9 papers · 1 filter
SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention
Qi Zhao, Qirui Li, Hanlin Tang +10
Diffusion Transformers (DiTs) incur quadratic self-attention cost over spatiotemporal tokens. Existing training-free sparse attention methods often construct sparse masks from bloc…
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
Maohua Li, Qirui Li, Yanke Zhou +10
Modern text-to-image diffusion transformers (DiTs) generate images through joint attention, in which text and image tokens interact directly within a single sequence. In large-scal…
PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation
Qirui Li, Jinkun Hao, Yibo Li +3
Recent advances in physics-grounded video generation leverage physics simulation as a physical prior to guide video synthesis toward physically plausible outcomes. The simulation p…
Rethinking Cross-Layer Information Routing in Diffusion Transformers
Chao Xu, Maohua Li, Qirui Li +9
Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, obj…
InpaintDPO: Mitigating Spatial Relationship Hallucinations in Foreground-conditioned Inpainting via Diverse Preference Optimization
Qirui Li, Yizhe Tang, Ran Yi +5
Foreground-conditioned inpainting, which aims at generating a harmonious background for a given foreground subject based on the text prompt, is an important subfield in controllabl…
Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation
Qirui Li, Guangcong Zheng, Qi Zhao +4
The computational demands of self-attention mechanisms pose a critical challenge for transformer-based video generation, particularly in synthesizing ultra-long sequences. Current…