AI Infrastructure

GPUs, training clusters, MLOps, and deployment

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

Top This Week

[2603.15159] To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation
Llms

[2603.15159] To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation

Abstract page for arXiv paper 2603.15159: To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation

arXiv - AI · 4 min ·
[2602.07374] TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Layer-wise Scaling
Llms

[2602.07374] TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Layer-wise Scaling

Abstract page for arXiv paper 2602.07374: TernaryLM: Memory-Efficient Language Modeling via Native 1.5-Bit Quantization with Adaptive Lay...

arXiv - AI · 4 min ·
[2512.11798] Particulate: Feed-Forward 3D Object Articulation
Machine Learning

[2512.11798] Particulate: Feed-Forward 3D Object Articulation

Abstract page for arXiv paper 2512.11798: Particulate: Feed-Forward 3D Object Articulation

arXiv - AI · 3 min ·

All Content

[2603.21720] SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models
Llms

[2603.21720] SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for Large Language Models

Abstract page for arXiv paper 2603.21720: SemEval-2026 Task 12: Abductive Event Reasoning: Towards Real-World Event Causal Inference for ...

arXiv - AI · 3 min ·
[2603.21701] Rethinking Token Reduction for Large Vision-Language Models
Llms

[2603.21701] Rethinking Token Reduction for Large Vision-Language Models

Abstract page for arXiv paper 2603.21701: Rethinking Token Reduction for Large Vision-Language Models

arXiv - AI · 4 min ·
[2603.21661] Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesis
Machine Learning

[2603.21661] Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesis

Abstract page for arXiv paper 2603.21661: Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-...

arXiv - Machine Learning · 4 min ·
[2603.21610] Rule-State Inference (RSI): A Bayesian Framework for Compliance Monitoring in Rule-Governed Domains
Machine Learning

[2603.21610] Rule-State Inference (RSI): A Bayesian Framework for Compliance Monitoring in Rule-Governed Domains

Abstract page for arXiv paper 2603.21610: Rule-State Inference (RSI): A Bayesian Framework for Compliance Monitoring in Rule-Governed Dom...

arXiv - Machine Learning · 4 min ·
[2603.21576] PRISM: Breaking the O(n) Memory Wall in Long-Context LLM Inference via O(1) Photonic Block Selection
Llms

[2603.21576] PRISM: Breaking the O(n) Memory Wall in Long-Context LLM Inference via O(1) Photonic Block Selection

Abstract page for arXiv paper 2603.21576: PRISM: Breaking the O(n) Memory Wall in Long-Context LLM Inference via O(1) Photonic Block Sele...

arXiv - Machine Learning · 4 min ·
[2603.21508] Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences
Machine Learning

[2603.21508] Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences

Abstract page for arXiv paper 2603.21508: Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences

arXiv - Machine Learning · 4 min ·
[2603.21461] DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment
Machine Learning

[2603.21461] DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment

Abstract page for arXiv paper 2603.21461: DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment

arXiv - Machine Learning · 3 min ·
[2603.21301] enhancing reasoning accuracy in large language models during inference time
Llms

[2603.21301] enhancing reasoning accuracy in large language models during inference time

Abstract page for arXiv paper 2603.21301: enhancing reasoning accuracy in large language models during inference time

arXiv - AI · 4 min ·
[2603.21280] WARBENCH: A Comprehensive Benchmark for Evaluating LLMs in Military Decision-Making
Llms

[2603.21280] WARBENCH: A Comprehensive Benchmark for Evaluating LLMs in Military Decision-Making

Abstract page for arXiv paper 2603.21280: WARBENCH: A Comprehensive Benchmark for Evaluating LLMs in Military Decision-Making

arXiv - AI · 4 min ·
[2603.21175] Reward Sharpness-Aware Fine-Tuning for Diffusion Models
Llms

[2603.21175] Reward Sharpness-Aware Fine-Tuning for Diffusion Models

Abstract page for arXiv paper 2603.21175: Reward Sharpness-Aware Fine-Tuning for Diffusion Models

arXiv - Machine Learning · 3 min ·
[2603.21135] One Pool Is Not Enough: Multi-Cluster Memory for Practical Test-Time Adaptation
Machine Learning

[2603.21135] One Pool Is Not Enough: Multi-Cluster Memory for Practical Test-Time Adaptation

Abstract page for arXiv paper 2603.21135: One Pool Is Not Enough: Multi-Cluster Memory for Practical Test-Time Adaptation

arXiv - AI · 4 min ·
[2603.21095] Representation-Level Adversarial Regularization for Clinically Aligned Multitask Thyroid Ultrasound Assessment
Ai Infrastructure

[2603.21095] Representation-Level Adversarial Regularization for Clinically Aligned Multitask Thyroid Ultrasound Assessment

Abstract page for arXiv paper 2603.21095: Representation-Level Adversarial Regularization for Clinically Aligned Multitask Thyroid Ultras...

arXiv - AI · 4 min ·
[2603.21084] ViCLSR: A Supervised Contrastive Learning Framework with Natural Language Inference for Natural Language Understanding Tasks
Machine Learning

[2603.21084] ViCLSR: A Supervised Contrastive Learning Framework with Natural Language Inference for Natural Language Understanding Tasks

Abstract page for arXiv paper 2603.21084: ViCLSR: A Supervised Contrastive Learning Framework with Natural Language Inference for Natural...

arXiv - Machine Learning · 4 min ·
[2603.21045] LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction
Machine Learning

[2603.21045] LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction

Abstract page for arXiv paper 2603.21045: LPNSR: Prior-Enhanced Diffusion Image Super-Resolution via LR-Guided Noise Prediction

arXiv - AI · 4 min ·
[2603.21016] Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO
Llms

[2603.21016] Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO

Abstract page for arXiv paper 2603.21016: Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO

arXiv - Machine Learning · 3 min ·
[2603.20980] From Causal Discovery to Dynamic Causal Inference in Neural Time Series
Machine Learning

[2603.20980] From Causal Discovery to Dynamic Causal Inference in Neural Time Series

Abstract page for arXiv paper 2603.20980: From Causal Discovery to Dynamic Causal Inference in Neural Time Series

arXiv - Machine Learning · 4 min ·
[2603.20957] Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models
Llms

[2603.20957] Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models

Abstract page for arXiv paper 2603.20957: Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Lan...

arXiv - AI · 4 min ·
[2603.20920] Democratizing AI: A Comparative Study in Deep Learning Efficiency and Future Trends in Computational Processing
Machine Learning

[2603.20920] Democratizing AI: A Comparative Study in Deep Learning Efficiency and Future Trends in Computational Processing

Abstract page for arXiv paper 2603.20920: Democratizing AI: A Comparative Study in Deep Learning Efficiency and Future Trends in Computat...

arXiv - Machine Learning · 4 min ·
[2603.20899] Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach
Llms

[2603.20899] Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach

Abstract page for arXiv paper 2603.20899: Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach

arXiv - AI · 3 min ·
[2603.20882] RubricRAG: Towards Interpretable and Reliable LLM Evaluation via Domain Knowledge Retrieval for Rubric Generation
Llms

[2603.20882] RubricRAG: Towards Interpretable and Reliable LLM Evaluation via Domain Knowledge Retrieval for Rubric Generation

Abstract page for arXiv paper 2603.20882: RubricRAG: Towards Interpretable and Reliable LLM Evaluation via Domain Knowledge Retrieval for...

arXiv - Machine Learning · 4 min ·
Previous Page 19 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