Fixed-point neural samplers on discrete spaces
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Sources
- Sampling two-dimensional spin systems with transformers
- Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matching
- Discrete diffusion samplers and bridges: Off-policy algorithms and applications in latent spaces
- Neural Flow Samplers with Shortcut Models
- ATLAS: A Foundation Neural Sampler for Amorphous Materials
- MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Well-Tempered Metadynamics
- Scaling Autoregressive Models for Lattice Thermodynamics
- Discrete Adjoint Schr\"odinger Bridge Sampler
- Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching
- FEAT: Free energy Estimators with Adaptive Transport
- Free energy Estimation on Any State Space
- LEAPS: A discrete neural sampler via locally equivariant networks
- Adjoint Schr\"odinger Bridge Sampler
- FrOGS: Discrete Neural Sampler for Independent Alloy Configurations Across Chemical Conditions
- Path Planning for Masked Diffusion Model Sampling
- Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective
- Score-based Continuous-time Discrete Diffusion Models
- Energy-based generator matching: A neural sampler for general state space
- Dream 7B: Diffusion Large Language Models
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