mcpc.site把论文句子读懂
🔥 1 天
← 全部句式 g26 · L3
X + V + A ..., and B ...(B 后面省略了同一个 V)

X 做了 A,也(做了)B——后半句省掉了重复的动词或介词

省略并列

为什么这么写

读懂 + 会看

读法:并列结构里,and 后面常常缺一个动词或介词,缺的那个就是前面出现过的那个。还原办法:把前半句的谓语补到后半句去试读。例句里 employs mask-guided ... distillation ..., and relative-pose ... distillation to enforce ...,后半句其实共享 employs;consists of a Reasoner ..., and a Planner ... 共享 consists of。为什么作者这么写:英语不喜欢重复同一个动词,能省就省,句子更紧凑;但对中国读者来说,「缺一块」最容易读崩,会误以为后半句没有谓语。判断信号:and 两边结构对称(都是名词短语、都带 to do),基本就是共享成分;如果 and 后面是完整的主谓,那就不是省略,而是两个独立分句。

论文里的例子

2 条

This framework employs mask-guided depth-aware distillation to retain fine-grained metric structures by emphasizing geometrically informative regions, and relative-pose relational distillation to enforce cross-view spatial consistency through pose-induced geometric relations.

LiAuto-GeoX (arXiv 2606.05774) · Abstract

At a high level, ColaVLA consists of a Cognitive Latent Reasoner that distills scene evidence into compact meta-action priors, and a Hierarchical Parallel Planner that converts these priors to multi-scale trajectories under a causality-preserving scheme.

ColaVLA (arXiv 2512.22939) · 1. Introduction

练这几句

拆句练习
006 Existing large-scale visual geometry models typically require substantial computational resources and lack the long-range geometric fidelity, surround-view consistency, and real-time efficiency demanded by dynamic driving environments. → 007 This framework employs mask-guided depth-aware distillation to retain fine-grained metric structures by emphasizing geometrically informative regions, and relative-pose relational distillation to enforce cross-view spatial consistency through pose-induced geometric relations. → 010 During inference, the teacher, LiDAR inputs, and mask adapter are removed; only the compact student is deployed to produce dense 3D reconstruction in a single forward pass. → 020 Compared to the base VLM, VGGDrive achieves a 2.72 improvement in PDMS, while VGGT-Dist and VGGT-Add show only marginal performance gains. → 028 Remarkably, with only a 0.5B Qwen2.5 model as MLLM backbone, DrivePI as a single unified model matches or exceeds both existing VLA models and specialized VA models. → 030 Next, a spatial projector is utilized to map the latent BEV features into the language space and obtain vision tokens. → 041 SCIS operationalizes the do-operator within the neural network by leveraging a pre-computed confounder dictionary to represent latent driving contexts and performing a parameterized causal intervention on the efficient vectorized scene queries of the VAD model. → 044 The above analysis reveals that causal confounding in the VAD framework is not a single failure point but a cascading systemic issue. →

怎么用

写一句含两个并列宾语的话(「我们的框架包含 A……,以及 B……」),故意省掉第二个动词,然后标出被省掉的是哪个词、它和前半句的哪个词是同一个。