The semantically interactive radiance field has always been an appealing task for its potential to facilitate user-friendly and automated real-world 3D scene understanding applications. However, it is a challenging task to achieve high quality, efficiency and zero-shot ability at the same time with semantics in radiance fields. In this work, we present FastLGS, an approach that supports real-time open-vocabulary query within 3D Gaussian Splatting (3DGS) under high resolution. We propose the semantic feature grid to save multi-view CLIP features which are extracted based on Segment Anything Model (SAM) masks, and map the grids to low dimensional features for semantic field training through 3DGS. Once trained, we can restore pixel-aligned CLIP embeddings through feature grids from rendered features for open-vocabulary queries. Comparisons with other state-of-the-art methods prove that FastLGS can achieve the first place performance concerning both speed and accuracy, where FastLGS is 98 times faster than LERF, 4 times faster than LangSplat and 2.5 times faster than LEGaussians. Meanwhile, experiments show that FastLGS is adaptive and compatible with many downstream tasks, such as 3D segmentation and 3D object inpainting, which can be easily applied to other 3D manipulation systems.

Multimodal Machine Translation (MMT) leverages additional modalities, such as visual data, to enhance translation accuracy and resolve linguistic ambiguities inherent in text-only approaches. Recent advancements predominantly focus on integrating image information via attention mechanisms or feature fusion techniques. However, current approaches lack explicit mechanisms to quantify and manage the uncertainty during translation process, resulting in the utilization of image information being a black box. This makes it difficult to effectively address the issues of incomplete utilization of visual information and even potential degradation of translation quality when using visual information.To address these challenges, we introduce a novel Uncertainty-Guided Multimodal Machine Translation (UG-MMT) framework that redefines how translation systems handle ambiguity through systematic uncertainty reduction. Designed with plug-and-play flexibility, our framework enables seamless integration into existing MMT systems, requiring minimal modification while delivering significant performance gains.

OBJECTIVE: Predicting breast cancer survival and targeting patients at high-risk of mortality is of crucial importance. METHODS: We built a Bayesian Dynamic Cox (BDCox) model for predicting 5-year overall survival in breast cancer patients using data of the SEER Cancer Registry with 12,840 women. Four feature selection methods were used to identify predictors and enhance parsimony: fast backward variable selection, elastic net, Bayesian Model Average (BMA), and clinical expertise. All resulting models and a baseline full model containing all features were internally validated via bootstrapping and externally validated in the Shanghai Breast Cancer Survival Study. RESULTS: BMA outperformed other feature selection methods in both internal and external validations. The BDCox model with 12 predictors had the best performance. Several predictors showed time-varying associations with survival that are in agreement with previous studies. CONCLUSION: The model developed using BDCox outperformed other prognostic models considered in our study. The internal validation results indicate that the BDCox model is capable of achieving high prediction accuracy (C-statistic: 0.802), and the external validation results showed excellent generalizability of the BDCox model (C-statistic: 0.739). SIGNIFICANCE: We built a dynamic Bayesian model from the large population-based registry SEER for predicting 5-year breast cancer overall survival. The prediction performance of the BDCox model is significantly better than other survival models.