系统评估20余种初始化策略，为LLM词汇扩展提供实用指南。
arXiv:2608.03494v1 Announce Type: cross Abstract: Vocabulary extension is an efficient way to adapt pretrained large language models (LLMs) to new lan…
阿里新一代语音识别大模型，专攻行业专业词识别，还能输出结构化文本，利好AI落地场景。
IT之家 7 月 31 日消息，阿里巴巴今日发布语音识别大模型 Qwen-Audio-3.0-ASR-Flash 。简单来说，就是让 AI 更好地听懂专业词汇。 Qwen-Audio-3.0-ASR-Flash 主要在上下文一致性、行业词识别和热词定制化三个维度做了系统性的优化，同时让模型具备语音润…
提出一种原地扩展分词器的方案，解决预训练大模型因后期语言加入导致的 token 效率低下问题，降低延迟与能耗。
arXiv:2607.15232v1 Announce Type: cross Abstract: A tokenizer fixed at the start of pre-training allocates vocabulary in proportion to the pre-trainin…
一站式搞定AI术语，从AGI到幻觉，这份年度必备词汇表让你不再迷茫
The rise of AI has brought an avalanche of new terms and slang. Here is a glossary with definitions of some of the most important words and phrases yo…
推理时校准提议，无需重新训练即可提升开放词汇目标检测精度，值得关注的新方案。
arXiv:2607.01759v1 Announce Type: cross Abstract: Open-vocabulary object detection aims to localize and classify objects beyond the fixed set of categ…
揭秘共享词汇任务表征如何解释LLM行为变异，为理解大模型行为差异提供新理论框架
arXiv:2604.22027v2 Announce Type: replace-cross Abstract: One of the most common complaints about large language models (LLMs) is their prompt sensiti…
从信息几何视角揭示模型更新与词汇规模的对齐机制，为大规模优化提供新洞见。
arXiv:2606.27242v1 Announce Type: new Abstract: Training-free source selection for LLM families with shared vocabularies arises in scientific string d…
换一个字母，单词接龙还能这么玩！Wordit 挑战你的四字母词汇量，和全球玩家实时比拼脑力。
Hi everyone, I got this idea for a game where, starting from a four letter word you need to go as deep as you can in your vocabulary, changing only on…
打破罗马乌尔都语模型词汇瓶颈，几何保持扩展法让低资源语言AI更强大。
arXiv:2606.22478v1 Announce Type: new Abstract: Multilingual Language Models like mBERT are widely used for low-resource NLP, yet their adaptation to …
从语义、词汇到句法，三层剖析大模型如何理解与处理人类隐喻，为NLP可解释性提供新洞见。
arXiv:2510.04120v2 Announce Type: replace Abstract: Large language models (LLMs) achieve strong performance on metaphor detection and interpretation t…
利用CLIP的视觉语言先验增强DINO检测器，提出名为VL-DINO的开放词汇目标检测新方法。
arXiv:2606.11546v1 Announce Type: new Abstract: Vision-language models like CLIP can provide rich semantic priors for open-vocabulary object detection…
提出推理时对齐迁移新方法，跨词汇混合logit无需额外训练即可转移对齐能力，为大模型高效部署提供新思路。
arXiv:2606.12342v1 Announce Type: cross Abstract: Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comp…
颠覆传统背单词，AI对话模式用可理解输入让语言习得更高效。
Article URL: https://manateavagner.com/news/translate-conversation-mode-language-learning Comments URL: https://news.ycombinator.com/item?id=48487243 …
词汇驱动的图记忆库，让AI代理高效存储和调用记忆，多种部署方式轻松上手。
Article URL: https://github.com/TjWheeler/deep-memory Comments URL: https://news.ycombinator.com/item?id=48455368 Points: 1 # Comments: 1
挑战无监督单词发现中传统评价指标，提出新视角下的词典评估方法。
arXiv:2606.06183v1 Announce Type: cross Abstract: Building a lexicon from discovered word-like units is a central goal in zero-resource speech process…
研究发现词汇性对LLM的持久影响，为语言模型认知再添新视角。
arXiv:2606.02750v1 Announce Type: new Abstract: Representations extracted from large language models (LLMs) play an important role in many downstream …
自动识别LLM中的词汇对齐与偏好阶段转变，16页研究揭示模型行为动态变化。
arXiv:2606.03165v1 Announce Type: cross Abstract: The language used by digital chat assistants such as ChatGPT can diverge from human expectations (mi…
提出一种无需数据整理的三角测量指标，精准隔离LLM在偏好学习阶段的词汇偏差。
arXiv:2606.00334v1 Announce Type: cross Abstract: Various language domains have undergone remarkable changes in recent years; these shifts are largely…
首个亚1B阿拉伯语专用开源模型，通过词汇注入实现边缘设备高效部署，填补小规模语言模型空白。
arXiv:2605.28827v1 Announce Type: cross Abstract: Open Arabic large language models split into two classes: sub-1B multilingual models that treat Arab…
新指标WCS精准测量LLM词汇可达性，揭示采样策略如何限制输出词汇多样性，为模型评估提供新视角。
arXiv:2605.27268v1 Announce Type: cross Abstract: Modern Large Language Models (LLMs) are often criticized for producing repetitive and homogeneous te…