IEEE

Learning-Based Model Predictive Control With High-Probability Safety Using Gaussian Mixture Models

Abstract: This article introduces a learning-based model predictive control (MPC) framework that leverages Gaussian mixture models (GMMs) to address dynamic system uncertainties effectively. To ...
GitHub

[CVPR 2025] UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting

UniPre3D is the first unified pre-training method for 3D point clouds that effectively handles both object- and scene-level data through cross-modal Gaussian splatting. Our proposed pre-training task ...
IEEE

Hierarchical Gaussian Mixture Model Splatting for Efficient and Part Controllable 3D Generation

Abstract: 3D content creation has achieved significant progress in terms of both quality and speed. Although current Gaussian Splatting-based methods can produce 3D objects within seconds, they are ...
GitHub

Z80-μLM: A Retrocomputing Micro Language Model

Z80-μLM is a 'conversational AI' that generates short character-by-character sequences, with quantization-aware training (QAT) to run on a Z80 processor with 64kb of ram. The root behind this project ...
marktechpost

Tavus Launches Phoenix-4: A Gaussian-Diffusion Model Bringing Real-Time Emotional Intelligence And Sub-600ms Latency To Generative Video AI

The ‘uncanny valley’ is the final frontier for generative video. We have seen AI avatars that can talk, but they often lack the soul of human interaction. They suffer from stiff movements and a lack ...