Derives an exact unbiased policy gradient for RL post-training of diffusion LLMs via entropy-guided step selection and one-step denoising rewards, achieving state-of-the-art results on coding and logical reasoning benchmarks.
hub
Beyond autoregression: Discrete diffu- sion for complex reasoning and planning.arXiv preprint arXiv:2410.14157
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
Uniform diffusion models rely on a leave-one-out denoiser rather than the usual denoising posterior, with exact conversions derived; an absorbing-state reformulation is introduced that matches or exceeds masked diffusion on language modeling while preserving the original joint distribution.
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.
Info-Gain Sampler improves MDM decoding by using bidirectional information gain to reduce cumulative uncertainty, outperforming greedy samplers on reasoning accuracy and creative writing tasks.
LoopMDM loops early-middle layers in masked diffusion models to match same-size MDM performance with up to 3.3x fewer training FLOPs and outperform on reasoning tasks by up to 8.5 points on GSM8K.
SSOPD converts intra-group correct-wrong contrast into process supervision by distilling a teacher distribution from the shortest correct completion into prefixes of the longest wrong completion, improving GRPO on AIME and HMMT benchmarks.
Joint training of the latent space with the diffusion process produces a competitive latent diffusion language model that is faster than existing discrete and continuous diffusion baselines.
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
Query position is a first-order variable in dLLM ICL whose variance matches semantic quality impact; mitigated via Average Confidence metric and training-free Auto-ICL routing.
RLDF is a new RL paradigm for diffusion language models that optimizes toward clipped clean states with weighted timestep sampling and reports substantial gains on reasoning benchmarks for LLaDA and Dream.
Replacing Softmax with Scaled Signed Averaging in transformer attention improves generalization under distribution shifts for in-context learning and boosts results on NLP benchmarks.
Static checking rewards and moderate AST-based hints improve diffusion RL performance for code generation, with effectiveness varying by task difficulty across HumanEval, MBPP, and LiveCodeBench.
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
citing papers explorer
-
Reinforcement Learning for Diffusion LLMs with Entropy-Guided Step Selection and Stepwise Advantages
Derives an exact unbiased policy gradient for RL post-training of diffusion LLMs via entropy-guided step selection and one-step denoising rewards, achieving state-of-the-art results on coding and logical reasoning benchmarks.
-
Adaptive Order Policies for Masked Diffusion
A policy network learns to choose unmasking order in masked diffusion by reweighting the loss, outperforming random and heuristic baselines on ordering-sensitive tasks.
-
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
Uniform diffusion models rely on a leave-one-out denoiser rather than the usual denoising posterior, with exact conversions derived; an absorbing-state reformulation is introduced that matches or exceeds masked diffusion on language modeling while preserving the original joint distribution.
-
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.
-
Self-Supervised On-Policy Distillation for Reasoning Language Models
SSOPD converts intra-group correct-wrong contrast into process supervision by distilling a teacher distribution from the shortest correct completion into prefixes of the longest wrong completion, improving GRPO on AIME and HMMT benchmarks.