How Your Brain Creates ‘Aha’ Moments and Why They Stick
quantamagazine.org·2h
⚡Flash Attention
Flag this post
The Death of the Demo
⏱️Benchmarking
Flag this post
Microglial-Mediated Neurotoxicity Prediction via Stochastic Hypernetwork Analysis of Amyloid Plaque Interactions
📊Gradient Accumulation
Flag this post
Self-Supervised Moving Object Segmentation of Sparse and Noisy Radar Point Clouds
arxiv.org·12h
🔗Kernel Fusion
Flag this post
MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
arxiv.org·12h
⚡ONNX Runtime
Flag this post
Variational Geometric Information Bottleneck: Learning the Shape of Understanding
arxiv.org·12h
🏎️TensorRT
Flag this post
MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
arxiv.org·1d
📊Gradient Accumulation
Flag this post
ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for LargeVision-and-Language Models
🏎️TensorRT
Flag this post
How to Design Efficient Memory Architectures for Agentic AI Systems
pub.towardsai.net·22h
⚡Flash Attention
Flag this post
FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding
arxiv.org·1d
🧩Attention Kernels
Flag this post
Hydra: Dual Exponentiated Memory for Multivariate Time Series Analysis
arxiv.org·1d
📊Gradient Accumulation
Flag this post
Probabilistic Robustness for Free? Revisiting Training via a Benchmark
arxiv.org·1d
📊Gradient Accumulation
Flag this post
Anatomically Constrained Transformers for Echocardiogram Analysis
arxiv.org·1d
📉Model Quantization
Flag this post
BoolSkel: Unlocking Boolean Network Efficiency Through Structural Pruning by Arvind Sundararajan
🔗Kernel Fusion
Flag this post
CytoNet: A Foundation Model for the Human Cerebral Cortex
arxiv.org·12h
🏎️TensorRT
Flag this post
Beyond ImageNet: Understanding Cross-Dataset Robustness of Lightweight Vision Models
arxiv.org·1d
🧮cuDNN
Flag this post
Loading...Loading more...