Research
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

3597191,0781,437 · Jun 202019922001200920172026
48 results for Diffusion Language Models

New method boosts performance of diffusion models on discrete data like natural language.

problem Performance of diffusion models on discrete data like natural language is poor.
method Proposes score entropy, a novel loss that extends score matching to discrete spaces.
result Significantly boosts performance on language modeling tasks.

This research explores discrete diffusion models for natural language generation.

problem Challenges in applying diffusion models to discrete data, especially natural language.
method Investigates Discrete Denoising Diffusion Probabilistic Model (D3PM) and compares it with autoregressive models.
result Discrete diffusion models achieve better processing speed than autoregressive models.

New diffusion models can generate text faster than traditional autoregressive models.

problem The slow generation time of autoregressive models.
method Theoretical analysis of diffusion language models using information theory.
result The sampling error in diffusion models decays with fewer iterations than the text sequence length.

Global watermark for diffusion language models decouples detection from local contexts.

problem Watermarking in diffusion language models is challenging due to joint sampling of distributions over many unresolved positions.
method Proposes a global vector-valued sketch representation to control watermarking in masked diffusion language models.
result The method decouples detection from local contexts, resulting in an order-agnostic statistic and robustness.

LADD models improve discrete diffusion for faster language generation.

problem Practical discrete diffusion models ignore cross-token dependencies, degrading performance.
method Introduces a learnable auxiliary latent channel, diffusing over the joint (token, latent) space.
result LADD models yield improvements on unconditional generation metrics.

Language Rectified Flow improves diffusion language generation by simplifying complex steps.

problem Complexity in diffusion language models limits their implementation in NLP applications.
method Reformulates probabilistic flow models to learn neural ODE models for efficient domain transfer.
result Consistently outperforms baselines on fine-grained control tasks and text editing.

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.

Unified continuous diffusion model outperforms discrete alternatives in scalability and quality.

problem Continuous diffusion models were perceived as less scalable than discrete models.
method Reconstructed Plaid model and compared it with modern discrete DLMs, optimizing noise schedule and embeddings via likelihood.
result Unified continuous diffusion model (RePlaid) outperforms discrete models in compute efficiency and quality.

Theoretical analysis shows MDMs can be efficient but not for all metrics.

problem Understanding the efficiency-accuracy trade-off of diffusion language models.
method Theoretical analysis of Masked Diffusion Model (MDM) using perplexity and sequence error rate as metrics.
result MDM achieves near-optimal perplexity but requires linear scaling for sequence error rate, highlighting efficiency-accuracy trade-offs.

Simplified masked diffusion models improve discrete data generation.

problem Complex model formulations and unclear relationships hinder discrete data generative modeling.
method Developed a simple and general framework for masked diffusion models.
result Models trained on OpenWebText surpass prior diffusion language models and outperform autoregressive models.

DDPD separates generation into planning and denoising for improved efficiency.

problem Efficiently denoise corrupted data during generation.
method Separates generation into a planner and denoiser, selecting denoising positions based on corruption severity.
result DDPD outperforms traditional methods on language and image generation benchmarks.

DOS improves language model generation by considering inter-token dependencies.

problem Lack of sequence-level information and inter-token dependencies in existing decoding strategies.
method Dependency-Oriented Sampler (DOS) that uses attention matrices to approximate inter-token dependencies.
result DOS consistently achieves superior performance on code generation and mathematical reasoning tasks.

Faster sampling in discrete diffusion models with predetermined transition time.

problem Efficiency in sampling discrete diffusion models.
method Discrete Non-Markov Diffusion Models (DNDM) with predetermined transition time.
result Significantly reduces the number of function evaluations for faster sampling.

Discrete diffusion models improve data generation for discrete data like language and graphs.

problem Adapting diffusion models to discrete state spaces for better data generation.
method Formulated as CTMCs, used uniformization of continuous Markov chains for sampling.
result Derive guarantees for sampling from any distribution on a hypercube, aligning with state-of-the-art achievements.

New RL algorithm GDPO improves DLM reasoning efficiency.

problem Adapting RL to DLMs for efficient, unbiased likelihood estimation.
method Group Diffusion Policy Optimization (GDPO) using semi-deterministic Monte Carlo.
result GDPO outperforms existing methods on math, reasoning, and coding benchmarks.

wd1 improves reasoning in dLLMs by optimizing policies without policy ratios.

problem Improving reasoning in diffusion-based large language models through RL.
method wd1: ratio-free policy optimization using weighted log-likelihood.
result wd1 outperforms diffusion-based GRPO while requiring lower computational cost.

This research compares masked diffusion models to autoregressive language models, focusing on architectural differences.

problem Comparing masked diffusion models to autoregressive language models due to architectural differences.
method Equitably compare MDMs within a decoder-only framework, investigating architectural influences.
result Decoder-only MDMs can achieve significant speedups and comparable perplexity with temperature annealing.

