AI Infrastructure

GPUs, training clusters, MLOps, and deployment

This Week's Best | Monthly Best | Guide | Trending

Top This Week

UMKC Announces New Master of Science in Artificial Intelligence
Ai Infrastructure

UMKC Announces New Master of Science in Artificial Intelligence

UMKC announces a new Master of Science in Artificial Intelligence program aimed at addressing workforce demand for AI expertise, set to l...

AI News - General · 4 min ·
[2604.07486] Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation
Llms

[2604.07486] Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation

Abstract page for arXiv paper 2604.07486: Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation

arXiv - AI · 3 min ·
[2601.14477] XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generation
Llms

[2601.14477] XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data Generation

Abstract page for arXiv paper 2601.14477: XD-MAP: Cross-Modal Domain Adaptation via Semantic Parametric Maps for Scalable Training Data G...

arXiv - AI · 4 min ·

All Content

[2504.06768] FedMerge: Federated Personalization via Model Merging
Machine Learning

[2504.06768] FedMerge: Federated Personalization via Model Merging

The paper introduces FedMerge, a novel approach in federated learning that enables personalized model creation for clients by merging mul...

arXiv - Machine Learning · 4 min ·
[2504.05615] FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels
Machine Learning

[2504.05615] FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels

The paper presents FedEFC, a novel approach to federated learning that addresses the challenges posed by noisy labels through techniques ...

arXiv - Machine Learning · 4 min ·
[2601.01569] CaveAgent: Transforming LLMs into Stateful Runtime Operators
Llms

[2601.01569] CaveAgent: Transforming LLMs into Stateful Runtime Operators

CaveAgent introduces a novel framework that transforms LLMs into stateful runtime operators, enhancing their ability to manage complex ta...

arXiv - AI · 4 min ·
[2510.12121] Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
Llms

[2510.12121] Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing

This paper introduces a method for precise control of attribute intensities in Large Language Models (LLMs) through targeted representati...

arXiv - Machine Learning · 4 min ·
[2502.07274] Forget Forgetting: Continual Learning in a World of Abundant Memory
Machine Learning

[2502.07274] Forget Forgetting: Continual Learning in a World of Abundant Memory

The paper explores continual learning (CL) in AI, proposing a shift from minimizing memory usage to leveraging abundant memory while addr...

arXiv - Machine Learning · 4 min ·
[2502.00213] Understanding Transformer Optimization via Gradient Heterogeneity
Machine Learning

[2502.00213] Understanding Transformer Optimization via Gradient Heterogeneity

This paper explores the optimization challenges of Transformer models, focusing on gradient heterogeneity and its impact on convergence w...

arXiv - Machine Learning · 4 min ·
[2509.00074] Language and Experience: A Computational Model of Social Learning in Complex Tasks
Machine Learning

[2509.00074] Language and Experience: A Computational Model of Social Learning in Complex Tasks

This article presents a computational model that explores how humans and AI can integrate linguistic guidance and direct experience for e...

arXiv - Machine Learning · 4 min ·
[2409.04332] Amortized Bayesian Workflow
Machine Learning

[2409.04332] Amortized Bayesian Workflow

The paper presents an Amortized Bayesian Workflow that combines fast amortized inference with accurate MCMC techniques, optimizing Bayesi...

arXiv - Machine Learning · 3 min ·
[2411.04760] Zero-Shot Temporal Resolution Domain Adaptation for Spiking Neural Networks
Machine Learning

[2411.04760] Zero-Shot Temporal Resolution Domain Adaptation for Spiking Neural Networks

This paper presents novel domain adaptation methods for Spiking Neural Networks (SNNs) to address performance drops due to mismatched tem...

arXiv - Machine Learning · 4 min ·
[2602.16690] Synthetic-Powered Multiple Testing with FDR Control
Machine Learning

[2602.16690] Synthetic-Powered Multiple Testing with FDR Control

The paper presents SynthBH, a novel method for multiple hypothesis testing that integrates synthetic data to enhance statistical inferenc...

arXiv - Machine Learning · 3 min ·
[2502.01160] Scalable Precise Computation of Shannon Entropy
Machine Learning

[2502.01160] Scalable Precise Computation of Shannon Entropy

This paper presents a scalable tool, PSE, for precise computation of Shannon entropy, optimizing the process to enhance efficiency in qua...

arXiv - AI · 4 min ·
[2602.16660] Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment
Llms

[2602.16660] Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment

The paper presents a method for enhancing multilingual safety alignment in large language models (LLMs) using a resource-efficient Multi-...

arXiv - Machine Learning · 4 min ·
[2602.16612] Causal and Compositional Abstraction
Machine Learning

[2602.16612] Causal and Compositional Abstraction

The paper presents a formal framework for causal and compositional abstraction, emphasizing its significance in AI and scientific practic...

arXiv - AI · 4 min ·
[2602.16603] FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving
Llms

[2602.16603] FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving

The paper presents FlowPrefill, a novel system designed to optimize large language model (LLM) serving by decoupling preemption from sche...

arXiv - AI · 4 min ·
[2602.16585] DataJoint 2.0: A Computational Substrate for Agentic Scientific Workflows
Machine Learning

[2602.16585] DataJoint 2.0: A Computational Substrate for Agentic Scientific Workflows

DataJoint 2.0 introduces a relational workflow model designed to enhance collaboration in scientific data pipelines, ensuring data integr...

arXiv - AI · 3 min ·
[2602.16320] RefineFormer3D: Efficient 3D Medical Image Segmentation via Adaptive Multi-Scale Transformer with Cross Attention Fusion
Machine Learning

[2602.16320] RefineFormer3D: Efficient 3D Medical Image Segmentation via Adaptive Multi-Scale Transformer with Cross Attention Fusion

RefineFormer3D presents a lightweight transformer architecture for 3D medical image segmentation, achieving high accuracy with significan...

arXiv - Machine Learning · 4 min ·
[2602.16233] DistributedEstimator: Distributed Training of Quantum Neural Networks via Circuit Cutting
Machine Learning

[2602.16233] DistributedEstimator: Distributed Training of Quantum Neural Networks via Circuit Cutting

The paper presents a novel approach to distributed training of quantum neural networks using circuit cutting, addressing overheads and pe...

arXiv - Machine Learning · 4 min ·
[2602.16430] Designing Production-Scale OCR for India: Multilingual and Domain-Specific Systems
Llms

[2602.16430] Designing Production-Scale OCR for India: Multilingual and Domain-Specific Systems

This article discusses the development of production-scale Optical Character Recognition (OCR) systems tailored for India's multilingual ...

arXiv - AI · 3 min ·
[2602.16148] Local adapt-then-combine algorithms for distributed nonsmooth optimization: Achieving provable communication acceleration
Nlp

[2602.16148] Local adapt-then-combine algorithms for distributed nonsmooth optimization: Achieving provable communication acceleration

This paper introduces FlexATC, a communication-efficient framework for distributed nonsmooth optimization, achieving notable convergence ...

arXiv - Machine Learning · 3 min ·
[2602.16132] CHAI: CacHe Attention Inference for text2video
Machine Learning

[2602.16132] CHAI: CacHe Attention Inference for text2video

The paper presents CHAI, a novel approach to enhance text-to-video generation by utilizing Cache Attention for efficient inference, achie...

arXiv - Machine Learning · 3 min ·
Previous Page 142 Next

Related Topics

Machine Learning Large Language Models Generative AI Natural Language Processing Computer Vision Robotics & Embodied AI

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Subscribe to Newsletter

Daily or weekly digest • Unsubscribe anytime