Multi-Amateur Contrastive Decoding for Text Generation
arxiv.org·6d
🧠Large Language Models (LLMs)
Active IRS-Enabled Integrated Sensing and Communications with Extended Targets
arxiv.org·1d
🔧Systems-level optimizations for LLM serving
Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training
arxiv.org·5d
📊AI Performance Profiling
The Role of Review Process Failures in Affective State Estimation: An Empirical Investigation of DEAP Dataset
arxiv.org·1h
📊AI Performance Profiling
Regime-Aware Conditional Neural Processes with Multi-Criteria Decision Support for Operational Electricity Price Forecasting
arxiv.org·1d
🧠Large Language Models (LLMs)
The Manipulative Power of Voice Characteristics: Investigating Deceptive Patterns in Mandarin Chinese Female Synthetic Speech
arxiv.org·1d
🧠Large Language Models (LLMs)
PointGauss: Point Cloud-Guided Multi-Object Segmentation for Gaussian Splatting
arxiv.org·1d
🔢Quantization of LLMs
Estimating Reliability of Electric Vehicle Charging Ecosystem using the Principle of Maximum Entropy
arxiv.org·1h
⚙️AI Infrastructure Automation
Post-Training Large Language Models via Reinforcement Learning from Self-Feedback
arxiv.org·6d
🧠Large Language Models (LLMs)
GraphVSSM: Graph Variational State-Space Model for Probabilistic Spatiotemporal Inference of Dynamic Exposure and Vulnerability for Regional Disaster Resilience...
arxiv.org·1h
🧠Large Language Models (LLMs)
Causality and Interpretability for Electrical Distribution System faults
arxiv.org·1h
⚙️AI Infrastructure Automation
Dimensions of Vulnerability in Visual Working Memory: An AI-Driven Approach to Perceptual Comparison
arxiv.org·5d
📊AI Performance Profiling
Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection
arxiv.org·4d
🧠Large Language Models (LLMs)
PunchPulse: A Physically Demanding Virtual Reality Boxing Game Designed with, for and by Blind and Low-Vision Players
arxiv.org·1h
⚡Real-time AI Systems
SMART-Ship: A Comprehensive Synchronized Multi-modal Aligned Remote Sensing Targets Dataset and Benchmark for Berthed Ships Analysis
arxiv.org·1h
📊AI Performance Profiling
AI-Driven Cybersecurity Threat Detection: Building Resilient Defense Systems Using Predictive Analytics
arxiv.org·1h
📊AI Performance Profiling
FairReason: Balancing Reasoning and Social Bias in MLLMs
arxiv.org·4d
🧠Large Language Models (LLMs)
J4CC, A Frame for Communication Control
arxiv.org·1d
🚀LLM serving frameworks
Attack Anything: Blind DNNs via Universal Background Adversarial Attack
arxiv.org·1h
📊AI Performance Profiling
Physics-Informed Data-Driven Control of Nonlinear Polynomial Systems with Noisy Data
arxiv.org·1h
✨Model optimizations in LLMs