Conditional Total Correlation and the Serial Depth of Adaptive Parallel Sampling
cs.IT, cs.CL, math.IT
Submitted: 2026-08-26
Updated: 2026-08-26
Terminology
Sources
- Structured Denoising Diffusion Models in Discrete State-Spaces
- Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
- Large Language Diffusion Models
- Optimal Inference Schedules for Masked Diffusion Models
- Error Bounds and Optimal Schedules for Masked Diffusions with Factorized Approximations
- Adaptation to Intrinsic Dependence in Diffusion Language Models
- The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
- From Bits to Rounds: Parallel Decoding with Exploration for Diffusion Language Models
- ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs
- Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective
- Parallel Sampling via Counting
- Parallel Sampling via Autospeculation
- Confidence-Based Decoding is Provably Efficient for Diffusion Language Models
- Parallel Token Prediction for Language Models
- Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
- Dream 7B: Diffusion Large Language Models
- Qwen2.5 Technical Report
- Qwen3-VL Technical Report
- Mercury: Ultra-Fast Language Models Based on Diffusion
- Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Related papers
- Clipped Affine Policy: Low-Complexity Near-Optimal Online Power Control for Energy Harvesting Communications over Fading Channels
- Discrepancy for Random Linear Codes
- A New Approach to Code Smoothing Bounds
- Contextual Memory-Enhanced Source Coding for Low-SNR Communications
- Symmetry-Enforced Quadratic Approximate-Degradability Bounds for Noisy Landau-Streater Channels
- Anonymous Shamir's Secret Sharing via Reed-Solomon Codes Against Permutations, Insertions, and Deletions