IEEE

An Optimized Model With Encoder-Decoder ConvLSTM for Global Ionospheric Forecasting

Abstract: The ionosphere is vital for satellite navigation and radio communication, but observational limitations necessitate ionospheric forecasting. The least squares collocation (LSC) method is ...
GitHub

Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors

Previous research has investigated the application of Multimodal Large Language Models (MLLMs) in understanding 3D scenes by interpreting them as videos. These approaches generally depend on ...
IEEE

Unlocking Generative Priors: A New Membership Inference Framework for Diffusion Models

Abstract: Diffusion models pose risks of privacy breaches and copyright disputes, primarily stemming from the potential utilization of unauthorized data during the training phase. Membership inference ...
GitHub

smiles-encoder: One-hot encoding for simple molecular-input line-entry system (SMILES) strings

smiles-encoder is a Python package used to generate one-hot vectors representing SMILES strings (each string element is a one-hot vector). To contribute to smiles-encoder, make a pull request.
VentureBeat

z.ai's open source GLM-5 achieves record low hallucination rate and leverages new RL 'slime' technique

Chinese AI startup Zhupai aka z.ai is back this week with an eye-popping new frontier large language model: GLM-5. The latest in z.ai's ongoing and continually impressive GLM series, it retains an ...