Yinglin Wang

In the context of novel view synthesis, 3D Gaussian Splatting (3DGS) has recently emerged as an efficient and competitive counterpart to Neural Radiance Field (NeRF), enabling high-fidelity photorealistic rendering in real time. Beyond novel view synthesis, the explicit and compact nature of 3DGS enables a wide range of downstream applications that require geometric and semantic understanding. This survey provides a comprehensive overview of recent progress in 3DGS applications. It first reviews the reconstruction preliminaries of 3DGS, followed by the problem formulation, 2D foundation models, and related NeRF-based research areas that inform downstream 3DGS applications. We then categorize 3DGS applications into three foundational tasks: segmentation, editing, and generation, alongside additional functional applications built upon or tightly coupled with these foundational capabilities. For each, we summarize representative methods, supervision strategies, and learning paradigms, highlighting shared design principles and emerging trends. Commonly used datasets and evaluation protocols are also summarized, along with a comparative analysis of recent methods across public benchmarks. To support ongoing research and development, a continually updated repository of papers, code, and resources is maintained at https://github.com/heshuting555/Awesome-3DGS-Applications.

Large language models (LLMs) have shown strong potential for medical natural language processing, yet adapting them to diverse clinical tasks simultaneously (e.g., entity recognition, terminology normalization, classification, report generation, and medical dialogue) remains challenging due to high fine-tuning costs and negative transfer across tasks. To address this, we propose DoubleGate-MOELoRA (DG-MOELoRA), a parameter-efficient multi-task fine-tuning framework that improves Mixture-of-Experts (MoE) routing in LoRA-based expert pools. Unlike prior MoE-LoRA approaches that rely on a single control signal, DG-MOELoRA integrates dual gating: (i) a multi-head attention task gate that models complex inter-task relationships for robust task-conditioned expert routing, and (ii) a SwiGLU-enhanced token gate that preserves token-level semantic modulation within each expert to enhance representational diversity. We further provide a gradient-level analysis that reveals two fundamental gating failure modes—gradient competition under heterogeneous inputs and gradient misalignment under homogeneous multi-branch gating—and show how our design resolves both issues. Experiments on PromptCBLUE, covering eight representative medical NLP tasks, demonstrate that DG-MOELoRA consistently outperforms strong PEFT baselines while maintaining high parameter efficiency, and remains robust across multiple backbone LLMs. These results indicate that DG-MOELoRA is an effective and practical method for medical multi-task adaptation with limited tuning budgets.

The natural language model BERT uses a large-scale unsupervised corpus to accumulate rich linguistic knowledge during its pretraining stage, and then, the information is fine-tuned for specific downstream tasks, which greatly improves the understanding capability of various natural language tasks. For some specific tasks, the capability of the model can be enhanced by introducing external knowledge. In fact, these methods, such as ERNIE, have been proposed for integrating knowledge graphs into BERT models, which significantly enhanced its capabilities in related tasks such as entity recognition. However, for two types of tasks, commonsense causal reasoning and predicting the ending of stories, few previous studies have combined model modification and process optimization to integrate external knowledge. Therefore, referring to ERNIE, in this paper, we propose enhanced language representation with event chains (EREC), which focuses on keywords in the text corpus and their implied relations. Event chains are integrated into EREC as external knowledge. Furthermore, various graph networks are used to generate embeddings and to associate keywords in the corpus. Finally, via multi-task training, external knowledge is integrated into the model generated in the pretraining stage so as to enhance the effect of the model in downstream tasks. The experimental process of the EREC model is carried out with a three-stage design, and the experimental results show that EREC has a deeper understanding of the causal relationship and event relationship contained in the text by integrating the event chains, and it achieved significant improvements on two specific tasks.

Reasoning on temporal knowledge graphs, which aims to infer new facts from existing knowledge, has attracted extensive attention and in-depth research recently. One of the important tasks of reasoning on temporal knowledge graphs is entity prediction, which focuses on predicting the missing objects in facts at current time step when relevant histories are known. The problem is that, for entity prediction task on temporal knowledge graphs, most previous studies pay attention to aggregating various semantic information from entities but ignore the impact of semantic information from relation types. We believe that relation types is a good supplement for our task and making full use of semantic information of facts can promote the results. Therefore, a framework of Enhanced Relational Graph Convolution Network (ERGCN) is put forward in this paper. Rather than only considering representations of entities, the context semantic information of both relations and entities is considered and merged together in this framework. Experimental results show that the proposed approach outperforms the state-of-the-art methods.