JIVE: Jacobian-Informed Volume Expansion for Diverse Generative Sampling
cs.LG, cs.AI, cs.CV
Submitted: 2026-09-27
Updated: 2026-09-27
Code: https://github.com/guangxunZhang/JIVE
License: http://creativecommons.org/licenses/by/4.0/
The gist: Generative models often suffer from mode collapse and limited sample diversity.
Terminology
Abstract
Generative models often suffer from mode collapse and limited sample diversity. While prior works attempt to mitigate this by jointly generating a batch of samples and repelling their trajectories, these heuristics do not explicitly maximize the diversity of the resulting endpoints. We introduce JIVE, a training-free framework that enhances generative diversity by injecting velocity perturbations aligned with the leading right singular subspace of the generator's endpoint Jacobian. By leveraging this local geometric structure, JIVE provably maximizes endpoint diversity while preserving sample quality. To maintain practical efficiency, we compute these perturbation directions via matrix-free iterations rooted in classical numerical linear algebra, requiring only a small computational overhead. Across different benchmarks, JIVE boosts both pixel and feature-level diversity in few-step and one-step generation.
Sources
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks