paper-with-me

홈 › Papers

TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation

2026-05-29 · Ruotong Liao, Guowen Huang, Qing Cheng, Guangyao Zhai, Lei Zhang, Xun Xiao, Thomas Seidl, Daniel Cremers, Volker Tresp arxiv

Text-to-video (T2V) generation faces challenging questions when generating videos with long horizons containing multiple events. Inspired by the intrinsics of the diffusion process, we probe video diffusion transformers (DiTs) and uncover intrinsic turning points in the DiT denoising trajectory where conditioning text affects generation from global layout to fine-grained details. Building on this finding, we present TunerDiT, a simple yet effective progressive steering method that requires no additional training for multi-event generation. TunerDiT comprises two steering handles: (1) Event-Partitioned Masking that enforces event boundaries while allowing cross-event transition bands; (2) Cross-Event Prompt Fusion that injects neighboring event semantics for late-stage refinement. We contribute a self-curated prompt suite for benchmarking multi-event generation, i.e., Meve. TunerDiT achieves state-of-the-art performance across 8 metrics and offers a tunable trade-off between video consistency and event separation, compared with other training-free methods. The improvement in text alignment increases with the event count, indicating a scaling possibility with increasing event count.

📄 PDF Abstract BibTeX arXiv:2605.31590

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers

2026-05-28 · Zihao Xue, Yan Wang, Zhen Bi, Long Ma 외 arxiv

Diffusion Transformers have become a powerful backbone for text-to-image generation, but their layered and cross-modal generation process makes safety control fundamentally different from prompt-level filtering or output…

Text-to-Image Generation

A General Framework for Inference-time Scaling and Steering of Diffusion Models

2025-01-12 · Raghav Singhal, Zachary Horvitz, Ryan Teehan, Mengye Ren 외

Diffusion models produce impressive results in modalities ranging from images and video to protein design and text. However, generating samples with user-specified properties remains a challenge. Recent research proposes…

Protein Design

ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models

2026-03-20 · Mohammad Shahab Sepehri, Asal Mehradfar, Berk Tinaz, Salman Avestimehr 외 arxiv

Text-to-image diffusion models achieve high visual fidelity but surprisingly exhibit systematic failures in numerical control when prompts specify explicit object counts. To address this limitation, we introduce ATHENA, …

Training-Free Debiasing of Diffusion Models via CLIP-Guided Denoising Optimization

2026-07-01 · Dain Kim, Jinseo Kim, Sungyong Baik arxiv

Text-to-image diffusion models achieve impressive visual quality, yet demographic bias remains a challenge, as neutral prompts consistently produce stereotypical representations across gender and race. Existing approache…

DLM-SWAI: Steering Diffusion Language Models Before They Unmask

2026-05-28 · Hyeseon An, Yo-Sub Han arxiv

Steering language model generation toward desired textual properties is essential for practical deployment, and inference-time methods are particularly appealing because they enable controllable generation without retrai…