CAPR is a new dLLM-RL method that uses cached trajectory states and block-wise reward redistribution from the denoising trace to deliver tree-like supervision at 0.75x flat and 0.6x tree rollout compute, achieving SOTA on Sudoku, Countdown, GSM8K and Math500.
Mdpo: Overcom- ing the training-inference divide of masked diffusion lan- guage models.arXiv preprint arXiv:2508.13148
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
Introduces Block-R1 benchmark, Block-R1-41K dataset, and a conflict score to handle domain-specific optimal block sizes in RL post-training of diffusion LLMs.
Token-to-Mask remasking improves self-correction in diffusion LLMs by resetting erroneous commitments to masks rather than overwriting them, yielding +13.33 points on AIME 2025 and +8.56 on CMATH.
BARD bridges autoregressive and diffusion VLMs with progressive block merging plus stage-wise intra-diffusion distillation, delivering 3x speedup and new SOTA on open dVLMs using under 4.4M data points.
MemDLM embeds a simulated denoising trajectory into DLM training via bi-level optimization, creating a parametric memory that improves convergence and long-context performance even when the memory is dropped at test time.
SLIM-RL matches or exceeds TraceRL performance on MATH500, GSM8K, MBPP and HumanEval for diffusion LLMs by risk-budgeted random-masking RL without trajectory slicing.
b1 is a plug-and-play post-training framework that trains diffusion LLMs to produce dynamic-size reasoning blocks by optimizing a monotonic entropy descent objective via reinforcement learning.
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
DiSPO optimizes intermediate decisions in masked diffusion LMs by branching at selected masked states, resampling tokens, scoring completions, and updating only new tokens using a derived policy-gradient estimator that reuses terminal rollouts.
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
citing papers explorer
-
Read the Trace, Steer the Path: Trajectory-Aware Reinforcement Learning for Diffusion Language Models
CAPR is a new dLLM-RL method that uses cached trajectory states and block-wise reward redistribution from the denoising trace to deliver tree-like supervision at 0.75x flat and 0.6x tree rollout compute, achieving SOTA on Sudoku, Countdown, GSM8K and Math500.
-
Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models
Introduces Block-R1 benchmark, Block-R1-41K dataset, and a conflict score to handle domain-specific optimal block sizes in RL post-training of diffusion LLMs.
-
Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Large Language Models
Token-to-Mask remasking improves self-correction in diffusion LLMs by resetting erroneous commitments to masks rather than overwriting them, yielding +13.33 points on AIME 2025 and +8.56 on CMATH.
-
BARD: Bridging AutoRegressive and Diffusion Vision-Language Models Via Highly Efficient Progressive Block Merging and Stage-Wise Distillation
BARD bridges autoregressive and diffusion VLMs with progressive block merging plus stage-wise intra-diffusion distillation, delivering 3x speedup and new SOTA on open dVLMs using under 4.4M data points.
-
MemDLM: Memory-Enhanced DLM Training
MemDLM embeds a simulated denoising trajectory into DLM training via bi-level optimization, creating a parametric memory that improves convergence and long-context performance even when the memory is dropped at test time.
-
SLIM-RL: Risk-Budgeted Random-Masking RL for Diffusion LLMs Without Trajectory Slicing
SLIM-RL matches or exceeds TraceRL performance on MATH500, GSM8K, MBPP and HumanEval for diffusion LLMs by risk-budgeted random-masking RL without trajectory slicing.
-
Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
b1 is a plug-and-play post-training framework that trains diffusion LLMs to produce dynamic-size reasoning blocks by optimizing a monotonic entropy descent objective via reinforcement learning.
-
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
-
Diffusion-State Policy Optimization for Masked Diffusion Language Models
DiSPO optimizes intermediate decisions in masked diffusion LMs by branching at selected masked states, resampling tokens, scoring completions, and updating only new tokens using a derived policy-gradient estimator that reuses terminal rollouts.