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.

168,695 papers · 148 categories

Trend · papers per month

9172634 · May 202619922001200920172026
48 results for Training-Free Guidance

Framework for training-free guidance in discrete diffusion models for molecular generation.

problem No equivalent training-free guidance methods for discrete diffusion models.
method Framework using guidance functions for discrete data.
result Demonstrated utility on molecular graph generation tasks.

New method improves training-free guidance for diffusion models, achieving state-of-the-art results.

problem Accurate, training-free guidance for conditional generation in diffusion models.
method Sequential Monte Carlo (SMC) framework with Multi-Level Monte Carlo (MLMC) variance reduction.
result Achieves state-of-the-art results on CIFAR-10 and ImageNet datasets with significant cost reduction.

SDG uses optimal control to improve classifier guidance in low-density regions.

problem Inefficient guidance in low-density regions of posterior distributions.
method Integrates stochastic optimal control with Stein variational inference to compute the steepest descent direction.
result SDG improves guidance in low-density regions, outperforming standard methods.

New method uses off-the-shelf classifiers to improve diffusion generation without extra training.

problem Improving sample quality and controllability in conditional diffusion generation.
method Leveraging off-the-shelf classifiers in a training-free fashion with calibration and pre-conditioning techniques.
result Significant performance improvements (up to 20%) over existing guidance schemes.

A new method approximates the exact posterior score for diffusion models.

problem Training-free guidance of diffusion models for image restoration and inverse problems.
method Presented a novel expression for the exact posterior score, leveraging it to compute step sizes on the fly.
result Demonstrated competitive performance with fewer time steps compared to state-of-the-art techniques.

NegToMe uses images to guide text-based models away from unwanted visual elements.

problem Insufficient text-based adversarial guidance for complex visual concepts.
method Negative token merging (NegToMe) using visual features from reference images.
result Significantly enhances output diversity and reduces visual similarity to copyrighted content.

Novel alignment framework for text-to-image generation using diffusion models and flow matching.

problem Improving text-to-image generation with minimal computational resources.
method Proposes a novel alignment framework that decomposes the score function into pre-trained score plus a conditional expectation of the reward.
result Achieves comparable performance to finetuning-based models with reduced computational cost.

DriftLite improves inference quality of diffusion models without retraining.

problem Adapting pre-trained diffusion models to new target distributions without retraining.
method Lightweight, training-free particle-based approach that steers inference dynamics with optimal stability control.
result Consistently reduces variance and improves sample quality over existing methods.

RB-Modulation trains free diffusion models without external adapters.

problem Training-free personalization of diffusion models with style and content control.
method Stochastic optimal control with a style descriptor and cross-attention aggregation.
result Precise content and style extraction and control without external adapters.

ESS-Flow guides flow models without retraining, using Bayesian inference in source space.

problem Training flow models on paired data for conditional generation or sample production.
method Gradient-free Bayesian inference in source space using Elliptical Slice Sampling.
result Effective in diverse tasks including material design and protein structure prediction.

A new method for generating samples without training, using smoothed score matching.

problem Generating samples efficiently and without training.
method Moment-matched score-smoothed overdamped Langevin dynamics (MM-SOLD).
result The method enables fast, robust, training-free sampling with competitive sample fidelity and diversity.

We use diffusion models to sample from complex GP priors in climate data.

problem Sampling from non-stationary Gaussian process priors is computationally hard.
method Replace GP prior with a diffusion model surrogate and use training-free guidance algorithms.
result Generated distributions are close to GP priors and can be fine-tuned.

Power-SMC reduces inference latency for training-free LLM reasoning.

problem Training-free LLM reasoning with low latency.
method Power-SMC, a training-free Sequential Monte Carlo scheme targeting sequence-level power distribution.
result Power-SMC reduces inference latency from 16-28× to 1.4-3.3× over baseline decoding.

Training-free method improves large language model sequence quality via reward-guided sampling.

problem Optimizing large language model sequence quality over token likelihood.
method Reward-augmented target distribution combined with Sequential Monte Carlo sampling.
result Significant gains in sequence generation and mathematical reasoning tasks.

Training-free looped transformers improve model performance without additional training.

problem Improving model performance without additional training or fine-tuning.
method A lightweight inference-time wrapper loops a contiguous mid-stack block of layers of a frozen checkpoint without additional fine-tuning.
result Our method improves model performance across various model families.

TFB simplifies Bayesian LLM uncertainty estimation without extra training.

problem Estimating uncertainty in LLM responses remains challenging.
method Training-Free Bayesianization (TFB) that transforms low-rank adapters into Bayesian ones without additional training.
result TFB achieves superior uncertainty estimation and generalization compared to existing methods.

Paper extends 2D ZSAD to 3D MRI without training, achieving robust anomaly detection.

problem Challenges in extending zero-shot anomaly detection to 3D medical images.
method Constructs localized volumetric tokens by aggregating 2D slices processed by 2D foundation models.
result Training-free, batch-based ZSAD effectively extends from 2D encoders to full 3D MRI volumes.

A new particle filter uses diffusion models to improve state estimation from noisy data.

problem Sequentially estimating the state of a dynamical system from noisy and incomplete observations.
method Uses a diffusion model to simulate and predict system dynamics, incorporating noisy observations to refine predicted states.
result An unbiased particle filtering method that rigorously fuses observational data with diffusion model simulations.

