constraint-satisfaction

Tag

Cards List
#constraint-satisfaction

Integrating Physics-Informed Neural Networks for Safe Reinforcement Learning in a 1-DoF Helicopter System

arXiv cs.LG · 2026-07-07 Cached

This work-in-progress paper proposes embedding a differentiable physics model into the PPO actor loss function to penalize anticipated safety violations in reinforcement learning, evaluated on a simulated 1-DoF helicopter system. The physics-informed soft regularizations reduce constraint violations while maintaining reliable target tracking.

0 favorites 0 likes
#constraint-satisfaction

@gklambauer: G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models Symbolic solver have to branch to check different choic…

X AI KOLs Timeline · 2026-07-03 Cached

This paper introduces G-RRM, a neuro-symbolic approach that uses recurrent reasoning models to guide symbolic solvers for constraint satisfaction problems, showing significant speedups in certain conditions.

0 favorites 0 likes
#constraint-satisfaction

Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement

arXiv cs.AI · 2026-06-30 Cached

Flow Reasoning Models (FRMs) introduce a training and test-time-scaling framework for discrete flow models on structured reasoning tasks. By using self-verification and self-conditioning, FRMs achieve nearly 100% solve rates on Sudoku and Zebra puzzles with far fewer passes than previous baselines.

0 favorites 0 likes
#constraint-satisfaction

FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows

Hugging Face Daily Papers · 2026-06-18 Cached

FlowBender is a closed-loop framework that improves constraint satisfaction in diffusion and flow models by training networks to correct alignment errors using inference-time feedback, outperforming traditional supervised and guidance-based approaches.

0 favorites 0 likes
#constraint-satisfaction

REVES: REvision and VErification--Augmented Training for Test-Time Scaling

Hugging Face Daily Papers · 2026-06-17 Cached

Proposes REVES, a two-stage iterative framework that alternates between data augmentation and policy optimization to improve LLM reasoning by leveraging intermediate correction steps, achieving superior performance on coding benchmarks and constraint satisfaction problems.

0 favorites 0 likes
#constraint-satisfaction

DiBS: Diffusion-Informed Branch Selection

arXiv cs.AI · 2026-06-08 Cached

Proposes DiBS, a diffusion model-guided approach for branch selection in exact Sudoku solvers that reduces search cost without sacrificing completeness, supported by theoretical proof and empirical results on the Royle 17-clue benchmark.

0 favorites 0 likes
#constraint-satisfaction

Constraint-Enhanced Physical Search through Correlation Matching

arXiv cs.AI · 2026-06-04 Cached

This paper proposes a principle of 'constraint-enhanced physical search' where temporal correlations in exploration are matched to constraint-induced spatial correlations in update dynamics, demonstrated via a tug-of-war bandit model. The authors show that efficient search emerges not from maximal randomness but from matching temporal correlation to the physical update scale that converts feedback into evidence.

0 favorites 0 likes
#constraint-satisfaction

DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers

arXiv cs.LG · 2026-06-01 Cached

Introduces DisjunctiveNet, a unified end-to-end framework for enforcing hard, input-dependent mixed integer linear constraints within neural networks via differentiable convexified optimization layers, achieving perfect rule satisfaction on real-world datasets.

0 favorites 0 likes
#constraint-satisfaction

PhyDrawGen: Physically Grounded Diagram Generation from Natural Language

arXiv cs.AI · 2026-06-01 Cached

PhyDrawGen is a neuro-symbolic pipeline that generates physically accurate diagrams from natural language by combining LLM-based scene understanding with a deterministic constraint solver and a VLM-based verify loop, outperforming existing models on a benchmark of physics problems.

0 favorites 0 likes
#constraint-satisfaction

ContextGuard: Structured Self-Auditing for Context Learning in Language Models

arXiv cs.CL · 2026-05-27 Cached

Introduces ContextGuard, a structured self-auditing framework that improves LLM context learning by decomposing model self-assessment into confirmed and uncertain categories and applying targeted revisions, achieving a task-solving rate increase from 9.64% to 13.85% on Qwen3.5-4B on the CL-Bench benchmark.

0 favorites 0 likes
#constraint-satisfaction

Constrained Code Generation with Discrete Diffusion

arXiv cs.CL · 2026-05-19 Cached

This paper introduces Constrained Diffusion for Code (CDC), a training-free neurosymbolic inference framework that integrates constraint satisfaction directly into the reverse denoising process of discrete diffusion models for code generation. CDC consistently improves constraint satisfaction in functional correctness, security, and syntax across benchmarks, outperforming existing diffusion and autoregressive baselines.

0 favorites 0 likes
#constraint-satisfaction

Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards

arXiv cs.CL · 2026-05-15 Cached

This paper introduces a text-based approach for generative floor plan design that fine-tunes a large language model with reinforcement learning and verifiable rewards to improve adherence to topological and numerical constraints, achieving significant improvements over existing methods.

0 favorites 0 likes
← Back to home

Submit Feedback