AI Infrastructure

GPUs, training clusters, MLOps, and deployment

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

Top This Week

[2604.01989] Attention at Rest Stays at Rest: Breaking Visual Inertia for Cognitive Hallucination Mitigation
Llms

[2604.01989] Attention at Rest Stays at Rest: Breaking Visual Inertia for Cognitive Hallucination Mitigation

Abstract page for arXiv paper 2604.01989: Attention at Rest Stays at Rest: Breaking Visual Inertia for Cognitive Hallucination Mitigation

arXiv - AI · 4 min ·
[2512.18809] FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation
Machine Learning

[2512.18809] FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation

Abstract page for arXiv paper 2512.18809: FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation

arXiv - AI · 4 min ·
[2512.08980] Training Multi-Image Vision Agents via End2End Reinforcement Learning
Machine Learning

[2512.08980] Training Multi-Image Vision Agents via End2End Reinforcement Learning

Abstract page for arXiv paper 2512.08980: Training Multi-Image Vision Agents via End2End Reinforcement Learning

arXiv - AI · 4 min ·

All Content

[2602.20677] UrbanFM: Scaling Urban Spatio-Temporal Foundation Models
Llms

[2602.20677] UrbanFM: Scaling Urban Spatio-Temporal Foundation Models

The paper presents UrbanFM, a novel framework for scaling urban spatio-temporal foundation models, addressing challenges in generalizabil...

arXiv - Machine Learning · 4 min ·
[2602.20676] PRECTR-V2:Unified Relevance-CTR Framework with Cross-User Preference Mining, Exposure Bias Correction, and LLM-Distilled Encoder Optimization
Llms

[2602.20676] PRECTR-V2:Unified Relevance-CTR Framework with Cross-User Preference Mining, Exposure Bias Correction, and LLM-Distilled Encoder Optimization

The paper presents PRECTR-V2, an advanced framework for improving search relevance and click-through rate (CTR) prediction by addressing ...

arXiv - AI · 4 min ·
[2602.20684] Agile V: A Compliance-Ready Framework for AI-Augmented Engineering -- From Concept to Audit-Ready Delivery
Machine Learning

[2602.20684] Agile V: A Compliance-Ready Framework for AI-Augmented Engineering -- From Concept to Audit-Ready Delivery

The paper presents Agile V, a framework integrating AI in engineering workflows to ensure compliance and verification at machine-speed de...

arXiv - AI · 4 min ·
[2602.20650] Dataset Color Quantization: A Training-Oriented Framework for Dataset-Level Compression
Machine Learning

[2602.20650] Dataset Color Quantization: A Training-Oriented Framework for Dataset-Level Compression

The paper presents Dataset Color Quantization (DCQ), a framework designed to compress large-scale image datasets by reducing color-space ...

arXiv - AI · 3 min ·
[2602.20595] OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services
Llms

[2602.20595] OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services

The paper presents OptiLeak, a framework utilizing reinforcement learning to enhance prompt reconstruction efficiency in multi-tenant LLM...

arXiv - AI · 4 min ·
[2602.20497] LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration
Machine Learning

[2602.20497] LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration

The paper introduces LESA, a framework for accelerating diffusion models using learnable stage-aware predictors, achieving significant sp...

arXiv - AI · 4 min ·
[2602.20467] Elimination-compensation pruning for fully-connected neural networks
Machine Learning

[2602.20467] Elimination-compensation pruning for fully-connected neural networks

This paper introduces a novel pruning method for fully-connected neural networks, which compensates for the removal of weights by adjusti...

arXiv - Machine Learning · 4 min ·
[2602.20449] Protein Language Models Diverge from Natural Language: Comparative Analysis and Improved Inference
Llms

[2602.20449] Protein Language Models Diverge from Natural Language: Comparative Analysis and Improved Inference

This article explores the differences between protein language models (PLMs) and natural language models, highlighting how these distinct...

arXiv - Machine Learning · 4 min ·
[2602.20442] Imputation of Unknown Missingness in Sparse Electronic Health Records
Machine Learning

[2602.20442] Imputation of Unknown Missingness in Sparse Electronic Health Records

The paper presents a novel algorithm for imputing unknown missing values in sparse electronic health records (EHRs) using a transformer-b...

arXiv - Machine Learning · 4 min ·
[2602.20400] Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation
Llms

[2602.20400] Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation

This article discusses three significant challenges and two potential solutions for improving the safety of unsupervised elicitation in l...

arXiv - Machine Learning · 4 min ·
[2602.20361] Learning During Detection: Continual Learning for Neural OFDM Receivers via DMRS
Machine Learning

[2602.20361] Learning During Detection: Continual Learning for Neural OFDM Receivers via DMRS

This paper presents a continual learning framework for neural OFDM receivers that allows for real-time adaptation to changing communicati...

arXiv - Machine Learning · 3 min ·
[2602.20332] No One Size Fits All: QueryBandits for Hallucination Mitigation
Llms

[2602.20332] No One Size Fits All: QueryBandits for Hallucination Mitigation

The paper introduces QueryBandits, a model-agnostic framework designed to mitigate hallucinations in large language models (LLMs) by opti...

arXiv - Machine Learning · 4 min ·
[2602.20292] Quantifying the Expectation-Realisation Gap for Agentic AI Systems
Ai Infrastructure

[2602.20292] Quantifying the Expectation-Realisation Gap for Agentic AI Systems

This article examines the expectation-realisation gap in agentic AI systems, revealing discrepancies between anticipated productivity gai...

arXiv - AI · 3 min ·
[2602.20271] Uncertainty-Aware Delivery Delay Duration Prediction via Multi-Task Deep Learning
Machine Learning

[2602.20271] Uncertainty-Aware Delivery Delay Duration Prediction via Multi-Task Deep Learning

This paper presents a multi-task deep learning model for predicting delivery delay durations in logistics, addressing challenges posed by...

arXiv - Machine Learning · 4 min ·
[2602.20217] KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
Llms

[2602.20217] KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem

The paper introduces KnapSpec, a framework for self-speculative decoding that optimizes layer selection in LLMs as a knapsack problem, en...

arXiv - Machine Learning · 4 min ·
[2602.20214] Right to History: A Sovereignty Kernel for Verifiable AI Agent Execution
Ai Safety

[2602.20214] Right to History: A Sovereignty Kernel for Verifiable AI Agent Execution

This paper proposes the 'Right to History,' a principle ensuring individuals have a verifiable record of AI agent actions on personal har...

arXiv - AI · 3 min ·
[2602.20208] Model Merging in the Essential Subspace
Machine Learning

[2602.20208] Model Merging in the Essential Subspace

This paper presents ESM, a novel framework for merging multiple task-specific models into a single multi-task model, addressing inter-tas...

arXiv - Machine Learning · 3 min ·
[2602.20207] Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
Llms

[2602.20207] Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis

This article discusses the concept of 'golden layers' in large language models (LLMs) and presents a novel method, Layer Gradient Analysi...

arXiv - AI · 4 min ·
[2602.20204] Analyzing Latency Hiding and Parallelism in an MLIR-based AI Kernel Compiler
Machine Learning

[2602.20204] Analyzing Latency Hiding and Parallelism in an MLIR-based AI Kernel Compiler

This paper analyzes the effectiveness of latency hiding and parallelism techniques in an MLIR-based AI kernel compiler, focusing on vecto...

arXiv - AI · 3 min ·
[2602.20200] Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation
Machine Learning

[2602.20200] Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation

The paper presents OptimusVLA, a dual-memory framework for robotic manipulation that enhances efficiency and robustness in action generat...

arXiv - AI · 4 min ·
Previous Page 87 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