16 papers
On first-order thermodynamic equilibrium conditions for fluid-fluid and solid-phase interfaces
Nicodemo Di Pasquale, Thomas Hudson
Starting from the constrained variational formulation of Larché and Cahn for solids in contact with fluids, a unified thermodynamic framework for such systems is developed. Both bu…
Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation
Xingtong Ge, Yi Zhang, Yushi Huang +6
Distilling video generation models to extremely low inference budgets (e.g., 2--4 NFEs) is crucial for real-time deployment, yet remains challenging. Trajectory-style consistency d…
AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization
Dailan He, Guanlin Feng, Xingtong Ge +5
Streaming autoregressive (AR) video generators combined with few-step distillation achieve low-latency, high-quality synthesis, yet remain difficult to align via reinforcement lear…
MambaRaw: Selective State Space Modeling for Efficient 4K Raw Image Reconstruction
Peize Li, Fanhu Zeng, Tongda Xu +5
In-camera JPEG previews are ubiquitous in raw image formats and provide an sRGB reference at negligible storage cost. Although existing metadata-based reconstruction frameworks can…
Versatile Recompression-Aware Perceptual Image Super-Resolution
Mingwei He, Tongda Xu, Xingtong Ge +3
Perceptual image super-resolution (SR) methods restore degraded images and produce sharp outputs. In practice, those outputs are usually recompressed for storage and transmission.…
Improving Joint Audio-Video Generation with Cross-Modal Context Learning
Bingqi Ma, Linlong Lang, Ming Zhang +5
The dual-stream transformer architecture-based joint audio-video generation method has become the dominant paradigm in current research. By incorporating pre-trained video diffusio…