4 papers · 1 filter
RefAdapt-DiT: Adaptive Joint Attention for Reference-Conditioned Diffusion Transformers
Jian Tang, Jiawei Fan, Qiannan Zhou +3
Diffusion Transformers (DiTs) have become the standard backbone for high-quality generative modeling, yet deploying them in conditional generation tasks remains computationally pro…
WAM4D: Fast 4D World Action Model via Spatial Register Tokens
Ying Li, Xiaobao Wei, Jiajun Cao +10
World action models (WAMs) have recently shown promise in jointly modeling future observations and executable robot actions. However, most existing WAMs still operate in 2D video o…
FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity
Jian Tang, Jiawei Fan, Qingbin Liu +3
While the overall inference latency of Video Diffusion Transformers (DiTs) can be substantially reduced through model distillation, per-step inference latency remains a critical bo…
Occupancy World Model for Robots
Zhang Zhang, Qiang Zhang, Wei Cui +12
Understanding and forecasting the scene evolutions deeply affect the exploration and decision of embodied agents. While traditional methods simulate scene evolutions through trajec…