AI Paper Atlas

Research map / Video / Video generation

BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration

Zhaoyang Li, Dongjun Qian, Kai Su, qishuai diao, Xiangyang Xia, Chang Liu, Wenfei Yang, Tianzhu Zhang, Zehuan Yuan

ICLR 2026 · Video › Video generation · approach: Efficient video diffusion models · 17 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 Qwen2.5-VL MLLM conditioning to T5-only (ablation)T5-only DiT · OpenS2V-EvalTotal Score: 55.16% -> 57.61%Improved
add Qwen2.5-VL MLLM conditioning to T5-only (ablation)T5-only DiT · OpenS2V-EvalMotionAmplitude: 7.48% -> 13.91%Improved
add Qwen2.5-VL MLLM conditioning to T5-only (ablation)T5-only DiT · OpenS2V-EvalGmeScore: 62.26% -> 67.79%Improved
add Qwen2.5-VL MLLM conditioning to T5-only (ablation)T5-only DiT · OpenS2V-EvalAesthetics: 42.80% -> 45.55%Improved
add Qwen2.5-VL MLLM conditioning to T5-only (ablation)T5-only DiT · OpenS2V-EvalNexusScore: 45.79% -> 46.84%Improved
add T5 text encoder to MLLM-only conditioning (ablation)MLLM + MLP + DiT · training stabilityconvergenceImproved

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