FreeSwim: Revisiting Sliding-Window Attention Mechanisms for Training-Free Ultra-High-Resolution Video Generation
Paper • 2511.14712 • Published • 2
Zhenxiong Tan PRO
Yuanshi
AI & ML interests
Reinforcement Learning; Large Language Model; Multimodality; AI Infrastructure;
Recent Activity
authored a paper 1 day ago
Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention TransformersOrganizations
authored 2
papers 1 day ago
submitted a
paper to Daily Papers 1 day ago
authored a
paper 19 days ago
authored 8
papers 3 months ago
MindBridge: A Cross-Subject Brain Decoding Framework
Paper • 2404.07850 • Published • 1
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
Paper • 2406.06911 • Published • 12
LinFusion: 1 GPU, 1 Minute, 16K Image
Paper • 2409.02097 • Published • 34
MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation
Paper • 2412.04448 • Published • 10
Ultra-Resolution Adaptation with Ease
Paper • 2503.16322 • Published • 13
OminiControl2: Efficient Conditioning for Diffusion Transformers
Paper • 2503.08280 • Published
Image Editing As Programs with Diffusion Models
Paper • 2506.04158 • Published • 24
SpotEdit: Selective Region Editing in Diffusion Transformers
Paper • 2512.22323 • Published • 39
submitted a
paper to Daily Papers 3 months ago
authored a
paper 4 months ago
authored a
paper over 1 year ago