A Few Words Can Distort Graphs: Knowledge Poisoning Attacks on Graph-based Retrieval-Augmented Generation of Large Language Models
arxiv.org·4h
🧠Large Language Models (LLMs)
Neuromorphic Cybersecurity with Semi-supervised Lifelong Learning
arxiv.org·4h
🧠Large Language Models (LLMs)
Merge-based syntax is mediated by distinct neurocognitive mechanisms: A clustering analysis of comprehension abilities in 84,000 individuals with language defic...
arxiv.org·1d
🧠Large Language Models (LLMs)
T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval
arxiv.org·2d
🔍Retrieval-augmented generation
Plant-Centric Metaverse: A Biocentric-Creation Framework for Ecological Art and Digital Symbiosis
arxiv.org·4h
⚙️AI Infrastructure Automation
Balancing Optimality and Diversity: Human-Centered Decision Making through Generative Curation
arxiv.org·1d
🔍Retrieval-augmented generation
Inequality in the Age of Pseudonymity
arxiv.org·4h
🔍Retrieval-augmented generation
Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning
arxiv.org·4h
🧠Large Language Models (LLMs)
Comparative Analysis of Novel NIRMAL Optimizer Against Adam and SGD with Momentum
arxiv.org·4h
✨Model optimizations in LLMs
Optimal Scheduling Algorithms for LLM Inference: Theory and Practice
arxiv.org·2d
🔧Systems-level optimizations for LLM serving
MARS: A Meta-Adaptive Reinforcement Learning Framework for Risk-Aware Multi-Agent Portfolio Management
arxiv.org·2d
🤖Agents using LLMs
Continual Multiple Instance Learning for Hematologic Disease Diagnosis
arxiv.org·4h
📊AI Performance Profiling
Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment
arxiv.org·4h
🔢Quantization of LLMs
What is Beneath Misogyny: Misogynous Memes Classification and Explanation
arxiv.org·4h
🧠Large Language Models (LLMs)
Who Should Run Advanced AI Evaluations -- AISIs?
arxiv.org·1d
⚙️AI Infrastructure Automation
HeQ: a Large and Diverse Hebrew Reading Comprehension Benchmark
arxiv.org·2d
🧠Large Language Models (LLMs)
Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes
arxiv.org·2d
🧠Large Language Models (LLMs)
RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection
arxiv.org·4h
🔍Retrieval-augmented generation
Breaking New Ground in Software Defect Prediction: Introducing Practical and Actionable Metrics with Superior Predictive Power for Enhanced Decision-Making
arxiv.org·4h
📊AI Performance Profiling
Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detection
arxiv.org·3d
🧠Large Language Models (LLMs)