Paper proposes a method to speed up discrete diffusion models by distilling many steps into few.

problem Challenges in capturing dependencies between elements in discrete diffusion models.
method Proposes 'mixture' models and loss functions to distill many sampling steps into few.
result Effective in distilling pretrained discrete diffusion models across image and language domains.

Gradient-based framework for optimizing text prompts in diffusion models.

problem Efficiently optimizing prompts in text-to-image diffusion models with large domain space and non-differentiable embeddings.
method Formulated as discrete optimization over language space, designed compact subspaces, and introduced shortcut text gradient.
result Empirically discovered prompts that enhance or destroy image faithfulness.

Paper reviews methods for conditional sampling in generative diffusion models.

problem Extending generative diffusion models to sample from conditional distributions.
method Review of existing computational approaches to conditional sampling.
result Highlight key methodologies for constructing conditional generative samplers.

Language models are at the heart of numerous works, notably in the text mining and information retrieval communities. These statistical models aim at extracting word distributions, from simple unigram models to recurrent approaches with latent variables that capture subtle dependencies in texts. However, those models a…

2019-09-11abs ↗pdf ↗

New framework for discrete-state diffusion models reduces sample complexity.

problem Lack of theoretical understanding and sample complexity analysis for discrete-state diffusion models.
method Developed a principled theoretical framework, decomposing score estimation error.
result Established sample complexity bound of O~(ε2)\widetilde{\mathcal{O}}(ε^{-2}).

Generates coherent storybooks from plain text using diffusion models.

problem Ensuring coherency in a sequence of images for storytelling applications.
method Combines pre-trained LLM and text-guided Latent Diffusion Model for zero-shot generation.
result Outperforms state-of-the-art image editing baselines in generating coherent storybooks.

DMVI uses diffusion models for efficient probabilistic inference in PPLs.

problem Efficient probabilistic inference in complex probabilistic programming languages.
method DMVI employs diffusion models as variational approximations to the posterior distribution, optimizing a bound on the marginal likelihood.
result DMVI produces more accurate posterior inferences than existing methods in PPLs with similar computational cost and less manual tuning.

Improved text-to-image and multimodal understanding through adaptive generation order optimization.

problem Determining optimal generation sequences in text-to-image synthesis and multimodal understanding.
method Introduced a learnable control module trained via Group Relative Policy Optimization (GRPO) to determine the generation order.
result Learning the control block substantially improves text-to-image alignment and multimodal understanding in DLMs.

Diffusion models generate music sequences without autoregressive loops.

problem Generating music sequences from symbolic data using diffusion models.
method Parameterize discrete symbolic data in continuous latent space, train diffusion model, generate sequences through reverse process.
result Strong unconditional generation and post-hoc conditional infilling compared to autoregressive models.

Method optimizes diffusion model generation to meet user preferences.

problem Optimizing diffusion model generation with only black-box target scores.
method Covariance-adaptive sequential optimization algorithm for black-box optimization.
result Proves superior performance in achieving better target scores.

New text-to-image diffusion models improve scene understanding for AI agents.

problem Fine-grained scene understanding for AI agents from text and images.
method Pre-trained text-to-image diffusion models optimized for generating images from text prompts.
result Policies learned with Stable Control Representations outperform state-of-the-art approaches on various control tasks.

Gaussian processes are conditioned on various types of data.

problem Exact inference in Gaussian processes is limited to linear-Gaussian settings.
method Established an equivalence between GPs and linear diffusion models, allowing for approximate inference in non-linear settings.
result A general-purpose GP inference scheme that handles various conditioning statements, including non-linear physics and natural language.

Unified framework reduces NFEs for inverse problems.

problem High computational costs and degraded reconstruction quality in existing LDM-based inverse solvers.
method Consistency Regularised Gradient Flows for posterior sampling and prompt optimization.
result Significantly reduced computational cost with state-of-the-art performance.

AutoDiff combines auto-encoder and diffusion model for realistic tabular data synthesis.

problem Generating realistic synthetic tabular data with heterogeneous features.
method Employing auto-encoder architecture to handle tabular data's complexity.
result Synthetic tables from AutoDiff show good statistical fidelity and perform well in machine learning tasks.

Unified framework for convergence of discrete diffusion models without state space size dependence.

problem Fundamental limitations in existing convergence theory for discrete diffusion models, especially under singular priors and large vocabularies.
method Unified adjoint-equation-based framework that establishes dimension-free convergence guarantees in any integral probability metric (IPM).
result First dimension-free convergence bounds applicable to both masked and uniform priors, free of state space size SS.

Improved sample complexity for diffusion models without needing empirical risk minimizers.

problem Theoretical limitations in sample complexity for diffusion models.
method Structured decomposition of score estimation error, eliminating dependence on neural network parameters.
result Achieved sample complexity bound of O(ε^(-4)) without empirical risk minimizer access.