 -> 136.0Improved
LiON-LoRA vs CamI2V on complex fused posesCogVideoX · DL3DV complex fused camera posesRotErr: 0.924 -> 1.044Hurt

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