Ubuntu Blog: Edge Networking gets smarter: AI and 5G in action
ubuntu.com·6h
⚡ONNX Runtime
Flag this post
OlmoEarth: A new state-of-the-art Earth observation foundation model family
⚡ONNX Runtime
Flag this post
Synopsys and NVIDIA Forge AI Powered Future for Chip Design and Multiphysics Simulation
semiwiki.com·1d
🌊CUDA Streams
Flag this post
Our newest model: Chandra (OCR)
🔄ONNX
Flag this post
PhysMaster: Mastering Physical Representation for Video Generation viaReinforcement Learning
🎓Model Distillation
Flag this post
Towards 1000-fold Electron Microscopy Image Compression for Connectomics via VQ-VAE with Transformer Prior
arxiv.org·1d
🔄ONNX
Flag this post
TA-LSDiff:Topology-Aware Diffusion Guided by a Level Set Energy for Pancreas Segmentation
arxiv.org·1d
🧮cuDNN
Flag this post
Spot The Ball: A Benchmark for Visual Social Inference
arxiv.org·1d
👁️Attention Optimization
Flag this post
FLoC: Facility Location-Based Efficient Visual Token Compression for Long Video Understanding
arxiv.org·1d
🧩Attention Kernels
Flag this post
Text-guided Fine-Grained Video Anomaly Detection
arxiv.org·1d
🧮cuDNN
Flag this post
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model
arxiv.org·2d
📉Model Quantization
Flag this post
Learning and Leveraging Anisotropy Parameters in ANOVA Approximation
arxiv.org·1d
📉Model Quantization
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·1d
📊Gradient Accumulation
Flag this post
MedRECT: A Medical Reasoning Benchmark for Error Correction in Clinical Texts
arxiv.org·1d
🛠Ml-eng
Flag this post
LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
machinelearning.apple.com·2d
⚡Flash Attention
Flag this post
Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
arxiv.org·1d
👁️Attention Optimization
Flag this post
Loading...Loading more...