TimePre: Bridging Accuracy, Efficiency, and Stability in Probabilistic Time-Series Forecasting

A new method called NVGS has been proposed to enhance 3D Gaussian Splatting by learning viewpoint-dependent visibility functions for occlusion culling, addressing the limitations posed by the semi-transparent nature of Gaussians. This approach utilizes a shared MLP across instances and integrates neural queries into an instanced software rasterizer, improving rendering efficiency and image quality.

Recent research has demonstrated that the impact of context in vanilla transformer models can be represented through token-dependent, rank-1 patches to MLP weights. This study extends this theory to modern Large Language Models (LLMs), providing analytical solutions for Gemma-style transformer blocks and generalizing the findings for multi-layer models.

FHE-Agent has been introduced as an innovative framework designed to automate the configuration of Fully Homomorphic Encryption (FHE) using the CKKS scheme, addressing the complexities that typically hinder its practical deployment in privacy-preserving machine learning as a service (MLaaS). The framework integrates a Large Language Model (LLM) to streamline the configuration process, making it more accessible to practitioners without deep cryptographic expertise.

A recent study has introduced a novel approach to in-camera color mapping by transitioning from traditional one-dimensional correlated color temperature (CCT) methods to a two-dimensional chromaticity space. This shift aims to enhance colorimetric accuracy, particularly in scenarios involving modern lighting technologies like LEDs, which often deviate from the Planckian locus.

A recent study has shown that semantic segmentation networks trained on specific lidar types struggle to generalize to new lidar systems without additional intervention. The research focuses on leveraging vision foundation models (VFMs) to enhance unsupervised domain adaptation for semantic segmentation of lidar point clouds, revealing key architectural insights for improving performance across different domains.

The introduction of CleverDistiller marks a significant advancement in self-supervised cross-modal knowledge distillation, enabling the transfer of features from 2D vision foundation models to 3D LiDAR-based models. This framework utilizes a direct feature similarity loss and a multi-layer perceptron projection head, enhancing the learning of complex semantic dependencies in autonomous driving applications.