Show HN: I built an edge ML system to detect and classify trick-or-treaters
🔍Type Checkers
Flag this post
Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models
arxiv.org·12h
📊Gradient Accumulation
Flag this post
MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
arxiv.org·12h
📊Gradient Accumulation
Flag this post
Enhancing riverine cyanobacterial bloom prediction: A hybrid deep learning approach combining wavelet decomposition, double-layer LSTM, ARIMA, and residual comp...
sciencedirect.com·1h
📊Gradient Accumulation
Flag this post
Readable Code Is Unreadable
🔍Type Checkers
Flag this post
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
arxiv.org·12h
👁️Attention Optimization
Flag this post
Towards Reliable Pediatric Brain Tumor Segmentation: Task-Specific nnU-Net Enhancements
arxiv.org·12h
🏎️TensorRT
Flag this post
Towards Automated Petrography
arxiv.org·12h
📊Gradient Accumulation
Flag this post
Multi-refined Feature Enhanced Sentiment Analysis Using Contextual Instruction
arxiv.org·12h
🛠Ml-eng
Flag this post
Geonum – geometric number library for unlimited dimensions with O(1) complexity
✂️CUTLASS
Flag this post
Zero-RAG: Towards Retrieval-Augmented Generation with Zero Redundant Knowledge
arxiv.org·12h
🎓Model Distillation
Flag this post
Knowledge Elicitation with Large Language Models for Interpretable Cancer Stage Identification from Pathology Reports
arxiv.org·12h
🎓Model Distillation
Flag this post
LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
machinelearning.apple.com·1d
⚡Flash Attention
Flag this post
RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks
arxiv.org·12h
🤖AI Coding Tools
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
Loading...Loading more...