On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “remasking”

Remasking Discrete Diffusion Models with Inference-Time Scalingcs.LG

Remasking improves the quality of discrete diffusion models for natural language and image generation.

problem Limited iterative refinement in masked discrete diffusion models.

method Introducing ReMDM sampler that allows remasking during inference.

result Remasking enables better quality outputs with increased sampling steps.

diffusion models masked diffusion natural language image generation iterative refinement

2025-03-01abs ↗pdf ↗

VGB for Masked Diffusion Model: Efficient Test-time Scaling for Reward Satisfaction and Sample Editingcs.LG

Improves generative models by optimizing rewards and sample editing.

problem Efficiently generating high-reward samples with structural constraints.

method Introduces MDM-VGB, a discrete diffusion sampler that augments unmasking generation with reward-guided remasking.

result MDM-VGB achieves quadratic complexity and robustness to noise, outperforming heuristics like best-of-

N

Masked Diffusion Model Reward-guided Sampling Generative Models Efficient Inference Constraint Satisfaction

2026-06-26abs ↗pdf ↗

Test-Time Anchoring for Discrete Diffusion Posterior Samplingcs.LG

Discrete diffusion models improve text and image inference.

problem Challenges in posterior sampling with discrete diffusion models.

method Anchored Posterior Sampling (APS) with quantized expectation and anchored remasking.

result APS achieves state-of-the-art performance on various tasks.

discrete diffusion posterior sampling gradient guidance quantization remasking

2025-10-02abs ↗pdf ↗

Self-Aware Markov Models for Discrete Reasoningcs.LG

Improved Markov models learn from their mistakes and adapt to problem complexity.

problem Limitations of standard masked discrete diffusion models in reasoning tasks.

method Learning a Markov transition kernel trained on its own outputs, allowing remasking and adaptation.

result Significant improvement in solving reasoning problems, especially Sudoku-Extreme and Countdown-4.

Markov models discrete reasoning adaptive learning diffusion models remasking

2026-03-17abs ↗pdf ↗

Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulationcs.LG

UDM reparameterization improves language model generation.

problem Mismatch between UDM training objective and denoising posterior.

method Leave-one-out denoising and absorbing state reformulation.

result Improved UDM generation through leave-one-out parameterization.

Uniform Diffusion Models Leave-One-Out Absorbing State Language Modeling Denoising Posterior

2026-05-21abs ↗pdf ↗