PEEK: One-Step-Look-Ahead Exposure Bias Correction for Diffusion Sampling
cs.CV, cs.AI
Submitted: 2026-10-20
Updated: 2026-11-08
Project page: https://dachengruoque.github.io/PEEK-Video
Terminology
Sources
- Three Creates All: You Only Sample 3 Steps
- A Geometric Perspective on Diffusion Models
- On the Trajectory Regularity of ODE-based Diffusion Sampling
- It Takes Two to Tango: Two Parallel Samplers Improve Quality in Diffusion Models for Limited Steps
- Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps
- Error as Signal: Stiffness-Aware Diffusion Sampling via Embedded Runge-Kutta Guidance
- Common Diffusion Noise Schedules and Sample Steps are Flawed
- DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
- Elucidating the Exposure Bias in Diffusion Models
- GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver
- Optimal Stepsize for Diffusion Sampling
- Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- Fast ODE-based Sampling for Diffusion Models in Around 5 Steps
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs