Toggle Poster Visibility
Opening Remarks
Fri Dec 15 06:50 AM -- 07:00 AM (PST) None
Opening Remarks
Keynote
Fri Dec 15 07:00 AM -- 07:30 AM (PST) None
Tali Dekel: Pretrained diffusion is all we need: a journey beyond training distribution
Keynote
Fri Dec 15 07:30 AM -- 08:00 AM (PST) None
Brian Trippe & Jason Yim: De novo design of protein structure and function with RFdiffusion
Break
Fri Dec 15 08:00 AM -- 08:15 AM (PST) None
Coffee Break
Poster session
Fri Dec 15 08:15 AM -- 09:15 AM (PST) None
Poster Session 1
Panel Discussion
Fri Dec 15 09:15 AM -- 10:00 AM (PST) None
Panel Discussion: Arash Vahdat, Ruiqi Gao, Tim Salimans, Robin Rombach
Keynote
Fri Dec 15 11:30 AM -- 12:00 PM (PST) None
Sayak Paul: Controlling Text-to-Image Diffusion Models
Keynote
Fri Dec 15 12:00 PM -- 12:30 PM (PST) None
Yang Song: Consistency Models
Oral
Fri Dec 15 12:30 PM -- 12:40 PM (PST) None
LC-SD: Realistic Endoscopic Image Generation with Stable Diffusion and ControlNet
[
OpenReview]
Oral
Fri Dec 15 12:50 PM -- 01:00 PM (PST) None
The Emergence of Reproducibility and Consistency in Diffusion Models
[
OpenReview]
Break
Fri Dec 15 01:00 PM -- 01:15 PM (PST) None
Coffee Break
Lightning Talks
Fri Dec 15 01:15 PM -- 02:15 PM (PST) None
Invited Lightning Talks
Poster Session
Fri Dec 15 02:15 PM -- 03:15 PM (PST) None
Poster Session 2
Closing Remarks
Fri Dec 15 03:15 PM -- 03:30 PM (PST) None
Closing Remarks + Award Reveal
None
Adversarial Estimation of Topological Dimension with Harmonic Score Maps
[
Slides]
[
Poster]
[
OpenReview]
None
DiffusionShield: A Watermark for Data Copyright Protection against Generative Diffusion Models
[
OpenReview]
None
Discrete Diffusion Language Modeling by Estimating the Ratios of the Data Distribution
[
OpenReview]
None
TS-DiffuGen: An equivariant diffusion model for reaction transition state conformation generation
[
Poster]
[
OpenReview]
None
CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images
[
Poster]
[
OpenReview]
None
Controllable Music Production with Diffusion Models and Guidance Gradients
[
Poster]
[
OpenReview]
None
AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
[
OpenReview]
None
DFU: scale-robust diffusion model for zero-shot super-resolution image generation
[
OpenReview]
None
Understanding Denoising Diffusion Probabilistic Models and their Noise Schedules via the Ornstein--Uhlenbeck Process
[
OpenReview]
None
Diffusion-C: Unveiling the Generative Challenges of Diffusion Models through Corrupted Data
[
Poster]
[
OpenReview]
None
ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
[
OpenReview]
None
WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models
[
OpenReview]
None
Diffusing More Objects for Semi-Supervised Domain Adaptation with Less Labeling
[
Poster]
[
OpenReview]
None
Beyond Generation: Exploring Generalization of Diffusion Models in Few-shot Segmentation
[
OpenReview]
None
Score Normalization for a Faster Diffusion Exponential Integrator Sampler (DEIS)
[
Poster]
[
OpenReview]
None
Harmonic Prior Self-conditioned Flow Matching for Multi-Ligand Docking and Binding Site Design
[
OpenReview]
None
Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization
[
Poster]
[
OpenReview]
None
Circumventing Concept Erasure Methods For Text-to-Image Generative Models
[
Poster]
[
OpenReview]
None
Generalized Contrastive Divergence: Joint Training of Energy-Based Model and Diffusion Model through Inverse Reinforcement Learning
[
OpenReview]
None
Diffusion based Zero-shot Medical Image-to-Image Translation for Cross Modality Segmentation
[
Slides]
[
OpenReview]
None
Faster Training of Diffusion Models and Improved Density Estimation via Parallel Score Matching
[
Poster]
[
OpenReview]
None
Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models
[
OpenReview]
None
Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
[
Poster]
[
OpenReview]
None
Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model
[
Poster]
[
OpenReview]
None
DiffDock-Pocket: Diffusion for Pocket-Level Docking with Sidechain Flexibility
[
Poster]
[
OpenReview]
None
Bridging the Gap: Addressing Discrepancies in Diffusion Model Training for Classifier-Free Guidance
[
Poster]
[
OpenReview]
None
DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting
[
Poster]
[
OpenReview]
None
In search of dispersed memories: Generative diffusion models are associative memory networks
[
OpenReview]
None
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
[
Slides]
[
OpenReview]
None
Learning from Invalid Data: On Constraint Satisfaction in Generative Models
[
Poster]
[
OpenReview]
None
Improved Convergence of Score-Based Diffusion Models via Prediction-Correction
[
Poster]
[
OpenReview]
None
LC-SD: Realistic Endoscopic Image Generation with Stable Diffusion and ControlNet
[
Poster]
[
OpenReview]
None
Investigating the Adversarial Robustness of Density Estimation Using the Probability Flow ODE
[
Poster]
[
OpenReview]
None
Denoising Heat-inspired Diffusion with Insulators for Collision Free Motion Planning
[
Poster]
[
OpenReview]
None
Sharp analysis of learning a flow-based generative model from limited sample complexity
[
Poster]
[
OpenReview]
None
Generate Your Own Scotland: Satellite Image Generation Conditioned on Maps
[
Poster]
[
OpenReview]
None
Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation
[
Poster]
[
OpenReview]
None
Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints
[
Poster]
[
OpenReview]
None
Probing Intersectional Biases in Vision-Language Models with Counterfactual Examples
[
Poster]
[
OpenReview]
None
Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective
[
OpenReview]
None
Decoding the Seeing Brain: Reconstructing Images and Text from fMRI Recordings with multimodal diffusion models
[
OpenReview]
None
Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks
[
Poster]
[
OpenReview]
Successful Page Load