Motion-Aware Caching for Efficient Autoregressive Video Generation Paper • 2605.01725 • Published May 3 • 8
SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices Paper • 2601.08303 • Published Jan 13 • 21
Seeing Fast and Slow: Learning the Flow of Time in Videos Paper • 2604.21931 • Published Apr 23 • 19
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models Paper • 2501.06751 • Published Jan 12, 2025 • 32
Running on Zero Agents 618 AuraSR-v2 😻 618 Upscale your images 4x with high-quality AI enhancement