✨Seeing the Forest and the Trees: Query-Aware Tokenizer for Long-Video Multimodal Language Models

📝 Summary:
QTSplus is a query-aware token selector for long-video multimodal language models. It dynamically selects the most important visual tokens based on a text query, significantly compressing vision data and reducing latency. This method maintains overall accuracy and enhances temporal understanding ...

🔹 Publication Date: Published on Nov 14

🔹 Paper Links:
• arXiv Page: https://huggingface.co/collections/AlpachinoNLP/qtsplus
• PDF: https://arxiv.org/pdf/2511.11910
• Project Page: https://qtsplus.github.io/
• Github: https://github.com/Siyou-Li/QTSplus

🔹 Models citing this paper:
• https://huggingface.co/AlpachinoNLP/QTSplus-3B
• https://huggingface.co/AlpachinoNLP/QTSplus-3B-FT

✨ Spaces citing this paper:
• https://huggingface.co/spaces/AlpachinoNLP/QTSplus-3B

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#MultimodalAI #VideoAI #LLM #Tokenization #ComputerVision

✨SampoNLP: A Self-Referential Toolkit for Morphological Analysis of Subword Tokenizers

📝 Summary:
SampoNLP is a new corpus-free toolkit for creating morphological lexicons for Uralic languages. It was used to systematically evaluate BPE tokenizers, identifying optimal vocabulary sizes and demonstrating BPE's limitations for these highly agglutinative languages.

🔹 Publication Date: Published on Jan 8

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.04469
• PDF: https://arxiv.org/pdf/2601.04469
• Github: https://github.com/AragonerUA/SampoNLP

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#NLP #ComputationalLinguistics #Morphology #Tokenization #UralicLanguages

✨What Really Controls Temporal Reasoning in Large Language Models: Tokenisation or Representation of Time?

📝 Summary:
MultiTempBench evaluates LLMs multilingual temporal reasoning across various calendars and languages. It finds that tokenization quality, specifically fragmentation of temporal data, is a major bottleneck that severely reduces accuracy in low-resource languages and less common calendar formats.

🔹 Publication Date: Published on Mar 19

🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.19017
• PDF: https://arxiv.org/pdf/2603.19017
• Github: https://github.com/gagan3012/mtb

==================================

For more data science resources:
✓ https://xn--r1a.website/DataScienceT

#LLM #TemporalReasoning #Tokenization #MultilingualAI #NLP