Harnessing Intrinsic Subject-Aware Attention for Controllable Multi-Subject Video Generation — Paper

Abstract

Multi-subject video generation faces two key challenges: uncontrollable fidelity strength and potential semantic drift. We address these by analyzing the internal mechanisms of Diffusion Transformers (DiTs). We found that certain attention blocks naturally form an Intrinsic Spatial Grounding Map (ISGM) that precisely locates reference subjects. Building on this insight, we propose Dual-phase Intrinsic Attention Leveraging (DIAL), a framework that uses these internal signals for both training and inference. In low-noise stages, we use ISGM to guide the attention mechanism, allowing precise control over fidelity strength during inference without retraining. In high-noise stages, we use these same maps to automatically build preference pairs at no additional cost for Reinforcement Learning (RL). This RL procedure effectively anchors the model's attention to reference subjects and mitigates semantic drift. Extensive experiments show that DIAL significantly outperforms baseline models on the OpenS2V-Eval benchmark, consistently improving identity consistency and enabling controllable fidelity strength.

Authors 8

Niange Yu, Ye Tian, Biaolong Chen, Miao Lu, Aixi Zhang, Hao Jiang, Yunhai Tong, Pipei Huang

Specification

Official page: arxiv.org/abs/2609.11507
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
Arxiv announce type: new
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
arXiv id: 2609.11507
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
Categories: cs.CV
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
PDF: arxiv.org/pdf/2609.11507
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
Primary category: cs.CV
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 4 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

4 h ago

Conflicts

None

No models linked to this paper yet.

Authors: Niange Yu, Ye Tian, Biaolong Chen

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Published

1 claims · 1 propertiesShow all properties

Publishedpublished_at1

Claim history for Published
Value	Valid from → to	Status	Source	Confidence	Extractor
11 Sept 2026	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New paperPaperHarnessing Intrinsic Subject-Aware Attention for Controllable Multi-Subject Video Generation
New paper: Harnessing Intrinsic Subject-Aware Attention for Controllable Multi-Subject Video Generation
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.CV	feed	T1· Official	2 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.