The Evolution from RAG to Agentic RAG to Agent Memory
leoniemonigatti.com·4h·
Discuss: Hacker News
🎓Model Distillation
Flag this post
A Thesis and Playbook for Edge AI
ondeviceguy.substack.com·1d·
Discuss: Substack
⚡ONNX Runtime
Flag this post
HyFormer-Net: A Synergistic CNN-Transformer with Interpretable Multi-Scale Fusion for Breast Lesion Segmentation and Classification in Ultrasound Images
arxiv.org·12h
🧮cuDNN
Flag this post
Adaptive Stemming via Graph-Augmented Recurrent Variational Autoencoders
dev.to·2d·
Discuss: DEV
🏎️TensorRT
Flag this post
Functional embeddings enable Aggregation of multi-area SEEG recordings over subjects and sessions
arxiv.org·1d
📉Model Quantization
Flag this post
H-FA: A Hybrid Floating-Point and Logarithmic Approach to Hardware Accelerated FlashAttention
arxiv.org·12h
⚡Flash Attention
Flag this post
A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios
arxiv.org·12h
🎓Model Distillation
Flag this post
Towards Automated Petrography
arxiv.org·12h
📉Model Quantization
Flag this post
How neuroscientists are using AI
thetransmitter.org·12h
⚡ONNX Runtime
Flag this post
Synthesized Generative Modeling via Graph-Constrained Semantic Embedding
dev.to·2d·
Discuss: DEV
🎓Model Distillation
Flag this post
Benchmarking Generative AI Against Bayesian Optimization for Constrained Multi-Objective Inverse Design
arxiv.org·12h
🎓Model Distillation
Flag this post
CoT-Saliency: Unified Chain-of-Thought Reasoning for Heterogeneous Saliency Tasks
arxiv.org·12h
🏎️TensorRT
Flag this post
Investigating Label Bias and Representational Sources of Age-Related Disparities in Medical Segmentation
arxiv.org·12h
🏎️TensorRT
Flag this post
It Doesn’t Need to Be a Chatbot
towardsdatascience.com·16h
🤖AI Coding Tools
Flag this post
Disciplined Biconvex Programming
arxiv.org·12h
📉Model Quantization
Flag this post
Towards Reliable Pediatric Brain Tumor Segmentation: Task-Specific nnU-Net Enhancements
arxiv.org·12h
🏎️TensorRT
Flag this post
ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
arxiv.org·12h
🏎️TensorRT
Flag this post
ReLaX-Net: Reusing Layers for Parameter-Efficient Physical Neural Networks
arxiv.org·12h
🎯Tensor Cores
Flag this post
Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes
arxiv.org·12h
🏎️TensorRT
Flag this post
Deep Learning Approach to Anomaly Detection in Enterprise ETL Processes with Autoencoders
arxiv.org·12h
🎓Model Distillation
Flag this post