Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidance
The maximum likelihood principle advocates parameter estimation via optimization of the data likelihood function. Models estimated in this way can exhibit a variety of generalization characteristics dictated by, e.g. architecture, parameterization, and optimization bias. This work addresses model learning in a setting where there further exists side-information in the form of an oracle that can label samples as being outside the support of the true data generating distribution. Specifically we develop a new denoising diffusion probabilistic modeling (DDPM) methodology, Gen-neG, that leverages this additional side-information. Our approach builds on generative adversarial networks (GANs) and discriminator guidance in diffusion models to guide the generation process towards the positive support region indicated by the oracle. We empirically establish the utility of Gen-neG in applications including collision avoidance in self-driving simulators and safety-guarded human motion generation.
Code (0)
등록된 구현이 없습니다.
Tasks
Collision AvoidanceDenoisingMotion Generationparameter estimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning
Current generative models for drug discovery primarily use molecular docking as an oracle to guide the generation of active compounds. However, such models are often not useful in practice because even compounds with hig…
Active LearningActivity PredictionDrug DiscoveryMolecular DockingBaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards
Today's generative models thrive with large amounts of supervised data and informative reward functions characterizing the quality of the generation. They work under the assumptions that the supervised data provides know…
InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling
Constructing historical language models (LMs) plays a crucial role in aiding archaeological provenance studies and understanding ancient cultures. However, existing resources present major challenges for training effecti…
Data AugmentationHow Good is a Recommender in Machine-Assisted Cross Document Event Coreference Resolution Annotation?
Annotating cross document event coreference links is a tedious task that requires annotators to have near-oracle knowledge of a document collection. The heavy cognitive load of this task decreases overall annotation qual…
coreference-resolutionCoreference ResolutionEvent Coreference ResolutionEnvisage: Diffusion-Based Rhinoplasty Goal Visualization with Mask-Decomposed Evaluation
Localized generative editing needs localized evaluation: full-image identity metrics are structurally confounded under hard-composited edits. We present Envisage, a FLUX.1-Fill inpainting reference pipeline for rhinoplas…