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

count % of corpus

9 results for “reward-guided”

Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlocs.LG

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.

Sequential Monte Carlo Reward-guided decoding Large language models Training-free Sequence quality

2026-04-07abs ↗pdf ↗

Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Designcs.LG

A novel framework refines diffusion models iteratively for better downstream reward optimization.

problem Optimizing reward functions during inference of diffusion models.

method Iterative refinement process with noising and reward-guided denoising steps.

result Superior empirical performance in protein and DNA design.

diffusion models reward optimization iterative refinement protein design DNA design

2025-02-20abs ↗pdf ↗

Towards a unified framework for guided diffusion modelsstat.ML

Unified framework improves diffusion model rewards without full trajectories.

problem Limited theoretical understanding of guided diffusion samplers.

method Developed a unified algorithmic and theoretical framework for diffusion guidance and reward-guided diffusion.

result Framework shows CFG decreases expected reciprocal of classifier probability.

diffusion models reward-guided classifier-free guidance reward improvement unified framework

2025-12-04abs ↗pdf ↗

Guided Speculative Inference for Efficient Test-Time Alignment of LLMscs.LG

GSI improves efficiency of large language model inference.

problem Efficiently guiding test-time alignment in large language models.

method Combines soft best-of-

n

scaling with a reward model and speculative samples.

result Achieves higher accuracy and reduced latency compared to standard methods.

Large Language Models Test-Time Alignment Reward Guidance Speculative Decoding Efficiency Improvements

2025-06-04abs ↗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 ↗

Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Reviewcs.AI

Tutorial on optimizing diffusion model samples for specific metrics.

problem Optimizing diffusion model samples for specific downstream metrics.

method Review and exploration of inference-time guidance and alignment methods.

result Unified perspective on inference-time algorithms and novel methods.

Diffusion models Inference-time alignment Reward-guided generation Sequential Monte Carlo Value-based sampling

2025-01-16abs ↗pdf ↗

DeepSmartFuzzer: Reward Guided Test Generation For Deep Learningcs.LG

Testing Deep Neural Network (DNN) models has become more important than ever with the increasing usage of DNN models in safety-critical domains such as autonomous cars. The traditional approach of testing DNNs is to create a test set, which is a random subset of the dataset about the problem of interest. This kind of a…

2019-11-24abs ↗pdf ↗

Training Large Language Models to Reason via EM Policy Gradientcs.LG

Enhances large language models' reasoning through simpler off-policy reinforcement learning.

problem Improving large language models' ability to reason and solve problems.

method EM Policy Gradient, optimizing expected return over reasoning trajectories using Expectation-Maximization (EM) optimization.

result Achieves comparable or slightly superior performance to state-of-the-art methods on reasoning datasets, with additional cognitive behaviors.

large language models reinforcement learning reasoning off-policy EM optimization

2025-04-24abs ↗pdf ↗

Learn to Guide Your Diffusion Modelcs.LG

A new method learns continuous guidance weights to improve diffusion model quality and distributional alignment.

problem Improving perceptual quality and distributional alignment of samples from conditional diffusion models.

method Learned continuous guidance weights

ω_{c,(s,t)}

are used to minimize distributional mismatch and reward guided sampling.

result Improvements in Fréchet inception distance (FID) for image generation and better image-prompt alignment in text-to-image applications.

classifier-free guidance diffusion models distributional alignment reward functions image generation

2025-10-01abs ↗pdf ↗