1
史前动物博物馆：和孩子一起看双语 3D 小博物馆，18 只恐龙
没有追逐撕咬的安静恐龙博物馆，爸爸用代码为女儿造了一座能转着看的双语3D史前动物园
女儿3岁时，喜欢恐龙，却害怕恐龙打架。 看到电视里的恐龙追逐、撕咬，她会躲到爸爸身后；但过一会儿，又会偷偷探出头继续看。 于是，一位程序员爸爸做了一座“安静版恐龙博物馆”：去掉追逐和战斗，只留下可以慢慢观察的史前动物。 现在，孩子可以像逛博物馆一样，自己旋转、放大、认识这些远古生命。 来自发现频道的
2
TIDES: A Longitudinal Bilingual Dataset for Modeling Multi-Party Social Dynamics
纵向双语多方社交数据集，为建模真实对话中的社会动态提供全新基准。
arXiv:2608.01724v1 Announce Type: cross Abstract: Group conversations are fundamental to human collaboration, yet standard large language models (LLMs…
3
Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings
给大模型文本打上隐形水印，双语义嵌入让盗版无处遁形
arXiv:2606.31602v1 Announce Type: new Abstract: This work presents Dual-Embedding Watermarking (DEW), a semantic watermarking scheme for large languag…
4
Humor Style Drives Laughter, Topic Shapes Acceptability: Evaluating Bilingual Personal and Political Robot-Delivered AI Jokes
AI幽默风格影响笑声，主题决定接受度，双语个人与政治笑话评估揭示机器人讲笑话的关键
arXiv:2606.13256v1 Announce Type: cross Abstract: Humor plays a central role in human social relationships, and recent advances in computational humor…
5
Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs
英中代码切换语音识别新突破，用直接偏好优化让Audio LLM准确理解双语混用
arXiv:2605.23975v1 Announce Type: new Abstract: Audio large language models (Audio LLMs) exhibit systematic failures in transcribing code-switching sp…