Humans and neural networks show similar patterns of transfer and interference
๐๏ธAttention Optimization
Flag this post
Scaling Coding-Agent RL to 32x H100s. 160% Improvement on Stanford's TBench
๐คAI Coding Tools
Flag this post
Temporal Fusion Transformer for Multi-Horizon Probabilistic Forecasting of Weekly Retail Sales
arxiv.orgยท19h
๐ONNX
Flag this post
Spatial Incompatibility Witnesses for Quantum Temporal Correlations
arxiv.orgยท19h
๐Kernel Fusion
Flag this post
Eyes on Target: Gaze-Aware Object Detection in Egocentric Video
arxiv.orgยท19h
๐๏ธAttention Optimization
Flag this post
Molecular Alchemy: AI-Powered Design of Novel Compounds by Arvind Sundararajan
๐Model Distillation
Flag this post
LangChain vs LangGraph: A Beginnerโs Guide to Building Smarter AI Workflows
hackernoon.comยท1d
๐คAI Coding Tools
Flag this post
[P] triplet-extract: GPU-accelerated triplet extraction via Stanford OpenIE in pure Python
๐ONNX
Flag this post
VISAT: Benchmarking Adversarial and Distribution Shift Robustness in Traffic Sign Recognition with Visual Attributes
arxiv.orgยท1d
๐งฎcuDNN
Flag this post
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
arxiv.orgยท19h
๐๏ธAttention Optimization
Flag this post
Region-Aware Reconstruction Strategy for Pre-training fMRI Foundation Model
arxiv.orgยท19h
๐Gradient Accumulation
Flag this post
Extensive FPGA and ASIC resource comparison for blind I/Q imbalance estimators and compensators
sciencedirect.comยท8h
๐ฏTensor Cores
Flag this post
Deep Learning-Accelerated Shapley Value for Fair Allocation in Power Systems: The Case of Carbon Emission Responsibility
arxiv.orgยท19h
๐๏ธTensorRT
Flag this post
Feature Importance Guided Random Forest Learning with Simulated Annealing Based Hyperparameter Tuning
arxiv.orgยท19h
โฑ๏ธBenchmarking
Flag this post
The Curvature Rate {\lambda}: A Scalar Measure of Input-Space Sharpness in Neural Networks
arxiv.orgยท19h
๐Model Quantization
Flag this post
The Power of AI in Transforming Visual Marketing Strategies
๐๏ธAttention Optimization
Flag this post
MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
arxiv.orgยท19h
๐Gradient Accumulation
Flag this post
Branched Signature Model
arxiv.orgยท19h
๐Kernel Fusion
Flag this post
Loading...Loading more...