Text-conditioned image-to-video (I2V) generation has advanced rapidly, yet generating videos with multiple subjects remains challenging. A model must simultaneously preserve the appearance of each sub...
arXiv:2606. 13768v1 Announce Type: cross Abstract: Cinematic video depicts multiple subjects acting or interacting at specific moments, captured with deliberate camera movement, and stitched together by shot transitions.
arXiv:2607. 06481v1 Announce Type: cross Abstract: We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning.
arXiv:2610.22744v1 Announce Type: new Abstract: Creative intent in video editing can be expressed through text instructions (e.g., "remove the people"), image references (e.g., subject appearance), v...
arXiv:2608.05648v2 Announce Type: replace Abstract: Video identity replacement seeks to transfer the identities of one or more subjects while preserving the motion, expressions, and temporal structur...
arXiv:2610.10400v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made significant progress in visual understanding and generation. However, generating interleaved image--...
arXiv:2609.18393v1 Announce Type: new Abstract: Conditioning a video generator on multiple images requires preserving appearance while associating each reference with its intended role. We present MS...
arXiv:2609.15863v1 Announce Type: new Abstract: Video diffusion models are stochastic and hard to control: precise content often requires repeated sampling without guaranteed success, and long-horizo...
The paper introduces Factor-Aware Predictive Learning (FAPL) to improve cinematic video generation by effectively leveraging multimodal large language model (MLLM) latents. FAPL trains a Video Diffusion Transformer (DiT) in three stages: grounding the DiT with frozen MLLM latents, enforcing factor-aware control through factor-span replacement, and optimizing temporal inference with limited-input representations while preserving full-observation reconstruction. Experiments show that FAPL outperforms baselines on sparse-to-video, factor-aware editing, and multi-shot generation tasks, demonstrating enhanced MLLM feature use, temporal control, and factor coordination.
arXiv:2609.37407v1 Announce Type: new Abstract: While recent video foundation models excel at generating high-quality short videos, long-form video generation remains a critical challenge, where a ma...
arXiv:2603.15614v2 Announce Type: replace Abstract: Recent video diffusion models achieve strong visual quality and temporal coherence, but still lack coordinated control over scene layout, customize...
Conditioning a video generator on multiple images requires preserving appearance while associating each reference with its intended role. We present MSR (Multiple Subject Reference), a slot-aware cond...