Counterfactual Probing for Parallel Unmasking with Hidden Forest Structure
cs.LG, stat.ML
Submitted: 2026-09-29
Updated: 2026-10-04
Terminology
Sources
- Parallel Sampling via Counting
- Parallel Sampling via Autospeculation
- Walk fast but be careful: Understanding Parallel Sampling in Masked Diffusion
- Adding a referee to an interconnection network: What can(not) be computed in one round
- Learning a Tree-Structured Ising Model in Order to Make Predictions
- Exact Learning of Juntas from Membership Queries
- Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
- Random Restrictions of High-Dimensional Distributions and Uniformity Testing with Subcube Conditioning
- Sample-Optimal and Efficient Learning of Tree Ising models
- From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models
- The Power of Test-Time Training for Approximate Sampling
- Error Bounds and Optimal Schedules for Masked Diffusions with Factorized Approximations
- Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models
- Sharp Convergence Rates for Masked Diffusion Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- R'enyi Divergence and Kullback-Leibler Divergence
- The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
- Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling
- Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks