SOURCE-LINKED INTELLIGENCE

MSR: Multiple Subject Reference for Video Generation

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

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 conditioning scheme for LTX-based video generation. Each reference image is independently encoded as a static clip and represented by a separate latent-token group. A compact Fourier-feature multilayer perceptron adds a numeric slot embedding, while slot-dependent temporal offsets modify the group's rotary coordinates. The reference groups are prepended to noisy target tokens and serve as clean contex

Read original source ↗ Open in workspace

recordType

paper

region

Global