Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Brix, Christopher, Walczak, Julia, Lommen, Nils, Noll, Thomas
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Learning-Based Ansatz Satisfying Boundary Conditions in Variational Problems
di: Florencio, Rafael, et al.
Pubblicazione: (2025)

ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
di: Yin, Junjie, et al.
Pubblicazione: (2023)

Transformers Can Do Arithmetic with the Right Embeddings
di: McLeish, Sean, et al.
Pubblicazione: (2024)

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

Targeting Completeness: Using Closed Forms for Size Bounds of Integer Programs
di: Lommen, Nils, et al.
Pubblicazione: (2023)

Can LLMs subtract numbers?
di: Jobanputra, Mayank, et al.
Pubblicazione: (2025)

Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs
di: Dai, Rui, et al.
Pubblicazione: (2025)

Understanding GNNs for Boolean Satisfiability through Approximation Algorithms
di: Hůla, Jan, et al.
Pubblicazione: (2024)

On the Expressive Power of GNNs for Boolean Satisfiability
di: Peltonen, Saku, et al.
Pubblicazione: (2026)

Boolean Satisfiability via Imitation Learning
di: Zhang, Zewei, et al.
Pubblicazione: (2025)

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
di: Cho, Hanseul, et al.
Pubblicazione: (2024)

The Fifth International Verification of Neural Networks Competition (VNN-COMP 2024): Summary and Results
di: Brix, Christopher, et al.
Pubblicazione: (2024)

SplitQuantV2: Enhancing Low-Bit Quantization of LLMs Without GPUs
di: Song, Jaewoo, et al.
Pubblicazione: (2025)

The Unreasonable Effectiveness of Solving Inverse Problems with Neural Networks
di: Holl, Philipp, et al.
Pubblicazione: (2024)

Robustness Verification of Graph Neural Networks Via Lightweight Satisfiability Testing
di: Lu, Chia-Hsuan, et al.
Pubblicazione: (2025)

Learning to Solve Weighted Maximum Satisfiability with a Co-Training Architecture
di: Wan, Kaidi, et al.
Pubblicazione: (2025)

Benchmarking GPUs on SVBRDF Extractor Model
di: Kandel, Narayan, et al.
Pubblicazione: (2023)

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

How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs
di: Feng, Guhao, et al.
Pubblicazione: (2024)

Using LLMs to Directly Guess Conditional Expectations Can Improve Efficiency in Causal Estimation
di: Engh, Chris, et al.
Pubblicazione: (2025)

Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
di: Abdali, Sara, et al.
Pubblicazione: (2024)

Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic
di: Saxena, Eshika, et al.
Pubblicazione: (2024)

Learning-Augmented Algorithms for Boolean Satisfiability
di: Attias, Idan, et al.
Pubblicazione: (2025)

Can LLMs Understand Time Series Anomalies?
di: Zhou, Zihao, et al.
Pubblicazione: (2024)

Can LLMs Lie? Investigation beyond Hallucination
di: Huan, Haoran, et al.
Pubblicazione: (2025)

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

Modular Automatic Complexity Analysis of Recursive Integer Programs
di: Lommen, Nils, et al.
Pubblicazione: (2025)

Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying Sufficiency
di: Benger, Etam, et al.
Pubblicazione: (2026)

Less Memory Means smaller GPUs: Backpropagation with Compressed Activations
di: Barley, Daniel, et al.
Pubblicazione: (2024)

Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
di: Zhou, Duo, et al.
Pubblicazione: (2024)

LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?
di: Ziomek, Juliusz, et al.
Pubblicazione: (2026)

PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training
di: Arfeen, Daiyaan, et al.
Pubblicazione: (2024)

SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?
di: Miserendino, Samuel, et al.
Pubblicazione: (2025)

LoRA Fine-Tuning Without GPUs: A CPU-Efficient Meta-Generation Framework for LLMs
di: Arabpour, Reza, et al.
Pubblicazione: (2025)

Learning Better Representations From Less Data For Propositional Satisfiability
di: Ghanem, Mohamed, et al.
Pubblicazione: (2024)

Conformalized Interval Arithmetic with Symmetric Calibration
di: Luo, Rui, et al.
Pubblicazione: (2024)

Text-Trained LLMs Can Zero-Shot Extrapolate PDE Dynamics, Revealing a Three-Stage In-Context Learning Mechanism
di: Bao, Jiajun, et al.
Pubblicazione: (2025)

Can LLMs Patch Security Issues?
di: Alrashedy, Kamel, et al.
Pubblicazione: (2023)

LTLDoG: Satisfying Temporally-Extended Symbolic Constraints for Safe Diffusion-based Planning
di: Feng, Zeyu, et al.
Pubblicazione: (2024)

Nonlinear Meta-Learning Can Guarantee Faster Rates
di: Meunier, Dimitri, et al.
Pubblicazione: (2023)