RSPO interprets reward advantages as targets for relative log-ratios in dLLMs, calibrating noisy estimates to stabilize RLVR training and achieve strong gains on planning tasks with competitive math reasoning performance.
wd1: Weighted policy optimization for reasoning in diffusion language models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
TAD improves the accuracy-parallelism trade-off in diffusion LLMs via temporal-aware self-distillation that applies hard labels to soon-to-be-decoded tokens and soft supervision to future tokens.
DTM recasts dLLM fine-tuning as weighted cross-entropy matching of tilted local posteriors, with demonstrated gains on Sudoku and math tasks.
b1 trains dLLMs to dynamically select reasoning block sizes via monotonic entropy descent with RL, improving coherence over fixed-size baselines on reasoning benchmarks.
Non-autoregressive diffusion language models have an inherent proximity bias in token unmasking that causes spatial error propagation, which a minimal planner and annealing strategy can mitigate for better reasoning performance.
DMax enables faster parallel decoding in diffusion language models by using on-policy training to recover from errors and soft embedding interpolations for iterative revision, boosting tokens per forward pass roughly 2-3x on benchmarks while preserving accuracy.
citing papers explorer
-
Relative Score Policy Optimization for Diffusion Language Models
RSPO interprets reward advantages as targets for relative log-ratios in dLLMs, calibrating noisy estimates to stabilize RLVR training and achieve strong gains on planning tasks with competitive math reasoning performance.
-
TAD: Temporal-Aware Trajectory Self-Distillation for Fast and Accurate Diffusion LLM
TAD improves the accuracy-parallelism trade-off in diffusion LLMs via temporal-aware self-distillation that applies hard labels to soon-to-be-decoded tokens and soft supervision to future tokens.
-
Discrete Tilt Matching
DTM recasts dLLM fine-tuning as weighted cross-entropy matching of tilted local posteriors, with demonstrated gains on Sudoku and math tasks.
-
Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
b1 trains dLLMs to dynamically select reasoning block sizes via monotonic entropy descent with RL, improving coherence over fixed-size baselines on reasoning benchmarks.
-
Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models
Non-autoregressive diffusion language models have an inherent proximity bias in token unmasking that causes spatial error propagation, which a minimal planner and annealing strategy can mitigate for better reasoning performance.
-
DMax: Aggressive Parallel Decoding for dLLMs
DMax enables faster parallel decoding in diffusion language models by using on-policy training to recover from errors and soft embedding interpolations for iterative revision, boosting tokens per forward pass roughly 2-3x on benchmarks while preserving accuracy.