arXiv:2608.22819v1 Announce Type: new Abstract: Text-conditioned image-to-video (I2V) generation has advanced rapidly, yet generating videos with multiple subjects remains challenging. A model must s...
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:2610.10400v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have made significant progress in visual understanding and generation. However, generating interleaved image--...
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: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...
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 SMART, a Self‑evolving Multi‑Agent Refinement Framework for conversational text‑to‑motion generation. It enables users to iteratively refine specific spatio‑temporal regions of a motion sequence based on natural language feedback, preserving the rest of the motion. The framework incorporates a semantic‑guided masked editing mechanism and a memory‑based self‑evolving strategy to reuse past editing knowledge and reduce redundant exploration.
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: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...
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.
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...