DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency
Paper • 2609.39096 • Published • 3
DragGan
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
Xingang-Pan
authored 20
papers about 14 hours ago
FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing
Paper • 2503.16153 • Published • 2
Alias-Free Latent Diffusion Models:Improving Fractional Shift Equivariance of Diffusion Latent Space
Paper • 2503.09419 • Published • 6
Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models
Paper • 2503.08434 • Published • 1
WORLDMEM: Long-term Consistent World Simulation with Memory
Paper • 2504.12369 • Published • 37
Textured 3D Regenerative Morphing with 3D Diffusion Prior
Paper • 2502.14316 • Published • 1
3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
Paper • 2412.18565 • Published • 1
Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion
Paper • 2412.09593 • Published • 18
AssetField: Assets Mining and Reconfiguration in Ground Feature Plane Representation
Paper • 2303.13953 • Published
MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priors
Paper • 2410.16272 • Published
GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild
Paper • 2211.12352 • Published • 1
ACE-Ego-Hand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery
Paper • 2608.20308 • Published • 3
HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models
Paper • 2608.13205 • Published • 3
The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction
Paper • 2606.30308 • Published • 10
4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere
Paper • 2602.10094 • Published • 4
AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO
Paper • 2606.06828 • Published
Hand2World: Autoregressive Egocentric Interaction Generation via Free-Space Hand Gestures
Paper • 2602.09600 • Published
Talk-to-Edit: Fine-Grained Facial Editing via Dialog
Paper • 2109.04425 • Published
PnP-U3D: Plug-and-Play 3D Framework Bridging Autoregression and Diffusion for Unified Understanding and Generation
Paper • 2602.03533 • Published
ClothTransformer: Unified Latent-Space Transformers for Scalable Cloth Simulation
Paper • 2605.27852 • Published • 1