Limits of Confidence in Diffusion

arXiv:2609.20581 · cs.AI · Submitted 2026-09-17 · Read on arXiv

cs.AI

Submitted: 2026-09-17

Updated: 2026-09-18

Code: https://github.com/apple/ml-YOURREPONAME

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Diffusion Model — 5× in this paper · explained in 8 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Diffusion Models — 4× in this paper · explained in 6 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Additivity — 2× in this paper · explained in 1 episode
• Distribution Shift — 2× in this paper · explained in 6 episodes
• International Conference on Learning Representations — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Distribution Matching — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 4 episodes
• Exchangeability — 1× in this paper · explained in 2 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Speculative Decoding — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing
• Teaching Arithmetic to Small Transformers
• The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models
• Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
• Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective
• Teaching Algorithmic Reasoning via In-context Learning

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection