Hebbian Memory-Augmented Recurrent Networks: Engram Neurons in Deep Learning
arxiv.org·5d
🔍Retrieval-augmented generation
InsurTech innovation using natural language processing
arxiv.org·5d
🤖Agents using LLMs
X-NeMo: Expressive Neural Motion Reenactment via Disentangled Latent Attention
arxiv.org·3d
🔢Quantization of LLMs
MetaCLIP 2: A Worldwide Scaling Recipe
arxiv.org·5d
🔍Retrieval-augmented generation
Modern Uyghur Dependency Treebank (MUDT): An Integrated Morphosyntactic Framework for a Low-Resource Language
arxiv.org·5d
🔍Retrieval-augmented generation
Beyond Text: Probing K-12 Educators' Perspectives and Ideas for Learning Opportunities Leveraging Multimodal Large Language Models
arxiv.org·6d
🔍Retrieval-augmented generation
Decoding Neural Signatures of Semantic Evaluations in Depression and Suicidality
arxiv.org·4d
🔢Quantization of LLMs
Invisible Architectures of Thought: Toward a New Science of AI as Cognitive Infrastructure
arxiv.org·3d
⚙️AI Infrastructure Automation
PointGauss: Point Cloud-Guided Multi-Object Segmentation for Gaussian Splatting
arxiv.org·22h
🔢Quantization of LLMs
Optimizing LLMs for Performance and Accuracy with Post-Training Quantization
developer.nvidia.com·5d
🔢Quantization of LLMs
Can We End the Cat-and-Mouse Game? Simulating Self-Evolving Phishing Attacks with LLMs and Genetic Algorithms
arxiv.org·5d
🤖Agents using LLMs
SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods
arxiv.org·5d
🔍Retrieval-augmented generation
Green Computing: The Ultimate Carbon Destroyer for a Sustainable Future
arxiv.org·22h
🔧Systems-level optimizations for LLM serving
Learning from Heterogeneous Structural MRI via Collaborative Domain Adaptation for Late-Life Depression Assessment
arxiv.org·4d
🔍Retrieval-augmented generation
FGFP: A Fractional Gaussian Filter and Pruning for Deep Neural Networks Compression
arxiv.org·4d
🔢Quantization of LLMs
Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting
arxiv.org·5d
💬Prompt optimizations for LLM serving
Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and Approximation
arxiv.org·5d
🔍Retrieval-augmented generation
Interpretable Anomaly-Based DDoS Detection in AI-RAN with XAI and LLMs
arxiv.org·5d
🔧Systems-level optimizations for LLM serving
Informing AI Risk Assessment with News Media: Analyzing National and Political Variation in the Coverage of AI Risks
arxiv.org·3d
⚡Real-time AI Systems
Graded Transformers: A Symbolic-Geometric Approach to Structured Learning
arxiv.org·6d
🔍Retrieval-augmented generation