Provably Safe Generative Sampling with Constricting Barrier Functions
cs.LG, cs.AI, cs.SY, eess.SY, math.OC
Submitted: 2026-02-24
Updated: 2026-07-31
Code: https://github.com/real-stanford/diffusion_policy
Terminology
Sources
- SafeFlow: Safe Robot Motion Planning with Flow Matching via Control Barrier Functions
- Constricting Tubes for Prescribed-Time Safe Control
- Test-time Alignment of Diffusion Models without Reward Over-optimization
- Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding
- HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
- Almost-Sure Safety Guarantees of Stochastic Zero-Control Barrier Functions Do Not Hold
- Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review
- Physics-Constrained Flow Matching: Sampling Generative Models with Hard Constraints
- SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier Functions
- LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
- Training-Free Constrained Generation With Stable Diffusion Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis