Image de couverture de livre

Using GPUs And LLMs Can Be Satisfying for Nonlinear Real Arithmetic Problems

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Brix, Christopher, Walczak, Julia, Lommen, Nils, Noll, Thomas
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Learning-Based Ansatz Satisfying Boundary Conditions in Variational Problems
par: Florencio, Rafael, et autres
Publié: (2025)

ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
par: Yin, Junjie, et autres
Publié: (2023)

Transformers Can Do Arithmetic with the Right Embeddings
par: McLeish, Sean, et autres
Publié: (2024)

Performance and Efficiency of Climate In-Situ Data Reconstruction: Why Optimized IDW Outperforms kriging and Implicit Neural Representation
par: Walczak, Jakub
Publié: (2025)

Targeting Completeness: Using Closed Forms for Size Bounds of Integer Programs
par: Lommen, Nils, et autres
Publié: (2023)

Can LLMs subtract numbers?
par: Jobanputra, Mayank, et autres
Publié: (2025)

Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs
par: Dai, Rui, et autres
Publié: (2025)

Understanding GNNs for Boolean Satisfiability through Approximation Algorithms
par: Hůla, Jan, et autres
Publié: (2024)

On the Expressive Power of GNNs for Boolean Satisfiability
par: Peltonen, Saku, et autres
Publié: (2026)

Boolean Satisfiability via Imitation Learning
par: Zhang, Zewei, et autres
Publié: (2025)

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
par: Cho, Hanseul, et autres
Publié: (2024)

The Fifth International Verification of Neural Networks Competition (VNN-COMP 2024): Summary and Results
par: Brix, Christopher, et autres
Publié: (2024)

SplitQuantV2: Enhancing Low-Bit Quantization of LLMs Without GPUs
par: Song, Jaewoo, et autres
Publié: (2025)

The Unreasonable Effectiveness of Solving Inverse Problems with Neural Networks
par: Holl, Philipp, et autres
Publié: (2024)

Robustness Verification of Graph Neural Networks Via Lightweight Satisfiability Testing
par: Lu, Chia-Hsuan, et autres
Publié: (2025)

Learning to Solve Weighted Maximum Satisfiability with a Co-Training Architecture
par: Wan, Kaidi, et autres
Publié: (2025)

Benchmarking GPUs on SVBRDF Extractor Model
par: Kandel, Narayan, et autres
Publié: (2023)

The AI Definition and a Program Which Satisfies this Definition
par: Dobrev, Dimiter
Publié: (2022)

How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs
par: Feng, Guhao, et autres
Publié: (2024)

Using LLMs to Directly Guess Conditional Expectations Can Improve Efficiency in Causal Estimation
par: Engh, Chris, et autres
Publié: (2025)

Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
par: Abdali, Sara, et autres
Publié: (2024)

Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic
par: Saxena, Eshika, et autres
Publié: (2024)

Learning-Augmented Algorithms for Boolean Satisfiability
par: Attias, Idan, et autres
Publié: (2025)

Can LLMs Understand Time Series Anomalies?
par: Zhou, Zihao, et autres
Publié: (2024)

Can LLMs Lie? Investigation beyond Hallucination
par: Huan, Haoran, et autres
Publié: (2025)

On Revealing the Hidden Problem Structure in Real-World and Theoretical Problems Using Walsh Coefficient Influence
par: Przewozniczek, M. W., et autres
Publié: (2025)

Modular Automatic Complexity Analysis of Recursive Integer Programs
par: Lommen, Nils, et autres
Publié: (2025)

Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying Sufficiency
par: Benger, Etam, et autres
Publié: (2026)

Less Memory Means smaller GPUs: Backpropagation with Compressed Activations
par: Barley, Daniel, et autres
Publié: (2024)

Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
par: Zhou, Duo, et autres
Publié: (2024)

LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?
par: Ziomek, Juliusz, et autres
Publié: (2026)

PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training
par: Arfeen, Daiyaan, et autres
Publié: (2024)

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
par: Miserendino, Samuel, et autres
Publié: (2025)

LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs
par: Arabpour, Reza, et autres
Publié: (2025)

Learning Better Representations From Less Data For Propositional Satisfiability
par: Ghanem, Mohamed, et autres
Publié: (2024)

Conformalized Interval Arithmetic with Symmetric Calibration
par: Luo, Rui, et autres
Publié: (2024)

Text-Trained LLMs Can Zero-Shot Extrapolate PDE Dynamics, Revealing a Three-Stage In-Context Learning Mechanism
par: Bao, Jiajun, et autres
Publié: (2025)

Can LLMs Patch Security Issues?
par: Alrashedy, Kamel, et autres
Publié: (2023)

LTLDoG: Satisfying Temporally-Extended Symbolic Constraints for Safe Diffusion-based Planning
par: Feng, Zeyu, et autres
Publié: (2024)

Nonlinear Meta-Learning Can Guarantee Faster Rates
par: Meunier, Dimitri, et autres
Publié: (2023)