-
Analyzing and Improving the Training Dynamics of Diffusion Models
Paper • 2312.02696 • Published • 33 -
Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models
Paper • 2312.12487 • Published • 9 -
Implicit Diffusion: Efficient Optimization through Stochastic Sampling
Paper • 2402.05468 • Published • 6
Hans
wav
AI & ML interests
Multi-modal generative models
Recent Activity
liked
a model 25 days ago
N8Programs/Unslopper-GGUF liked
a model 5 months ago
moondream/moondream3-preview liked
a model 10 months ago
facebook/PE-Core-G14-448 Organizations
Evaluation
Tabular Data
Timeseries
-
FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder
Paper • 2401.10032 • Published • 13 -
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
Paper • 2401.04658 • Published • 27 -
FreeInit: Bridging Initialization Gap in Video Diffusion Models
Paper • 2312.07537 • Published • 27 -
TCNCA: Temporal Convolution Network with Chunked Attention for Scalable Sequence Processing
Paper • 2312.05605 • Published • 3
Efficiency
Diffusion
-
Analyzing and Improving the Training Dynamics of Diffusion Models
Paper • 2312.02696 • Published • 33 -
Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models
Paper • 2312.12487 • Published • 9 -
Implicit Diffusion: Efficient Optimization through Stochastic Sampling
Paper • 2402.05468 • Published • 6
Timeseries
-
FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder
Paper • 2401.10032 • Published • 13 -
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
Paper • 2401.04658 • Published • 27 -
FreeInit: Bridging Initialization Gap in Video Diffusion Models
Paper • 2312.07537 • Published • 27 -
TCNCA: Temporal Convolution Network with Chunked Attention for Scalable Sequence Processing
Paper • 2312.05605 • Published • 3
Evaluation
Efficiency
Tabular Data