mlsanityData to 7 Oct 2026

VDLM: Variable Diffusion LMs via Robust Latent-to-Text Rendering

arXiv 2602.15870 ↗First posted 27 Jan 2026cs.CLcited by 1

On the map: Diffusion models → Discrete and text diffusion

Abstract (arXiv)

Autoregressive language models decode left-to-right with irreversible commitments, limiting revision during multi-step reasoning. We propose VDLM, a modular variable diffusion language model that separates semantic planning from text rendering. VDLM applies LLaDA-style masked diffusion over semantic variable embeddings to enable iterative refinement in latent space, then post-trains the planner with trajectory-aware optimization using embedding-space rewards and values, avoiding text decoding inside the RL loop. To convert planned embeddings back to text, we use a Vec2Text renderer and introduce embedding perturbations to robustify decoding under planner noise. Across nine benchmarks spanning general reasoning, math, and code, VDLM is competitive in pre-training and yields substantial post-training improvements on long-form generation tasks, outperforming other baselines. These results highlight the effectiveness of embedding-space post-training and robust latent-to-text rendering for diffusion language modeling.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Discrete and text diffusion, one of 14 directions in Diffusion models. Builds on 31 of its 50 references that are in the map. First posted on arXiv 27 Jan 2026.

Builds on

31 of 50 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025LLaDA2.0: Scaling Up Diffusion Language Models to 100B10 Dec
  2. 2025d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation25 Sep
  3. 2025Diffusion Beats Autoregressive in Data-Constrained Settings21 Jul
  4. 2025Discrete Diffusion in Large Language and Multimodal Models: A Survey16 Jun
  5. 2024Simple and Effective Masked Diffusion Language Models11 Jun
  6. 2022DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models28 Nov

Other references · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  7. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  8. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  9. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,818
  10. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  11. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  12. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
13 more
  1. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  2. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  3. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  4. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 189
  5. 2019Generalization in Generation: A closer look at Exposure Biascited by 123
  6. 2025Accelerating Diffusion LLMs via Adaptive Parallel Decodingcited by 108
  7. 2022Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generationcited by 106
  8. 2018Semi-Autoregressive Neural Machine Translationcited by 48
  9. 2019Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation?cited by 33
  10. 2025Language Models are Injective and Hence Invertiblecited by 31
  11. 2025AdaBlock-dLLM: Semantic-Aware Diffusion LLM Inference via Adaptive Block Sizecited by 30
  12. 2025Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thoughtcited by 16
  13. 2025Unveiling the Potential of Diffusion Large Language Model in Controllable Generationcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026From Interface to Inference: Eliciting Any-Order Inference from Any-Order Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Think First, Diffuse Fast: Improving Diffusion Language Model Reasoning via Autoregressive Plan Conditioning
  2. 2026AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling
  3. 2026TextLDM: Language Modeling with Continuous Latent Diffusion
  4. 2026Hierarchical Continuous Diffusion Language Models
  5. 2025Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner
  6. 2026Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models
  7. 2026Planning and Rendering in Concert: DeepFusion of Autoregressive Layouts and Diffusion for Visual Text Generation
  8. 2026Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment