DRL trains a discriminator on data versus base-model samples in pretrained representation space and uses its logit as reward in KL-regularized RL, cutting guidance-free FID from 9.38 to 2.62 on SiT and similar gains on other backbones.
author Li, M
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
AR Forcing trains diffusion world models by integrating standard noise prediction loss into an autoregressive loop that uses self-generated predictions as context, reducing train-inference mismatch for improved long-horizon image consistency and trajectory accuracy on navigation datasets.
Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance or energy; a data deviation kernel explains and predicts the shifts and supports a内核
Rolling Sink is a training-free cache adjustment technique that maintains visual consistency in autoregressive video diffusion models for ultra-long open-ended generation beyond training horizons.
DiffGap introduces adaptive alignment of denoising steps and temperature annealing in diffusion models for 3D molecule generation, reporting better docking scores and binding affinity than prior methods on CrossDocked2020.
citing papers explorer
-
The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL
DRL trains a discriminator on data versus base-model samples in pretrained representation space and uses its logit as reward in KL-regularized RL, cutting guidance-free FID from 9.38 to 2.62 on SiT and similar gains on other backbones.
-
AR Forcing: Towards Long-Horizon Robot Navigation World Model
AR Forcing trains diffusion world models by integrating standard noise prediction loss into an autoregressive loop that uses self-generated predictions as context, reducing train-inference mismatch for improved long-horizon image consistency and trajectory accuracy on navigation datasets.
-
Mechanisms of Misgeneralization in Physical Sequence Modeling
Generative sequence models for physical tasks exhibit physical misgeneralization where local prediction errors propagate through physical measurements to distort aggregate distributions over quantities like distance or energy; a data deviation kernel explains and predicts the shifts and supports a内核
-
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
Rolling Sink is a training-free cache adjustment technique that maintains visual consistency in autoregressive video diffusion models for ultra-long open-ended generation beyond training horizons.
-
Bridging the Gap between Learning and Inference for Diffusion-Based Molecule Generation
DiffGap introduces adaptive alignment of denoising steps and temperature annealing in diffusion models for 3D molecule generation, reporting better docking scores and binding affinity than prior methods on CrossDocked2020.