Real-time stock volatility prediction with deep learning on a time-series DB
⚡ONNX Runtime
Flag this post
I tried to go with Google's Flow, but it's a creative gamble — I'm not falling for it
androidpolice.com·2h
⚡Flash Attention
Flag this post
Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information Minimization
arxiv.org·9h
🛠Ml-eng
Flag this post
Weakly Supervised Concept Learning with Class-Level Priors for Interpretable Medical Diagnosis
arxiv.org·9h
🏎️TensorRT
Flag this post
[R] We were wrong about SNNs. The bo.ttleneck isn't binary/sparsity, it's frequency.
👁️Attention Optimization
Flag this post
Isotropic Curvature Model for Understanding Deep Learning Optimization: Is Gradient Orthogonalization Optimal?
arxiv.org·9h
📉Model Quantization
Flag this post
Logic-informed reinforcement learning for cross-domain optimization of large-scale cyber-physical systems
arxiv.org·9h
🎓Model Distillation
Flag this post
Thought-For-Food: Reasoning Chain Induced Food Visual Question Answering
arxiv.org·9h
🧩Attention Kernels
Flag this post
Enhanced Bone Fracture Prediction via Multi-Modal FEA & Deep Learning Integration
🏎️TensorRT
Flag this post
Latent Domain Prompt Learning for Vision-Language Models
arxiv.org·9h
🧩Attention Kernels
Flag this post
DEER: Disentangled Mixture of Experts with Instance-Adaptive Routing for Generalizable Machine-Generated Text Detection
arxiv.org·9h
🏎️TensorRT
Flag this post
On the Structure of Floating-Point Noise in Batch-Invariant GPU Matrix Multiplication
arxiv.org·9h
✂️CUTLASS
Flag this post
AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs
arxiv.org·9h
📊Gradient Accumulation
Flag this post
Deep recurrent-convolutional neural network learning and physics Kalman filtering comparison in dynamic load identification
arxiv.org·9h
🏎️TensorRT
Flag this post
CoT-Saliency: Unified Chain-of-Thought Reasoning for Heterogeneous Saliency Tasks
arxiv.org·9h
🏎️TensorRT
Flag this post
ReLaX-Net: Reusing Layers for Parameter-Efficient Physical Neural Networks
arxiv.org·9h
📊Gradient Accumulation
Flag this post
High Resolution Seismic Waveform Generation using Denoising Diffusion
arxiv.org·9h
🏎️TensorRT
Flag this post
Region-Aware Reconstruction Strategy for Pre-training fMRI Foundation Model
arxiv.org·9h
📊Gradient Accumulation
Flag this post
MambaNetLK: Enhancing Colonoscopy Point Cloud Registration with Mamba
arxiv.org·9h
✂️CUTLASS
Flag this post
Loading...Loading more...