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

1122 · Mar 202619922001200920172026
16 results for Sudoku

We introduce Deep Reasoning Networks (DRNets), an end-to-end framework that combines deep learning with reasoning for solving complex tasks, typically in an unsupervised or weakly-supervised setting. DRNets exploit problem structure and prior knowledge by tightly combining logic and constraint reasoning with stochastic…

2019-06-03abs ↗pdf ↗

Neural framework learns one solution from multiple for combinatorial problems.

problem Finding any one of many possible solutions for combinatorial problems.
method Adapts existing prediction networks to handle solution multiplicity using a selection module trained via RL.
result Framework significantly improves accuracy in solving combinatorial problems.

Paper presents a framework to automatically discover constraints from data.

problem Discovering constraints from data for structured output prediction.
method Formulates structured output prediction as ILP, mines constraints by estimating polytopes of feasible set.
result Successfully identifies feasible sets and constraints for various tasks.

Proposes a method to generate text that adheres to logical constraints.

problem Generating text that respects logical constraints is hard for autoregressive models.
method Bayesian conditioning to draw samples subject to a constraint, considering the entire sequence and inducing a local, factorized distribution.
result Our approach generates samples that closely approximate the target distribution and are guaranteed to satisfy the constraints.

DTM improves dLLM fine-tuning stability and performance.

problem Intractable sequence-level marginal likelihoods for masked diffusion models.
method Discrete Tilt Matching (DTM) recasts dLLM fine-tuning as state-level matching of local unmasking posteriors under reward tilting.
result DTM yields strong gains on Sudoku and Countdown while remaining competitive on MATH500 and GSM8K.

This paper presents OptNet, a network architecture that integrates optimization problems (here, specifically in the form of quadratic programs) as individual layers in larger end-to-end trainable deep networks. These layers encode constraints and complex dependencies between the hidden states that traditional convoluti…

2017-03-01abs ↗pdf ↗

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.

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-NN.

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.