Training-free model learns SDE dynamics without training, accelerating parameter studies.

problem High computational cost of simulating parameter-dependent SDEs.
method Training-free conditional diffusion model with joint kernel-weighted Monte Carlo estimator.
result Accurate approximation of conditional distributions across varying parameter values.

This work formalizes guidance in diffusion models and introduces a stochastic control framework.

problem Lack of a solid theoretical foundation for guidance scheduling in diffusion models.
method Introduces a stochastic optimal control framework to cast guidance scheduling as an adaptive optimization problem.
result Establishes a principled foundation for more effective guidance in diffusion models.

Exact guidance for discrete data improves posterior sampling efficiency.

problem Inefficient guidance for discrete data in posterior sampling.
method Derive exact transition rate for desired distribution given learned discrete flow matching model.
result Significantly improved efficiency with single forward pass per sampling step.

Diffusion models improve sample quality with guidance, proving it works for general data distributions.

problem Theoretical understanding of guidance effect in diffusion models for general data distributions.
method Analyzing diffusion guidance under general data distributions, proving improvement in sample quality.
result Guidance improves the average reciprocal of the classifier probability, aligning with its motivation.

Research shows guidance in diffusion models does not sample from intended distribution, affecting boundary sampling.

problem Clarifying the misconception that guidance modifies the data distribution in diffusion models.
method Rigorous proof and fine-grained analysis of guidance dynamics in two cases: mixtures of compactly supported distributions and mixtures of Gaussians.
result Guidance leads to sampling more heavily from the boundary of the support of the conditional distribution as the parameter increases.

Regression problems assume every instance is annotated (labeled) with a real value, a form of annotation we call \emph{strong guidance}. In order for these annotations to be accurate, they must be the result of a precise experiment or measurement. However, in some cases additional \emph{weak guidance} might be given by…

2018-04-01abs ↗pdf ↗

A criterion for training-free time-lagged spectral embeddings of multivariate time series

problem Applicability of fixed-length descriptors for multivariate time series
method Using a stationary Gaussian VAR(1) model and cosine similarity to classify descriptors
result D(τ) separates two classes when signals are approximately stationary and cross-channel temporal coupling is present

Jeffrey guidance extends diffusion-model control to more complex applications.

problem Controlling diffusion models beyond simple cases like conditional sampling.
method Leveraging Jeffrey's rule of conditioning to update marginal distributions towards a target distribution.
result Significant reductions in FID on CIFAR-10 and FFHQ with Inception embeddings as the target.

OPNP prunes parameters and neurons to improve OOD detection without training.

problem Detecting out-of-distribution samples in real-world machine learning models.
method OPNP approach that identifies and removes sensitive parameters and neurons.
result OPNP consistently outperforms existing methods on multiple OOD detection tasks.

The paper analyzes how guidance affects diffusion models using Gaussian mixture models.

problem Understanding how guidance influences diffusion models in specific contexts.
method Theoretical study using Gaussian mixture models and comparison inequalities for differential equations.
result Guidance boosts classification confidence but reduces distribution diversity, leading to lower differential entropy.

New study on guidance in masked diffusion models, showing how it shapes sampling dynamics.

problem Understanding how guidance influences the sampling behavior of masked diffusion models.
method Derived explicit solution to guided reverse dynamics, analyzing effects in 1D and 2D.
result Guidance amplifies class-specific regions and suppresses shared regions, affecting covariance structures.

LatentFlow simplifies conditioning of stochastic processes without training.

problem Intractable conditional laws for complex stochastic models.
method Writing stochastic process as latent innovation, reducing conditioning to latent-space inference.
result Exact conditional sampling across various model classes.

The paper analyzes CFG in masked diffusion models and proposes a new method to improve sample quality.

problem Improving sample quality in conditional generation with CFG in masked diffusion models.
method Analyzing CFG's effect in a low-dimensional masked diffusion model, revealing early-stage guidance harms quality and late-stage improves it. Proposed a novel method to smooth transitions between distributions.
result The proposed method improves sample quality via a simple one-line code change.

Gradient guidance improves diffusion models for optimizing specific objectives.

problem Improving diffusion models for specific optimization tasks.
method Established a mathematical framework for gradient-guided diffusion, linking it to optimization theory. Developed a modified gradient guidance method and iteratively fine-tuned version.
result Gradient-guided diffusion models are essentially solutions to regularized optimization problems, preserving latent structure.

RealStats detects fake images rigorously, combining multiple detectors for robustness.

problem Detecting AI-generated images remains challenging due to evolving generative models.
method Combines training-free statistics to compute p-values and aggregate them for a unified real-image distribution.
result Framework produces interpretable probability scores for robust fake image detection.

Self-guidance controls image generation by extracting properties from diffusion model representations.

problem Generating images from text descriptions is challenging due to the complexity of visual details.
method Self-guidance uses internal representations of diffusion models to control image generation.
result Properties like object shape, location, and appearance can be extracted and used to steer image generation.

SFG improves on-manifold sampling without labels or additional training.

problem Guiding score-based models on manifolds without labeled data or extra training.
method Developed saddle-free guidance (SFG) that uses curvature of log density estimates.
result SFG achieves state-of-the-art metrics in image generation without labeled data or additional training.

New method aligns diffusion models for inference-time properties without retraining.

problem Aligning pre-trained diffusion models for desired inference-time properties.
method Variationally stable Doob's matching for provable guidance estimation.
result Consistent estimator of guidance with non-asymptotic convergence guarantees.