Simple Methods Defend RAG Systems Well Against Real-World Attacks
arxiv.org·1d
📊AI Performance Profiling
Veli: Unsupervised Method and Unified Benchmark for Low-Cost Air Quality Sensor Correction
arxiv.org·10h
🧠Large Language Models (LLMs)
AI-Driven Cybersecurity Threat Detection: Building Resilient Defense Systems Using Predictive Analytics
arxiv.org·1d
📊AI Performance Profiling
AoI-Aware Resource Allocation with Deep Reinforcement Learning for HAPS-V2X Networks
arxiv.org·2d
⚙️AI Infrastructure Automation
Cognitive Loop via In-Situ Optimization: Self-Adaptive Reasoning for Science
arxiv.org·10h
⚙️AI Infrastructure Automation
Key-Augmented Neural Triggers for Knowledge Sharing
arxiv.org·10h
🧠Large Language Models (LLMs)
Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges
arxiv.org·2d
🧠Large Language Models (LLMs)
Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
arxiv.org·1d
🤖Agents using LLMs
LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning
arxiv.org·10h
🧠Large Language Models (LLMs)
Kernel-Based Sparse Additive Nonlinear Model Structure Detection through a Linearization Approach
arxiv.org·1d
🧠Large Language Models (LLMs)
MIDAR: Mimicking LiDAR Detection for Traffic Applications with a Lightweight Plug-and-Play Model
arxiv.org·10h
📊AI Performance Profiling
Who Should Run Advanced AI Evaluations -- AISIs?
arxiv.org·10h
⚙️AI Infrastructure Automation
From EMR Data to Clinical Insight: An LLM-Driven Framework for Automated Pre-Consultation Questionnaire Generation
arxiv.org·2d
🧠Large Language Models (LLMs)
SynAdapt: Learning Adaptive Reasoning in Large Language Models via Synthetic Continuous Chain-of-Thought
arxiv.org·2d
🧠Large Language Models (LLMs)
Pulse Shape Discrimination Algorithms: Survey and Benchmark
arxiv.org·10h
🔢Quantization of LLMs
BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS
arxiv.org·10h
⚙️AI Infrastructure Automation
On Conformal Machine Unlearning
arxiv.org·10h
✨Model optimizations in LLMs
PentestJudge: Judging Agent Behavior Against Operational Requirements
arxiv.org·10h
🤖Agents using LLMs
AI on the Pulse: Real-Time Health Anomaly Detection with Wearable and Ambient Intelligence
arxiv.org·10h
⚡Real-time AI Systems
Toward using explainable data-driven surrogate models for treating performance-based seismic design as an inverse engineering problem
arxiv.org·2d
✨Model optimizations in LLMs