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.
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.
Training-free GNNs use labels as features to improve node classification.
problem Improving graph neural networks for transductive node classification.
method Advocates labels as features, designs training-free GNNs based on this.
result Training-free GNNs outperform traditional GNNs in node classification.
A training-free method for conditional sampling using flow matching.
problem Weight degeneracy in high-dimensional importance sampling.
method Sequential Monte Carlo with resampling and stochastic flow.
result Significantly outperforms existing methods on MNIST and CIFAR-10.
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.
Training-free method improves text-to-image generation quality.
problem Error accumulation in simultaneous token updates of masked diffusion models.
method Training-free self-correction framework exploiting inductive biases.
result Significantly improved generation quality on text-to-image tasks.
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.
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.
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.
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.
A new method improves SSVEP BCI to recognize responses in sub-second time with high accuracy.
problem Achieving high accuracy in SSVEP BCI with short response times.
method CSTA (Combining Spatial-Filtering and Temporal Alignment) method.
result CSTA achieves maximum mean accuracy of 97.43% in sub-second response time.
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.
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.
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.
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.
TADA improves diffusion sampling without training, up to 186% faster.
problem Efficient sampling in diffusion models, especially for high-fidelity images.
method Training-free ODE solver with higher-dimensional initial noise.
result Up to 186% faster sampling compared to state-of-the-art methods.
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.
A training-free message passing module improves hypergraph neural networks.
problem Computational intensive training process in hypergraph neural networks.
method Decoupling hypergraph structural information from model learning stage.
result TF-HNN achieves superior performance and training efficiency.
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.
Bayesian optimization reduces RNN architecture search time.
problem Optimizing RNN architectures for time series prediction.
method Bayesian Optimization with a training-free performance metric.
result BO designs well-performing RNN architectures with reduced optimization time.
New method samples from multi-modal distributions on Riemannian manifolds without training.
problem Sampling from multi-modal distributions on Riemannian manifolds is challenging.
method Simulation of a non-equilibrium deterministic dynamics to transport noise toward target distributions.
result Method is entirely training-free and effective on various multi-modal problems.
A training-free conformal interval is a mandatory baseline for probabilistic time-series forecasting.
problem Comparing probabilistic forecasters against weak or omitted baselines.
method A simple conformal interval with no parameters and no training.
result The ConformalNaive interval decisively beats several baselines.
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
Ground-A-Video edits videos without training, preserving intended changes.
problem Complex multi-attribute video editing with omitted or wrong changes.
method Grounding-guided video-to-video translation with Cross-Frame Gated Attention.
result Zero-shot multi-attribute video editing with improved accuracy and frame consistency.
New method uses diffusion models to solve inverse problems.
problem Solving ill-posed inverse problems with powerful priors.
method Formulate posterior sampling as a regularized Wasserstein gradient flow in latent space.
result Demonstrates improved performance on standard benchmarks.
CSP improves time-series forecasting without training, outperforming DeepNPTS in speed and accuracy.
problem Improving probabilistic time-series forecasting without training.
method Mixing empirical and residual draws around a seasonal naive forecast.
result CSP significantly outperforms DeepNPTS on CRPS, normalized mean quantile loss, and coverage metrics.
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.
A new differentiable resampling method for Monte Carlo simulations.
problem Improving the efficiency and differentiability of resampling in Monte Carlo simulations.
method Proposes a diffusion model surrogate for resampling, proving consistency and outperforming existing methods.
result The proposed method outperforms state-of-the-art differentiable resampling methods on various benchmarks.
TGD improves conditional sampling by concentrating computation on promising trajectories.
problem Efficiently training-free conditional sampling with diffusion priors.
method Tempered Guided Diffusion (TGD) using annealed sequential Monte Carlo.
result TGD yields a consistent particle approximation to the posterior as the number of particles grows.
Variance-Calibrated Modulation (VCM) addresses the likelihood trap in LLMs by reshaping the probability distribution before truncation.
problem LLMs fall into the likelihood trap, leading to repetitive degeneration and vocabulary dullness.
method VCM reshapes the probability distribution before truncation through Contextual Searchlight and Adaptive Self-Debiasing.
result VCM mitigates the likelihood trap across open-ended generation, factual QA, and mathematical reasoning.
Improves spline quality and accuracy in computational microscopy.
problem Detecting slender, overlapping structures in microscopy images.
method Differentiable rendering approach for spline refinement.
result Achieves high reliability and sub-pixel accuracy.
We present Graph Random Neural Features (GRNF), a novel embedding method from graph-structured data to real vectors based on a family of graph neural networks. The embedding naturally deals with graph isomorphism and preserves the metric structure of the graph domain, in probability. In addition to being an explicit em…
PiVoT improves real-time multi-object detection and tracking in clutter.
problem Challenges in multi-object detection and tracking from noisy point clouds.
method Variational inference for fast, clutter-resilient multi-object tracking.
result Substantial performance improvement over existing Bayesian trackers.
Paper uses RL and diffusion models to solve Bayesian inverse problems.
problem Bayesian inverse problems with latent biases.
method Relative Trajectory Balance (RTB) for RL, conditional diffusion models, off-policy backtracking exploration.
result RTB improves diffusion model posteriors for inverse problems.
Transformer models show distinct spectral fingerprints under voice changes.
problem Detecting architectural biases in transformer models.
method Spectral analysis of attention-induced token graphs.
result Clear architectural signatures in model fingerprints correlate with language-specific behavior.
Training-free source selection for LLM families with shared vocabularies
problem Source selection for LLM families with shared vocabularies
method Fisher alignment at vocabulary scale
result Fisher alignment is a cosine between kernel mean embeddings in the joint activation-error space
Paper proposes a new method to speed up diffusion models.
problem High computational cost of sampling from diffusion models.
method Stochastic Runge-Kutta method for acceleration.
result Provable acceleration with reduced score function evaluations.
Bayesian approach improves rain field reconstruction using CMLs and DMs.
problem Challenges in accurately reconstructing ground-level rainfall from CML path-integrated measurements.
method Bayesian inverse problem with Diffusion Models as priors.
result Improved performance in rainfall estimation compared to existing methods.
A new method improves Bayesian filtering in nonlinear systems.
problem Bayesian filtering in nonlinear dynamical systems with non-Gaussian posteriors.
method Transport maps with block-triangular structure and gradient flows for MMD minimization.
result Accurate approximation of non-Gaussian posteriors without particle collapse.
Method adapts frozen models for few-shot tasks without training.
problem Deployment constraints limit model updates, necessitating new adaptation methods.
method Exponential tilting of latent distribution for inference.
result Method outperforms parameter-update methods across benchmarks.
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.
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.
Stochastic attention learns to retrieve and generate from memory without training.
problem Learning to retrieve and generate from memory efficiently.
method Langevin dynamics on modern Hopfield energy for stochastic attention.
result Stochastic attention can retrieve and generate from memory without training, matching gold standards.
ResCP uses reservoir computing to create efficient, scalable time series prediction intervals.
problem Building distribution-free prediction intervals for time series data with small sample sizes and changing distributions.
method Reservoir Conformal Prediction (ResCP) leverages reservoir computing to dynamically reweight conformity scores based on similarity among reservoir states.
result ResCP achieves asymptotic conditional coverage and is effective across diverse forecasting tasks.
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.
Essential principal components simplify spectral analysis with minimal training data.
problem Accurate spectral quantification from complex mixtures.
method Identifying essential principal components and using molar extinction coefficients.
result Near one-to-one projection from principal components to mixture constituents.