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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Qwen2.5-VL MLLM conditioning to T5-only (ablation) | T5-only DiT · OpenS2V-Eval | Total Score: 55.16% -> 57.61% | Improved |
| add Qwen2.5-VL MLLM conditioning to T5-only (ablation) | T5-only DiT · OpenS2V-Eval | MotionAmplitude: 7.48% -> 13.91% | Improved |
| add Qwen2.5-VL MLLM conditioning to T5-only (ablation) | T5-only DiT · OpenS2V-Eval | GmeScore: 62.26% -> 67.79% | Improved |
| add Qwen2.5-VL MLLM conditioning to T5-only (ablation) | T5-only DiT · OpenS2V-Eval | Aesthetics: 42.80% -> 45.55% | Improved |
| add Qwen2.5-VL MLLM conditioning to T5-only (ablation) | T5-only DiT · OpenS2V-Eval | NexusScore: 45.79% -> 46.84% | Improved |
| add T5 text encoder to MLLM-only conditioning (ablation) | MLLM + MLP + DiT · training stability | convergence | Improved |
Closest papers by meaning
- DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation (CVPR 2025 · similarity 0.89)
- Bernini: Latent Semantic Planning for Video Diffusion (NeurIPS 2026 · similarity 0.88)
- T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation (CVPR 2025 · similarity 0.87)
- DuoGen: Towards Autonomous Interleaved Multimodal Generation (CVPR 2026 · similarity 0.87)
- MVBench: A Comprehensive Multi-modal Video Understanding Benchmark (CVPR 2024 · similarity 0.87)
- PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation (CVPR 2025 · similarity 0.86)
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.
