Library
Generative vision
30 published papers.
7:13
FLEX-WAM: Flexible Block-Causal World-Action Models for Long-Horizon Imagination and Planning
VLA models · deck
2610.05483
5:42
L-Diffusion: Laplace Diffusion for Efficient Pathology Image Segmentation
Diffusion models · deck
4:50
Human Body Restoration with One-Step Diffusion Model and A New Benchmark
Diffusion models · deck
5:00
RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior
Diffusion models · deck
5:35
You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View Corruption
· deck
6:23
Compressed Image Generation with Denoising Diffusion Codebook Models
Diffusion models · deck
5:42
CHD: Coupled Hierarchical Diffusion for Long-Horizon Tasks
Diffusion models · deck
5:26
KDPE: A Kernel Density Estimation Strategy for Diffusion Policy Trajectory Selection
Learning from demonstration · deck
7:46
Impossible Videos
Video generation · deck
6:33
LaDi-WM: A Latent Diffusion-Based World Model for Predictive Manipulation
Diffusion models · deck
9:33
Diffusion Dynamics Models with Generative State Estimation for Cloth Manipulation
Diffusion models · deck
7:57
Generative Point Cloud Registration
Diffusion models · deck
5:53
Rethinking Video Generation Model for the Embodied World
Video generation · deck
5:49
Attention Sparsity is Input-Stable: Training-Free Sparse Attention for Video Generation via Offline Sparsity Profiling and Online QK Co-Clustering
Video generation · deck
9 views
5:50
Self-Refining Video Sampling
Video generation · deck
6:45
Motion-Aware Caching for Efficient Autoregressive Video Generation
Diffusion models · deck
7:58
When Environments Shift: Safe Planning with Generative Priors and Robust Conformal Prediction
Model predictive control · deck
9:50
Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework
Diffusion models · deck
5:29
Responsible Text-to-Image Diffusion: Interpretable and Linearly Controllable Semantics for Fair and Safe Generation
Open-vocabulary perception · deck
8:59
NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devices
Neural rendering · deck
7:34
DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing
Open-vocabulary perception · deck
6:01
Concept-Guided Tokenization: Closing the Gap Between Reconstruction and Generation
Open-vocabulary perception · deck
7:28
DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion
Tracking · deck
7:12
SMD: Multi-view Safety-Critical Driving Video Generation in the Real-world Domain
Diffusion models · deck
6:31
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
Video generation · deck
6:18
MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
Diffusion models · deck
6:15
Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories
Diffusion models · deck
7:00
How Far is Video Generation from World Model: A Physical Law Perspective
Diffusion models · deck
7:26
Latent Theory of Mind: A Decentralized Diffusion Architecture for Cooperative Manipulation
Collaboration · deck
7:28
History-Guided Video Diffusion
Diffusion models · deck