Train with Terabyte-Scale Datasets on a Single NVIDIA Grace Hopper Superchip Using XGBoost 3.0
developer.nvidia.com·4d
📊AI Performance Profiling
From Explainable to Explanatory Artificial Intelligence: Toward a New Paradigm for Human-Centered Explanations through Generative AI
arxiv.org·3h
⚙️AI Infrastructure Automation
FairPOT: Balancing AUC Performance and Fairness with Proportional Optimal Transport
arxiv.org·4d
🧠Large Language Models (LLMs)
Hacking Hallucinations of MLLMs with Causal Sufficiency and Necessity
arxiv.org·4d
🧠Large Language Models (LLMs)
A 3DGS-Diffusion Self-Supervised Framework for Normal Estimation from a Single Image
arxiv.org·3h
🔢Quantization of LLMs
Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment
arxiv.org·4d
🔢Quantization of LLMs
A New Lens on Homelessness: Daily Tent Monitoring with 311 Calls and Street Images
arxiv.org·3h
🌐Distributed LLM Systems
Accelerating SGDM via Learning Rate and Batch Size Schedules: A Lyapunov-Based Analysis
arxiv.org·5d
✨Model optimizations in LLMs
NomicLaw: Emergent Trust and Strategic Argumentation in LLMs During Collaborative Law-Making
arxiv.org·3d
🧠Large Language Models (LLMs)
Transformer-Based Explainable Deep Learning for Breast Cancer Detection in Mammography: The MammoFormer Framework
arxiv.org·3h
🔍Retrieval-augmented generation
LLMs Have a Heart of Stone: Demystifying the Soft Thinking Ability of Large Reasoning Models
arxiv.org·5d
🧠Large Language Models (LLMs)
DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition
arxiv.org·3d
🧠Large Language Models (LLMs)
Deconstructing the Crystal Ball: From Ad-Hoc Prediction to Principled Startup Evaluation with the SAISE Framework
arxiv.org·3d
📊AI Performance Profiling
Stepwise Fine and Gray: Subject-Specific Variable Selection Shows When Hemodynamic Data Improves Prognostication of Comatose Post-Cardiac Arrest Patients
arxiv.org·3h
⚡Real-time AI Systems
FVGen: Accelerating Novel-View Synthesis with Adversarial Video Diffusion Distillation
arxiv.org·3h
🔍Retrieval-augmented generation
An Explainable Machine Learning Framework for Railway Predictive Maintenance using Data Streams from the Metro Operator of Portugal
arxiv.org·3d
⚙️AI Infrastructure Automation
Refine-n-Judge: Curating High-Quality Preference Chains for LLM-Fine-Tuning
arxiv.org·6d
🧠Large Language Models (LLMs)
How and Why: Taming Flow Matching for Unsupervised Anomaly Detection and Localization
arxiv.org·3d
📊AI Performance Profiling
HALO: Hindsight-Augmented Learning for Online Auto-Bidding
arxiv.org·5d
🧠Large Language Models (LLMs)
Street View Sociability: Interpretable Analysis of Urban Social Behavior Across 15 Cities
arxiv.org·3h
🧠Large Language Models (LLMs)