AI Paper Atlas

Research map / Video / Video generation

LibraGen: Playing a Balance Game in Subject-Driven Video Generation

Jiahao Zhu, Shanshan Lao, Lijie Liu, Gen Li, Tianhao Qi, hanwei hanwei, Bingchuan Li, FangfangLiu FangfangLiu, Zhuowei Chen, Tianxiang Ma, Qian HE, Yi Zhou and 1 more

ECCV 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 2 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
merge in-pair LoRA at 0.15 (ablation)cross-pair SFT baseline · In-house S2V benchmark (cumulative strategy ablation)GSB ratio: GSB 0.190Improved
merge in-pair LoRA at 0.15 (ablation)cross-pair SFT baseline · In-house S2V benchmark (cumulative strategy ablation)VQ: 2.794 -> 2.708Hurt
merge in-pair LoRA at 0.15 (ablation)cross-pair SFT baseline · In-house S2V benchmark (cumulative strategy ablation)AES: 0.6420 -> 0.6306Hurt
add Consis-DPO LoRA (0.5) (ablation)SFT + in-pair merge · In-house S2V benchmark (cumulative strategy ablation)GSB ratio: GSB 0.286Improved
add Consis-DPO LoRA (0.5) (ablation)SFT + in-pair merge · In-house S2V benchmark (cumulative strategy ablation)TA: 3.466 -> 3.490Improved
add Real-Fake DPO LoRA (0.1) (ablation)SFT + Consis-DPO · In-house S2V benchmark (cumulative strategy ablation)VQ: 2.714 -> 2.756Improved
add Real-Fake DPO LoRA (0.1) (ablation)SFT + Consis-DPO · In-house S2V benchmark (cumulative strategy ablation)AES: 0.6334 -> 0.6394Improved
add Real-Fake DPO LoRA (0.1) (ablation)SFT + Consis-DPO · In-house S2V benchmark (cumulative strategy ablation)GSB ratio: GSB 0.025No clear effect
add time-dependent dynamic CFG (ablation)SFT + both DPO LoRAs · In-house S2V benchmark (cumulative strategy ablation)TA: 3.524 -> 3.594Improved
add time-dependent dynamic CFG (ablation)SFT + both DPO LoRAs · In-house S2V benchmark (cumulative strategy ablation)AES: 0.6394 -> 0.6496Improved
replace MAGREF with LibraGen on subject consistencyLibraGen · In-house S2V benchmark (200 cases)GSB ratio (4 reference images): 0.700Improved
replace Kling O1 with LibraGen on subject consistencyLibraGen · In-house S2V benchmark (200 cases)GSB ratio (1 reference image): 0.077Improved

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