A new open-source package called Varmapack simulates VARMA time series exactly from the first observation, eliminating ...
October 19, 2026, 09:04:24 to October 20, 09:04:24 (JST, fixed)Adoption: 10 independent items.Conclusion of this report: ...
Researchers at Tsinghua University have developed a Series Saliency module guided by large language models that improves the ...
Introduction: The Dawn of Next-Generation Financial AI Architecture and New Trends on GitHubOn October 14, 2026, a new ...
Mistral AI Releases Timestral: A 209M Forecasting Model Family That Outperforms Google’s TimesFM-3
Mistral Timestral is a time series foundation model family, 5M to 209M parameters, forecasting zero-shot on a CPU.
Frame-wise 4-step 🤗 Huggingface Rich dynamics and high quality Frame-wise 2-step🔥 🤗 Huggingface The first frame-wise 2-step model even better than 4-step Frame-wise 1-step 🤗 Huggingface Extremely ...
AI startup Visko brought Orbis, its interactive, continuously streaming video world model, to production with TPUs in just 30 days.
t0-gamma is an open-weights time-series forecasting foundation model from The Forecasting Company. t0 is a transformer-based model that produces probabilistic multi-horizon forecasts and natively ...
A GPU kernel is the code that runs on the GPU when you call an operation like torch.matmul, as thousands of copies at once.
Trained with reinforcement learning in real environments, Mellum2.1 is built for coding agents and fast sub-agents that run ...
A curated collection of papers, benchmarks, surveys, and tools for model quantization, covering low-bit networks, LLMs, multimodal and generative models, vector and lattice quantization, and efficient ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results